diff --git "a/papers.csv" "b/papers.csv" --- "a/papers.csv" +++ "b/papers.csv" @@ -47,22 +47,22 @@ Self-Calibrated Cross Attention Network for Few-Shot Segmentation,"Xu, Qianxiong Multi-granularity Interaction Simulation for Unsupervised Interactive Segmentation,"Li, Kehan*; Zhao, Yian; Wang, Zhennan; Cheng, Zesen; Jin, Peng; Ji, Xiangyang; Yuan, Li; Liu, Chang; Chen, Jie",poster,2303.13399,https://arxiv.org/abs/2303.13399,,https://huggingface.co/papers/2303.13399,,,,9,0 Texture Learning Domain Randomization for Domain Generalized Segmentation,"Kim, Sunghwan*; Kim, Dae-hwan; Kim, Hoseong",poster,2303.11546,https://arxiv.org/abs/2303.11546,https://github.com/ssssshwan/TLDR,https://huggingface.co/papers/2303.11546,,,,3,0 Unsupervised Video Object Segmentation with Online Adversarial Self-Tuning,"Su, Tiankang*; Song, Huihui; Liu, Dong; Liu, Bo; Liu, Qingshan",poster,,,,,,,,, -Exploring Open-Vocabulary Semantic Segmentation without Human Labels,"Chen, Jun*; Zhu, Deyao; Qian, Guocheng; Ghanem, Bernard; Yan, Zhicheng; Zhu, Chenchen; Xiao, Fanyi; Elhoseiny, Mohamed; Culatana, Sean",poster,2306.00450,https://arxiv.org/abs/2306.00450,,https://huggingface.co/papers/2306.00450,,,,9,0 +Exploring Open-Vocabulary Semantic Segmentation without Human Labels,"Chen, Jun*; Zhu, Deyao; Qian, Guocheng; Ghanem, Bernard; Yan, Zhicheng; Zhu, Chenchen; Xiao, Fanyi; Elhoseiny, Mohamed; Culatana, Sean",poster,2306.0045,https://arxiv.org/abs/2306.00450,,https://huggingface.co/papers/2306.00450,,,,9,0 RbA: Segmenting Unknown Regions Rejected by All,"Nayal, Nazir*; YAVUZ, MISRA; Henriques, Joao F; Guney, Fatma",poster,2211.14293,https://arxiv.org/abs/2211.14293,,https://huggingface.co/papers/2211.14293,,,,4,1 SEMPART: Self-supervised Multi-resolution Partitioning of Image Semantics,"Ravindran, Sriram; Basu, Debraj D*",poster,,,,,,,,, Multi-Object Discovery by Low-Dimensional Object Motion,"Safadoust, Sadra*; Guney, Fatma",poster,2307.08027,https://arxiv.org/abs/2307.08027,,https://huggingface.co/papers/2307.08027,,,,2,0 MemorySeg: Online LiDAR Semantic Segmentation with a Latent Memory,"Li, Enxu*; Casas, Sergio; Urtasun, Raquel",poster,,,,,,,,, Treating Pseudo-labels Generation as Image Matting for Weakly Supervised Semantic Segmentation,"Wang, Changwei; Xu, Rongtao; Xu, Shibiao*; Meng, Weiliang; Zhang, Xiaopeng",poster,,,,,,,,, -BoxSnake: Polygonal Instance Segmentation with Box Supervision,"Yang, Rui*; Song, Lin; Ge, Yixiao; Li, Xiu",poster,2303.11630,https://arxiv.org/abs/2303.11630,,https://huggingface.co/papers/2303.11630,,,,4,1 +BoxSnake: Polygonal Instance Segmentation with Box Supervision,"Yang, Rui*; Song, Lin; Ge, Yixiao; Li, Xiu",poster,2303.1163,https://arxiv.org/abs/2303.11630,,https://huggingface.co/papers/2303.11630,,,,4,1 Dynamic Token Pruning in Plain Vision Transformers for Semantic Segmentation,"Tang, Quan*; Zhang, Bowen bz; Liu, Jiajun; Liu, Fagui; Liu, Yifan",poster,2308.01045,https://arxiv.org/abs/2308.01045,,https://huggingface.co/papers/2308.01045,,,,5,0 Instance Neural Radiance Field,"Liu, Yichen*; Tai, Yu-Wing; Tang, Chi-Keung; Hu, Benran; Huang, Junkai",poster,2304.04395,https://arxiv.org/abs/2304.04395,https://github.com/lyclyc52/Instance_NeRF,https://huggingface.co/papers/2304.04395,,,,5,0 Global Knowledge Calibration for Fast Open-Vocabulary Segmentation,"Han, Kunyang*; Liu, Yong; Liew, Jun Hao; Ding, Henghui; Wei, Yunchao; Liu, Jiajun; Wang, Yitong; Tang, Yansong; Yang, Yujiu; Feng, Jiashi; Zhao, Yao",poster,2303.09181,https://arxiv.org/abs/2303.09181,,https://huggingface.co/papers/2303.09181,,,,11,0 -Diffusion-based Image Translation with Label Guidance for Domain Adaptive Semantic Segmentation,"Duo, Peng; Hu, Ping; Ke, Qiuhong; Liu, Jun*",poster,2308.12350,https://arxiv.org/abs/2308.12350,,https://huggingface.co/papers/2308.12350,,,,4,0 +Diffusion-based Image Translation with Label Guidance for Domain Adaptive Semantic Segmentation,"Duo, Peng; Hu, Ping; Ke, Qiuhong; Liu, Jun*",poster,2308.1235,https://arxiv.org/abs/2308.12350,,https://huggingface.co/papers/2308.12350,,,,4,0 Boosting Semantic Segmentation from an Explicit Class Embedding’s Perspective,"Liu, Yuhe*; Liu, Chuanjian; Han, Kai; Tang, Quan; Qin, Zengchang",poster,,,,,,,,, The Making and Breaking of Camouflage,"Lamdouar, Hala*; Xie, Weidi; Zisserman, Andrew",poster,,,,,,,,, CoinSeg: Contrast Inter- and Intra- Class Representations for Incremental Segmentation,"Zhang, Zekang; Gao, Guangyu Ryan*; Jiao, Jianbo; Wei, Yunchao; Liu, Chi Harold",poster,,,,,,,,, Few-Shot Physically-Aware Articulated Mesh Generation via Hierarchical Deformation,"Liu, Xueyi*; Wang, Bin; Wang, He; Yi, Li",poster,2308.10898,https://arxiv.org/abs/2308.10898,,https://huggingface.co/papers/2308.10898,,,,4,0 -HAL3D: Hierarchical Active Learning for Fine-Grained 3D Part Labeling,"YU, FENGGEN; Qian, Yiming*; Gil-Ureta, Francisca T; Jackson, Brian P; Bennett, Eric P; Zhang, Hao",poster,2301.10460,https://arxiv.org/abs/2301.10460,,https://huggingface.co/papers/2301.10460,,,,6,0 +HAL3D: Hierarchical Active Learning for Fine-Grained 3D Part Labeling,"YU, FENGGEN; Qian, Yiming*; Gil-Ureta, Francisca T; Jackson, Brian P; Bennett, Eric P; Zhang, Hao",poster,2301.1046,https://arxiv.org/abs/2301.10460,,https://huggingface.co/papers/2301.10460,,,,6,0 FreeCOS: Self-Supervised Learning from Fractals and Unlabeled Images for Curvilinear Object Segmentation,"Shi, Tianyi*; Ding, Xiaohuan; zhang, liang; Yang, Xin",poster,2307.07245,https://arxiv.org/abs/2307.07245,https://github.com/TY-Shi/FreeCOS,https://huggingface.co/papers/2307.07245,,,,4,0 MasQCLIP for Open-Vocabulary Universal Image Segmentation,"Xu, Xin; Xiong, Tianyi; Ding, Zheng*; Tu, Zhuowen",poster,,,,,,,,, CTVIS: Consistent Training for Online Video Instance Segmentation,"Ying, Kaining; Zhong, Qing; Mao, Weian; Wang, Zhenhua*; Chen, Hao; Wu, Lin Yuanbo; Liu, Yifan; Fan, Chengxiang; Zhuge, Yunzhi; Shen, Chunhua",poster,2307.12616,https://arxiv.org/abs/2307.12616,,https://huggingface.co/papers/2307.12616,,,,10,1 @@ -77,7 +77,7 @@ Foreground-Background Separation through Concept Distillation from Generative Im SegPrompt: Boosting Open-World Segmentation via Category-level Prompt Learning,"Zhu, Muzhi*; Li, Hengtao; Chen, Hao; Fan, Chengxiang; Mao, Weian; Jing, Chenchen; Liu, Yifan; Shen, Chunhua",poster,2308.06531,https://arxiv.org/abs/2308.06531,,https://huggingface.co/papers/2308.06531,,,,8,0 Monte Carlo Linear Clustering with Single-Point Supervision is Enough for Infrared Small Target Detection,"Li, Boyang*; Wang, Yingqian; Wang, Longguang; Zhang, Fei; Liu, Ting; Lin, Zaiping; An, Wei; Guo, Yulan",poster,2304.04442,https://arxiv.org/abs/2304.04442,https://github.com/YeRen123455/SIRST-Single-Point-Supervision,https://huggingface.co/papers/2304.04442,,,,8,0 A Simple Framework for Open-Vocabulary Segmentation and Detection,"Zhang, Hao; Li, Feng*; Zou, Xueyan; Liu, Shilong; Li, Chunyuan; Yang, Jianwei; Zhang, Lei",poster,2303.08131,https://arxiv.org/abs/2303.08131,,https://huggingface.co/papers/2303.08131,,,,8,0 -Source-free Depth for Object Pop-out,"WU, Zongwei; Paudel, Danda Pani; Fan, Deng-Ping*; Wang, Jingjing; Wang, Shuo; Demonceaux, Cedric; Timofte, Radu; Van Gool, Luc",poster,2212.05370,https://arxiv.org/abs/2212.05370,,https://huggingface.co/papers/2212.05370,,,,8,0 +Source-free Depth for Object Pop-out,"WU, Zongwei; Paudel, Danda Pani; Fan, Deng-Ping*; Wang, Jingjing; Wang, Shuo; Demonceaux, Cedric; Timofte, Radu; Van Gool, Luc",poster,2212.0537,https://arxiv.org/abs/2212.05370,,https://huggingface.co/papers/2212.05370,,,,8,0 DynaMITe: Dynamic Query Bootstrapping for Multi-object Interactive Segmentation Transformer,"Rana, Amit Kumar; Mahadevan, Sabarinath*; Hermans, Alexander; Leibe, Bastian",poster,2304.06668,https://arxiv.org/abs/2304.06668,,https://huggingface.co/papers/2304.06668,,,,4,0 Atmospheric Transmission and Thermal Inertia Induced Blind Road Segmentation with a Large-Scale Dataset TBRSD,"Chen, Junzhang*; Bai, Xiangzhi",poster,,,,,,,,, Informative Data Mining for One-shot Cross-Domain Semantic Segmentation,"Wang, yuxi*; Liang, Jian; mei, shuqi; yang, yuran; Xiao, Jun; Zhang, Zhaoxiang",poster,,,,,,,,, @@ -96,7 +96,7 @@ MixReorg: Cross-Modal Mixed Patch Reorganization is a Good Mask Learner for Open DiffuMask: Synthesizing Images with Pixel-level Annotations for Semantic Segmentation Using Diffusion Models,"Wu, Weijia*; Zhao, Yuzhong; Shou, Mike Zheng; ZHOU, HONG; Shen, Chunhua",poster,2303.11681,https://arxiv.org/abs/2303.11681,,https://huggingface.co/papers/2303.11681,,,,5,0 Alignment Before Aggregation: Trajectory Memory Retrieval Network for Video Object Segmentation,"Sun, Rui*; Wang, Yuan; Mai, Huayu; Zhang, Tianzhu; Wu, Feng",poster,,,,,,,,, Semi-Supervised Semantic Segmentation under Label Noise via Diverse Learning Groups,"Li, Peixia*; Purkait, Pulak; Ajanthan, Thalaiyasingam; Abdolshah, Majid; Garg, Ravi; Husain, Hisham; Xu, Chenchen; Gould, Stephen; Ouyang, Wanli; van den Hengel, Anton",poster,,,,,,,,, -SUMMIT: Source-Free Adaptation of Uni-Modal Models to Multi-Modal Targets,"Simons, Cody M*; Raychaudhuri, Dripta S.; AHMED, SK MIRAJ; You, Suya; Karydis, Konstantinos; Roy-Chowdhury, Amit K. ",poster,2308.11880,https://arxiv.org/abs/2308.11880,https://github.com/csimo005/SUMMIT,https://huggingface.co/papers/2308.11880,,,,6,0 +SUMMIT: Source-Free Adaptation of Uni-Modal Models to Multi-Modal Targets,"Simons, Cody M*; Raychaudhuri, Dripta S.; AHMED, SK MIRAJ; You, Suya; Karydis, Konstantinos; Roy-Chowdhury, Amit K. ",poster,2308.1188,https://arxiv.org/abs/2308.11880,https://github.com/csimo005/SUMMIT,https://huggingface.co/papers/2308.11880,,,,6,0 Class-incremental Continual Learning for Instance Segmentation with Image-level Weak Supervision,"Hsieh, Yu-Hsing*; Chen, Guan-Sheng; Cai, Shun-Xian; Wei, Ting-Yun; Yang, Huei-Fang; Chen, Chu-Song",poster,,,,,,,,, Coarse-to-Fine Amodal Segmentation with Shape Prior,"Gao, Jianxiong; Qian, Xuelin*; Fu, Yanwei; Wang, Yikai; Xiao, Tianjun; Zhang, Zheng; He, Tong",poster,2308.16825,https://arxiv.org/abs/2308.16825,,https://huggingface.co/papers/2308.16825,,,,7,0 Rethinking Amodal Video Segmentation from Learning Supervised Signals with Object-centric Representation,"Fan, Ke; Lei, Jingshi; Qian, Xuelin*; Yu, Miaopeng; Zhang, Zheng; He, Tong; Xiao, Tianjun; Fu, Yanwei",poster,,,,,,,,, @@ -107,11 +107,11 @@ Decoupled or End-to-End Trained Video Segmentation if Target Data is Scarce?,"Ch Cross Contrasting Feature Perturbation for Domain Generalization,"Li, Chenming*; Zhang, Daoan; Huang, Wenjian; Zhang, Jianguo",poster,2307.12502,https://arxiv.org/abs/2307.12502,,https://huggingface.co/papers/2307.12502,,,,4,0 Flexible Visual Recognition by Evidential Modeling of Confusion and Ignorance,"Fan, Lei*; Liu, Bo; Li, Haoxiang; Wu, Ying; Hua, Gang",poster,,,,,,,,, CDUL: CLIP-Driven Unsupervised Learning for Multi-Label Image Classification,"Abdelfattah, Rabab*; Guo, Qing; Li, Xiaoguang; Wang, XIAOFENG; Wang, Song",poster,2307.16634,https://arxiv.org/abs/2307.16634,,https://huggingface.co/papers/2307.16634,,,,5,0 -RankMixup: Ranking-based Mixup Training for Network Calibration,"Noh, Jongyoun; Park, Hyekang; Lee, Junghyup; Ham, Bumsub*",poster,2308.11990,https://arxiv.org/abs/2308.11990,,https://huggingface.co/papers/2308.11990,,,,4,0 +RankMixup: Ranking-based Mixup Training for Network Calibration,"Noh, Jongyoun; Park, Hyekang; Lee, Junghyup; Ham, Bumsub*",poster,2308.1199,https://arxiv.org/abs/2308.11990,,https://huggingface.co/papers/2308.11990,,,,4,0 Label-Noise Learning with Intrinsically Long-Tailed Data,"Lu, Yang*; Zhang, Yiliang; Han, Bo; CHEUNG, Yiu-ming; Wang, Hanzi",poster,2208.09833,https://arxiv.org/abs/2208.09833,https://github.com/Wakings/TABASCO,https://huggingface.co/papers/2208.09833,,,,5,0 Parallel Attention Interaction Network for Few-Shot Skeleton-based Action Recognition,"Liu, Xingyu; Zhou, Sanping*; Wang, Le; Hua, Gang",poster,,,,,,,,, Rethinking Mobile Block for Efficient Attention-based Models,"Zhang, Jiangning*; Li, Xiangtai; Li, Jian; Liu, Liang; Zhang, Boshen; Jiang, ZhengKai; Huang, Tianxin; Xue, Zhucun; Wang, Yabiao; Wang, Chengjie",poster,2301.01146,https://arxiv.org/abs/2301.01146,,https://huggingface.co/papers/2301.01146,,,,10,0 -Read-only Prompt Optimization for Vision-Language Few-shot Learning,"Lee, DongJun*; Song, Seokwon; Suh, Jihee; Choi, Joonmyung; Lee, Sanghyeok; Kim, Hyunwoo J",poster,2308.14960,https://arxiv.org/abs/2308.14960,https://github.com/mlvlab/RPO,https://huggingface.co/papers/2308.14960,,,,6,0 +Read-only Prompt Optimization for Vision-Language Few-shot Learning,"Lee, DongJun*; Song, Seokwon; Suh, Jihee; Choi, Joonmyung; Lee, Sanghyeok; Kim, Hyunwoo J",poster,2308.1496,https://arxiv.org/abs/2308.14960,https://github.com/mlvlab/RPO,https://huggingface.co/papers/2308.14960,,,,6,0 Understanding Self-attention Mechanism via Dynamical System Perspective,"Huang, Zhongzhan; Liang, Mingfu; Qin, Jinghui; Zhong, Shanshan; Lin, Liang*",poster,2308.09939,https://arxiv.org/abs/2308.09939,,https://huggingface.co/papers/2308.09939,,,,5,0 Learning in Imperfect Environment: Multi-Label Classification with Long-Tailed Distribution and Partial Labels,"Zhang, Wenqiao*; LIU, CHANGSHUO; Ooi, Beng Chin; Tang, Siliang; Zhuang, Yueting",poster,2304.10539,https://arxiv.org/abs/2304.10539,,https://huggingface.co/papers/2304.10539,,,,6,0 What do neural networks learn in image classification? A frequency shortcut perspective,"Wang, Shunxin*; Veldhuis, Raymond; Brune, Christoph; Strisciuglio, Nicola",poster,2307.09829,https://arxiv.org/abs/2307.09829,,https://huggingface.co/papers/2307.09829,,,,4,0 @@ -197,7 +197,7 @@ A-STAR: Test-time Attention Segregation and Retention for Text-to-image Synthesi TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition,"Lu, Shilin*; Liu, Yanzhu; Kong, Wai-Kin Adams",poster,,,,,,,,, Breaking The Limits of Text-conditioned 3D Motion Synthesis with Elaborative Descriptions,"Qian, Yijun*; Urbanek, Jack; Hauptmann, Alexander ; Won, Jungdam",poster,,,,,,,,, BeLFusion: Latent Diffusion for Behavior-Driven Human Motion Prediction,"Barquero, German*; Escalera, Sergio; Palmero, Cristina",poster,2211.14304,https://arxiv.org/abs/2211.14304,,https://huggingface.co/papers/2211.14304,,,,3,1 -Delta Denoising Score,"Hertz, Amir*; Cohen-Or, Danny; Aberman, Kfir",poster,2304.07090,https://arxiv.org/abs/2304.07090,,https://huggingface.co/papers/2304.07090,,,,3,0 +Delta Denoising Score,"Hertz, Amir*; Cohen-Or, Danny; Aberman, Kfir",poster,2304.0709,https://arxiv.org/abs/2304.07090,,https://huggingface.co/papers/2304.07090,,,,3,0 Mimic3D: Thriving 3D-Aware GANs via 3D-to-2D Imitation,"Chen, Xingyu*; Deng, Yu; Wang, Baoyuan",poster,2303.09036,https://arxiv.org/abs/2303.09036,,https://huggingface.co/papers/2303.09036,,,,3,0 DreamBooth3D: Subject-Driven Text-to-3D Generation,"Raj, Amit; Kaza, Srinivas; Poole, Ben; Niemeyer, Michael; Ruiz, Nataniel; Mildenhall, Ben; Zada, Shiran; Aberman, Kfir; Rubinstein, Michael; Barron, Jonathan T; Li, Yuanzhen; Jampani, Varun*",poster,2303.13508,https://arxiv.org/abs/2303.13508,,https://huggingface.co/papers/2303.13508,,,,12,0 Feature Proliferation — the “Cancer” in StyleGAN and its Treatments,"Song, Shuang; Liang, Yuanbang; Wu, Jing; Lai, Yu-Kun; Qin, Yipeng*",poster,,,,,,,,, @@ -290,7 +290,7 @@ ProtoTransfer: Cross-Modal Prototype Transfer for Point Cloud Segmentation,"Tang SA-BEV: Generating Semantic-Aware Bird's-Eye-View Feature for Multi-view 3D Object Detection,"Zhang, Jinqing*; Zhang, Yanan; Liu, Qingjie; Wang, Yunhong",poster,,,,,,,,, GraphAlign: Enhancing Accurate Feature Alignment by Graph matching for Multi-Modal 3D Object Detection,"Song, Ziying; Wei, Haiyue; Bai, Lin; Yang, Lei; Jia, Caiyan*",poster,,,,,,,,, Tangent Sampson Error: Fast Approximate Two-view Reprojection Error for Central Camera Models,"Terekhov, Mikhail A.*; Larsson, Viktor",poster,,,,,,,,, -Using a Waffle Iron for Automotive Point Cloud Semantic Segmentation,"Puy, Gilles*; Boulch, Alexandre; Marlet, Renaud",poster,2301.10100,https://arxiv.org/abs/2301.10100,,https://huggingface.co/papers/2301.10100,,,,3,0 +Using a Waffle Iron for Automotive Point Cloud Semantic Segmentation,"Puy, Gilles*; Boulch, Alexandre; Marlet, Renaud",poster,2301.101,https://arxiv.org/abs/2301.10100,,https://huggingface.co/papers/2301.10100,,,,3,0 Fast Globally Optimal Surface Normal Estimation from an Affine Correspondence,"Hajder, Levente*; Barath, Daniel; Lóczi, Lajos",poster,,,,,,,,, HeadsUp: A Data-Driven Volumetric Prior for Few-shot Synthesis of Ultra High-resolution Human Heads,"Bühler, Marcel C.; Sarkar, Kripasindhu; Shah, Tanmay; Li, Gengyan; Wang, Daoye; Helminger, Leonhard; Orts-Escolano, Sergio; Lagun, Dmitry; Hilliges, Otmar; Beeler, Thabo; Meka, Abhimitra*",poster,,,,,,,,, TILTED: Robust Neural Fields via Latent Registration,"Yi, Brent H*; Zeng, Weijia ; Buchanan, Sam; Ma, Yi",poster,,,,,,,,, @@ -339,7 +339,7 @@ EgoLoc: Revisiting 3D Object Localization from Egocentric Videos with Visual Que ClothPose: A Real-world Benchmark for Visual Analysis of Garment Pose via An Indirect Recording Solution,"Xu, Wenqiang*; Du, Wenxin; Xue, Han; Li, Yutong; Ye, Ruolin; Wang, Yan-Feng; Lu, Cewu",oral,,,,,,,,, EMR-MSF: Self-Supervised Recurrent Monocular Scene Flow Exploiting Ego-Motion Rigidity,"Jiang, Zijie*; Okutomi, Masatoshi",oral,,,,,,,,, ENVIDR: Implicit Differentiable Renderer with Neural Environment Lighting,"Liang, Ruofan*; Chen, Huiting; Li, Chunlin; Chen, Fan; Panneer, Selvakumar; Vijaykumar, Nandita",oral,2303.13022,https://arxiv.org/abs/2303.13022,,https://huggingface.co/papers/2303.13022,,,,6,0 -Robust Mixture-of-Expert Training for Convolutional Neural Networks,"Zhang, Yihua*; Cai, Ruisi; Chen, Tianlong; Zhang, Guanhua; Zhang, Huan; Chen, Pin-Yu; Chang, Shiyu; Wang, Zhangyang; Liu, Sijia",oral,2308.10110,https://arxiv.org/abs/2308.10110,https://github.com/OPTML-Group/Robust-MoE-CNN,https://huggingface.co/papers/2308.10110,,,,9,0 +Robust Mixture-of-Expert Training for Convolutional Neural Networks,"Zhang, Yihua*; Cai, Ruisi; Chen, Tianlong; Zhang, Guanhua; Zhang, Huan; Chen, Pin-Yu; Chang, Shiyu; Wang, Zhangyang; Liu, Sijia",oral,2308.1011,https://arxiv.org/abs/2308.10110,https://github.com/OPTML-Group/Robust-MoE-CNN,https://huggingface.co/papers/2308.10110,,,,9,0 Set-Level Guidance Attack: Boosting Adversarial Transferability of Vision-Language Pre-training Models,"Lu, Dong*; Wang, Zhiqiang; Wang, Teng; GUAN, WEILI; Gao, Hongchang; Zheng, Feng",oral,2307.14061,https://arxiv.org/abs/2307.14061,,https://huggingface.co/papers/2307.14061,,,,6,0 CleanCLIP: Mitigating Data Poisoning Attacks in Multimodal Contrastive Learning,"Bansal, Hritik*; Singhi, Nishad; Yang, Yu; Yin, Fan; Grover, Aditya; Chang, Kai-Wei",oral,2303.03323,https://arxiv.org/abs/2303.03323,https://github.com/nishadsinghi/CleanCLIP,https://huggingface.co/papers/2303.03323,,,,6,0 CGBA: Curvature-aware Geometric Black-box Attack,"Reza, Md Farhamdur*; Rahmati, Ali; Wu, Tianfu; Dai, Huaiyu",oral,2308.03163,https://arxiv.org/abs/2308.03163,https://github.com/Farhamdur/CGBA,https://huggingface.co/papers/2308.03163,,,,4,0 @@ -353,7 +353,7 @@ ACTIVE: Towards Highly Transferable 3D Physical Camouflage for Universal and Rob Frequency-aware GAN for Adversarial Manipulation Generation,"Zhu, Peifei*; Osada, Genki; Kataoka, Hirokatsu; Takahashi, Tsubasa",poster,,,,,,,,, Breaking Temporal Consistency: Generating Video Universal Adversarial Perturbations Using Image Models,"Kim, Hee-Seon; Son, Minji; Kim, Minbeom; Kwon, Myung-Joon; Kim, Changick*",poster,,,,,,,,, Tracing the Origin of Adversarial Attack for Forensic Investigation and Deterrence,"Fang, Han*; Zhang, Jiyi; Qiu, Yupeng; Liu, Jiayang; Xu, Ke; Fang, Chengfang; Chang, Ee-Chien",poster,2301.01218,https://arxiv.org/abs/2301.01218,,https://huggingface.co/papers/2301.01218,,,,6,0 -Downstream-agnostic Adversarial Examples,"Zhou, Ziqi; Hu, Shengshan*; Zhao, Ruizhi; Wang, Qian; ZHANG, LEO YU; Hou, Junhui; Jin, Hai",poster,2307.12280,https://arxiv.org/abs/2307.12280,,https://huggingface.co/papers/2307.12280,,,,7,0 +Downstream-agnostic Adversarial Examples,"Zhou, Ziqi; Hu, Shengshan*; Zhao, Ruizhi; Wang, Qian; ZHANG, LEO YU; Hou, Junhui; Jin, Hai",poster,2307.1228,https://arxiv.org/abs/2307.12280,,https://huggingface.co/papers/2307.12280,,,,7,0 Hiding Visual Information via Obfuscating Adversarial Perturbations,"Su, Zhigang; Zhou, Dawei; Liu, Decheng; Wang, Nannan*; Wang, Zhen; Gao, Xinbo",poster,2209.15304,https://arxiv.org/abs/2209.15304,,https://huggingface.co/papers/2209.15304,,,,6,0 An Embarrassingly Simple Self-supervised Trojan Attack,"Li, Changjiang *; Ren, Pang; Xi, Zhaohan; Du, Tianyu; Ji, Shouling; Wang, Ting; Yao, Yuan",poster,,,,,,,,, Efficient Decision-based Black-box Patch Attacks on Video Recognition ,"Jiang, Kaixun*; Chen, Zhaoyu; Huang, Hao; Wang, Jiafeng; Yang, Dingkang; Li, Bo; Wang, Yan; Zhang, Wenqiang",poster,,,,,,,,, @@ -367,7 +367,7 @@ RFLA: A Stealthy Reflected Light Adversarial Attack in the Physical World,"Wang, Enhancing Fine-Tuning based Backdoor Defense with Sharpness-Aware Minimization,"Zhu, Mingli*; Wei, Shaokui; Shen, Li; Fan, Yanbo; Wu, Baoyuan",poster,2304.11823,https://arxiv.org/abs/2304.11823,,https://huggingface.co/papers/2304.11823,,,,5,0 Conditional 360-degree Image Synthesis for Immersive Indoor Scene Decoration,"Shum, Ka-Chun*; Pang, Hong Wing; Hua, Binh-Son; Nguyen, Thanh; Yeung, Sai-Kit",poster,2307.09621,https://arxiv.org/abs/2307.09621,,https://huggingface.co/papers/2307.09621,,,,5,0 An Adaptive Model Ensemble Adversarial Attack for Boosting Adversarial Transferability,"Chen, Bin; Yin, Jia-Li*; Chen, Shu-Kai; Chen, Bo-Hao; Liu, Ximeng",poster,2308.02897,https://arxiv.org/abs/2308.02897,,https://huggingface.co/papers/2308.02897,,,,5,0 -Mitigating Adversarial Vulnerability through Causal Parameter Estimation by Adversarial Double Machine Learning,"Lee, Byung-Kwan*; Kim, Junho; Ro, Yong Man",poster,2307.07250,https://arxiv.org/abs/2307.07250,,https://huggingface.co/papers/2307.07250,,,,3,0 +Mitigating Adversarial Vulnerability through Causal Parameter Estimation by Adversarial Double Machine Learning,"Lee, Byung-Kwan*; Kim, Junho; Ro, Yong Man",poster,2307.0725,https://arxiv.org/abs/2307.07250,,https://huggingface.co/papers/2307.07250,,,,3,0 LEA2: A Lightweight Ensemble Adversarial Attack via Non-overlapping Vulnerable Frequency Regions,"QIAN, Yaguan*; He, Shuke; Zhao, Chenyu; Sha, Jia Qiang; Wang, Wei; WANG , Bin",poster,,,,,,,,, Explaining Adversarial Robustness of Neural Networks from Clustering Effect Perspective,"Jin, Yulin*; Zhang, Xiaoyu; Lou, Jian; Ma, Xu; Chen, Xiaofeng; Wang, Zilong",poster,,,,,,,,, VertexSerum: Poisoning Graph Neural Networks for Link Inference,"Ding, Ruyi*; Duan, Shijin; Xu, Xiaolin; Fei, Yunsi",poster,2308.01469,https://arxiv.org/abs/2308.01469,,https://huggingface.co/papers/2308.01469,,,,4,0 @@ -380,7 +380,7 @@ Hard No-Box Adversarial Attack on Skeleton-Based Human Action Recognition with S Structure Invariant Transformation for better Adversarial Transferability,"Wang, Xiaosen*; Zhang, Zeliang; Zhang, Jianping",poster,,,,,,,,, Beating Backdoor Attack at Its Own Game,"Liu, Min*; Sangiovanni-Vincentelli, Alberto L; Yue, Xiangyu",poster,2307.15539,https://arxiv.org/abs/2307.15539,https://github.com/damianliumin/non-adversarial_backdoor,https://huggingface.co/papers/2307.15539,,,,3,0 Transferable Adversarial Attack for Both Vision Transformers and Convolutional Networks via Momentum Integrated Gradients,"Ma, Wenshuo*; Li, Yidong; Xiaofeng, Jia; Xu, Wei",poster,,,,,,,,, -REAP: A Large-Scale Realistic Adversarial Patch Benchmark,"Hingun, Nabeel; Sitawarin, Chawin*; Li, Jerry; Wagner, David",poster,2212.05680,https://arxiv.org/abs/2212.05680,https://github.com/wagner-group/reap-benchmark,https://huggingface.co/papers/2212.05680,,,,4,1 +REAP: A Large-Scale Realistic Adversarial Patch Benchmark,"Hingun, Nabeel; Sitawarin, Chawin*; Li, Jerry; Wagner, David",poster,2212.0568,https://arxiv.org/abs/2212.05680,https://github.com/wagner-group/reap-benchmark,https://huggingface.co/papers/2212.05680,,,,4,1 Multi-metrics adaptively identifies backdoors in Federated learning,"Huang, Siquan*; Li, Yijiang; Chen, Chong; Shi, Leyu; Gao, Ying",poster,2303.06601,https://arxiv.org/abs/2303.06601,,https://huggingface.co/papers/2303.06601,,,,5,0 Backpropagation Path Search On Adversarial Transferability,"Xu, Zhuoer*; Gu, Zhangxuan; Zhang, Jianping; Cui, Shiwen; Meng, Changhua; Wang, Weiqiang",poster,2308.07625,https://arxiv.org/abs/2308.07625,,https://huggingface.co/papers/2308.07625,,,,6,0 Fast Adaptation of Neural Networks using Test-Time Feedback,"Yeo, Teresa*; Kar, O?uzhan Fatih; Sodagar, Zahra; Zamir, Amir",poster,,,,,,,,, @@ -400,7 +400,7 @@ Global Balanced Experts for Federated Long-tailed Learning,"Zeng, Yaopei; Liu, L Source-free Domain Adaptive Human Pose Estimation,"Peng, Qucheng*; Zheng, Ce; Chen, Chen",poster,2308.03202,https://arxiv.org/abs/2308.03202,https://github.com/davidpengucf/SFDAHPE,https://huggingface.co/papers/2308.03202,,,,3,0 Gender Artifacts in Visual Datasets,"Meister, Nicole*; Zhao, Dorothy; Wang, Angelina; Ramaswamy, Vikram V.; Russakovsky, Olga; Fong, Ruth C",poster,2206.09191,https://arxiv.org/abs/2206.09191,,https://huggingface.co/papers/2206.09191,,,,6,0 FRAug: Tackling Federated Learning with Non-IID Features via Representation Augmentation ,"Chen, Haokun*; Frikha, Ahmed; Krompass, Denis; Gu, Jindong; Tresp, Volker",poster,,,,,,,,, -zPROBE: Zero Peek Robustness Checks for Federated Learning,"Ghodsi, Zahra; Javaheripi, Mojan; Sheybani, Nojan*; Zhang, Xinqiao; Huang, Ke; Koushanfar, Farinaz",poster,2206.12100,https://arxiv.org/abs/2206.12100,,https://huggingface.co/papers/2206.12100,,,,6,0 +zPROBE: Zero Peek Robustness Checks for Federated Learning,"Ghodsi, Zahra; Javaheripi, Mojan; Sheybani, Nojan*; Zhang, Xinqiao; Huang, Ke; Koushanfar, Farinaz",poster,2206.121,https://arxiv.org/abs/2206.12100,,https://huggingface.co/papers/2206.12100,,,,6,0 Practical Membership Inference Attacks Against Large-Scale Multi-Modal Models: A Pilot Study,"Ko, Myeongseob*; Jin, Ming; Wang, Chenguang; Jia, Ruoxi",poster,,,,,,,,, FedPD: Federated Open Set Recognition with Parameter Disentanglement,"YANG, Chen*; Zhu, Meilu; Liu, Yifan; Yuan, Yixuan",poster,,,,,,,,, MUter: Machine Unlearning for Adversarial Training Models,"Liu, Junxu; Xue, Mingsheng; Lou, Jian*; Zhang, Xiaoyu; Xiong, Li; Qin, Zhan",poster,,,,,,,,, @@ -412,7 +412,7 @@ Mining bias-target Alignment from Voronoi Cells,"Nahon, Remi*; Nguyen, Van-Tam; Better May Not Be Fairer: A Study on Subgroup Discrepancy in Image Classification,"Chiu, Ming-Chang*; Chen, Pin-Yu; Ma, Xuezhe",poster,,,,,,,,, GIFD: A Generative Gradient Inversion Method with Feature Domain Optimization,"Fang, Hao*; Chen, Bin; Wang, Xuan; Wang, Zhi; Xia, Shu-Tao",poster,2308.04699,https://arxiv.org/abs/2308.04699,,https://huggingface.co/papers/2308.04699,,,,5,0 Benchmarking Algorithmic Bias in Face Recognition: An Experimental Approach Using Synthetic Faces and Human Evaluation,"Liang, Hao*; Perona, Pietro; Balakrishnan, Guha",poster,2308.05441,https://arxiv.org/abs/2308.05441,,https://huggingface.co/papers/2308.05441,,,,3,0 -FedPerfix: Towards Partial Model Personalization of Vision Transformers in Federated Learning,"Sun, Guangyu*; Mendieta, Matias; Luo, Jun; Wu, Shandong; Chen, Chen",poster,2308.09160,https://arxiv.org/abs/2308.09160,,https://huggingface.co/papers/2308.09160,,,,5,0 +FedPerfix: Towards Partial Model Personalization of Vision Transformers in Federated Learning,"Sun, Guangyu*; Mendieta, Matias; Luo, Jun; Wu, Shandong; Chen, Chen",poster,2308.0916,https://arxiv.org/abs/2308.09160,,https://huggingface.co/papers/2308.09160,,,,5,0 Towards Attack-tolerant Federated Learning via Critical Parameter Analysis,"Han, Sungwon*; Park, Sungwon; Wu, Fangzhao; Kim, Sundong; Zhu, Bin; Xie, Xing; Cha, Meeyoung",poster,2308.09318,https://arxiv.org/abs/2308.09318,,https://huggingface.co/papers/2308.09318,,,,7,0 What can Discriminator do? Towards Box-free Ownership Verification of Generative Adversarial Networks,"Huang, Ziheng; Li, Boheng; Cai, Yan; Wang, Run*; Guo, Shangwei ; Fang, Liming; Chen, Jing; Wang, Lina",poster,,,,,,,,, Robust Heterogeneous Federated Learning under Data Corruption,"Fang, Xiuwen; Ye, Mang*; Yang, Xiyuan",poster,,,,,,,,, @@ -426,13 +426,13 @@ Domain Specified Optimization for Deployment Authorization,"Wang, Haotian*; Chi, STPrivacy: Spatio-Temporal Privacy-Preserving Action Recognition,"Li, Ming*; Xu, Xiangyu; Fan, Hehe; Zhou, Pan; Liu, Jun; Liu, Jia-Wei; Li, Jiahe; Keppo, Jussi; Shou, Mike Zheng; Yan, Shuicheng",poster,2301.03046,https://arxiv.org/abs/2301.03046,,https://huggingface.co/papers/2301.03046,,,,10,0 SAL-ViT: Towards Latency Efficient Private Inference on ViT using Selective Attention Search with a Learnable Softmax Approximation,"Zhang, Yuke*; Chen, Dake; Kundu, Souvik; Li, Chenghao; A. Beerel, Peter",poster,,,,,,,,, Generative Gradient Inversion Without Prior,"Zhang, Chi*; Xiaoman, Zhang; Sotthiwat, Ekanut; Xu, Yanyu; Liu, Ping; Zhen, Liangli; Liu, Yong",poster,,,,,,,,, -Inspecting the Geographical Representativeness of Images from Text-to-Image Models,"Basu, Abhipsa*; RADHAKRISHNAN, Venkatesh Babu; Pruthi, Danish",poster,2305.11080,https://arxiv.org/abs/2305.11080,,https://huggingface.co/papers/2305.11080,,,,3,0 +Inspecting the Geographical Representativeness of Images from Text-to-Image Models,"Basu, Abhipsa*; RADHAKRISHNAN, Venkatesh Babu; Pruthi, Danish",poster,2305.1108,https://arxiv.org/abs/2305.11080,,https://huggingface.co/papers/2305.11080,,,,3,0 Divide and Conquer: a Two-Step Method for High Quality Face De-identification with Model Explainability,"Wen, Yunqian*; Liu, Bo; Cao, Jingyi; Xie, Rong; Song, Li",poster,,,,,,,,, Exploring the Benefits of Visual Prompting in Differential Privacy,"Li, Yizhe; Tsai, Yu-Lin; Yu, Chia-Mu*; Chen, Pin-Yu; Ren, Xuebin",poster,2303.12247,https://arxiv.org/abs/2303.12247,https://github.com/EzzzLi/Prompt-PATE,https://huggingface.co/papers/2303.12247,,,,5,0 Towards Fairness-aware Adversarial Network Pruning,"Wang, Zhibo*; Zhang, Lei; Dong, Xiaowei; Feng, Yunhe; Pang, Xiaoyi; Zhang, Zhifei; Ren, Kui",poster,,,,,,,,, AutoReP: Automatic ReLU Replacement for Fast Private Network Inference,"Peng, Hongwu*; Huang, Shaoyi; Zhou, Tong; Luo, Yukui; Wang, Chenghong; Wang, Zigeng; Zhao, Jiahui; Xie, Xi; Li, Ang; Geng, Tony; Mahmood, Kaleel; Wen, Wujie; Xu, Xiaolin; Ding, Caiwen",poster,2308.10134,https://arxiv.org/abs/2308.10134,,https://huggingface.co/papers/2308.10134,,,,14,0 Flatness-Aware Minimization for Domain Generalization,"Zhang, Xingxuan*; Xu, Renzhe; Yu, Han; Dong, Yancheng; Tian, Pengfei; Cui, Peng",poster,2307.11108,https://arxiv.org/abs/2307.11108,,https://huggingface.co/papers/2307.11108,,,,6,1 -Communication-Efficient Vertical Federated Learning with Limited Overlapping Samples,"Sun, Jingwei*; Xu, Ziyue; Yang, Dong; Nath, Vishwesh; Li, Wenqi; Zhao, Can; Xu, Daguang; Chen, Yiran; Roth, Holger R",poster,2303.16270,https://arxiv.org/abs/2303.16270,,https://huggingface.co/papers/2303.16270,,,,9,0 +Communication-Efficient Vertical Federated Learning with Limited Overlapping Samples,"Sun, Jingwei*; Xu, Ziyue; Yang, Dong; Nath, Vishwesh; Li, Wenqi; Zhao, Can; Xu, Daguang; Chen, Yiran; Roth, Holger R",poster,2303.1627,https://arxiv.org/abs/2303.16270,,https://huggingface.co/papers/2303.16270,,,,9,0 Multimodal Distillation for Egocentric Action Recognition,"Radevski, Gorjan*; Grujicic, Dusan; Blaschko, Matthew B.; Moens, Sien; Tuytelaars, Tinne",poster,2307.07483,https://arxiv.org/abs/2307.07483,https://github.com/gorjanradevski/multimodal-distillation,https://huggingface.co/papers/2307.07483,,,,5,0 Self-Supervised Object Detection from Egocentric Videos,"Akiva, Peri*; Huang, Jing ; Liang, Kevin J; Chen, Xingyu; Kovvuri, Rama; Feiszli, Matt; Dana, Kristin; Hassner, Tal",poster,,,,,,,,, Multi-label affordance mapping from egocentric vision,"Mur-Labadia, Lorenzo*; Guerrero, Josechu; Martinez-Cantin, Ruben",poster,,,,,,,,, @@ -488,7 +488,7 @@ FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization,"A IIEU: Rethinking Neural Feature Activation from Decision-Making,"Cai, Sudong*",poster,,,,,,,,, Scratching Visual Transformer's Back with Uniform Attention,"Hyeon-Woo, Nam*; Yu-Ji, Kim; Heo, Byeongho; Han, Dongyoon; Oh, Seong Joon; Oh, Tae-Hyun",poster,2210.08457,https://arxiv.org/abs/2210.08457,,https://huggingface.co/papers/2210.08457,,,,6,0 SpaceEvo: Hardware-Friendly Search Space Design for Efficient INT8 Inference,"Wang, Xudong; Zhang, Li Lyna*; Xu, Jiahang; Zhang, Quanlu; Wang, Yujing; Yang, Yuqing; Zheng, Ningxin; Cao, Ting; Yang, Mao",poster,2303.08308,https://arxiv.org/abs/2303.08308,,https://huggingface.co/papers/2303.08308,,,,9,1 -ElasticViT: Conflict-aware Supernet Training for Deploying Fast Vision Transformer on Diverse Mobile Devices,"Tang, Chen; Zhang, Li Lyna*; Jiang, Huiqiang; Xu, Jiahang; Cao, Ting; Zhang, Quanlu; Yang, Yuqing; Wang, Zhi; Yang, Mao",poster,2303.09730,https://arxiv.org/abs/2303.09730,,https://huggingface.co/papers/2303.09730,,,,9,1 +ElasticViT: Conflict-aware Supernet Training for Deploying Fast Vision Transformer on Diverse Mobile Devices,"Tang, Chen; Zhang, Li Lyna*; Jiang, Huiqiang; Xu, Jiahang; Cao, Ting; Zhang, Quanlu; Yang, Yuqing; Wang, Zhi; Yang, Mao",poster,2303.0973,https://arxiv.org/abs/2303.09730,,https://huggingface.co/papers/2303.09730,,,,9,1 Gramian Attention Heads are Strong yet Efficient Vision Learners,"Ryu, Jongbin*; Han, Dongyoon; Lim, Jongwoo",poster,,,,,,,,, EfficientTrain: Exploring Generalized Curriculum Learning for Training Visual Backbones,"Wang, Yulin; Yue, Yang; Lu, Rui; Liu, Tianjiao; Zhong, Zhao; Song, Shiji; Huang, Gao*",poster,2211.09703,https://arxiv.org/abs/2211.09703,https://github.com/LeapLabTHU/EfficientTrain,https://huggingface.co/papers/2211.09703,,,,7,0 Ord2Seq: Regard Ordinal Regression as Label Sequence Prediction,"Wang, Jinhong*; Cheng, Yi; Chen, Jintai; Chen, Tingting; Chen, Danny Z; Wu, Jian",poster,,,,,,,,, @@ -496,7 +496,7 @@ Unified Data-Free Compression: Pruning and Quantization without Fine-Tuning,"Bai LaPE: Layer-adaptive Position Embedding for Vision Transformers with Independent Layer Normalization,"Yu, Runyi*; Wang, Zhennan; Wang, Yinhuai; Li, Kehan; Liu, Chang; Duan, Haoyi; Ji, Xiangyang; Chen, Jie",poster,,,,,,,,, Exemplar-Free Continual Transformer with Convolutions,"Roy, Anurag*; Voonna, Sravan; Verma, Vinay K; Ghosh, Kripabandhu; Ghosh, Saptarshi; Das, Abir",poster,2308.11357,https://arxiv.org/abs/2308.11357,,https://huggingface.co/papers/2308.11357,,,,6,0 Building Vision Transformers with Hierarchy Aware Feature Aggregation,"chen, yongjie; Liu, Hongmin; Yin, Haoran; Fan, Bin*",poster,,,,,,,,, -ShiftNAS: Improving One-shot NAS via Probability Shift,"Zhang, Mingyang*; Yu, Xinyi; Zhao, Haodong; Ou, Linlin",poster,2307.08300,https://arxiv.org/abs/2307.08300,https://github.com/bestfleer/ShiftNAS,https://huggingface.co/papers/2307.08300,,,,4,0 +ShiftNAS: Improving One-shot NAS via Probability Shift,"Zhang, Mingyang*; Yu, Xinyi; Zhao, Haodong; Ou, Linlin",poster,2307.083,https://arxiv.org/abs/2307.08300,https://github.com/bestfleer/ShiftNAS,https://huggingface.co/papers/2307.08300,,,,4,0 DarSwin: Distortion Aware Radial Swin Transformer,"Athwale, Akshaya; Afrasiyabi, Arman; Lagüe, Justin; Shili, Ichrak; Ahmad, Ola; Lalonde, Jean-Francois*",poster,2304.09691,https://arxiv.org/abs/2304.09691,,https://huggingface.co/papers/2304.09691,,,,6,0 ROME: Robustifying Memory-Efficient NAS via Topology Disentanglement and Gradient Accumulation,"Wang, Xiaoxing*; Chu, Xiangxiang; Fan, Yuda; Zhang, Zhexi; Zhang, Bo; Yang, Xiaokang; Yan, Junchi",poster,2011.11233,https://arxiv.org/abs/2011.11233,,https://huggingface.co/papers/2011.11233,,,,7,0 FDViT: Improve the Hierarchical Architecture of Vision Transformer,"Xu, Yixing*; Li, Chao; Li, Dong; Sheng, Xiao; Jiang, Fan; Tian, Lu; Sirasao, Ashish",poster,,,,,,,,, @@ -517,7 +517,7 @@ EGformer: Equirectangular Geometry-biased Transformer for 360 Depth Estimation," SPANet: Frequency-balancing Token Mixer using Spectral Pooling Aggregation Modulation,"Yun, Guhnoo; Yoo, Juhan; Kim, Kijung; Lee, Jeongho; Kim, Dong Hwan*",poster,2308.11568,https://arxiv.org/abs/2308.11568,,https://huggingface.co/papers/2308.11568,,,,5,0 ModelGiF: Gradient Fields for Model Functional Distance,"Song, Jie; Xu, Zhengqi; Wu, Sai; Chen, Gang; Song, Mingli*",poster,,,,,,,,, ClusT3: Information Invariant Test-Time Training,"Vargas Hakim, Gustavo A*; OSOWIECHI, David; Noori, Mehrdad; Cheraghalikhani, Milad; Bahri, Ali; Ben Ayed, Ismail; Desrosiers, Christian",poster,,,,,,,,, -Cumulative Spatial Knowledge Distillation for Vision Transformers,"Zhao, Borui*; Song, Renjie; Liang, Jiajun",poster,2307.08500,https://arxiv.org/abs/2307.08500,,https://huggingface.co/papers/2307.08500,,,,3,1 +Cumulative Spatial Knowledge Distillation for Vision Transformers,"Zhao, Borui*; Song, Renjie; Liang, Jiajun",poster,2307.085,https://arxiv.org/abs/2307.08500,,https://huggingface.co/papers/2307.08500,,,,3,1 Luminance-aware Color Transform for Multiple Exposure Correction,"Baek, Jong Hyeon*; Kim, DaeHyun; Choi, Su-Min; Lee, Hyo-Jun; Kim, Hanul; Koh, Yeong Jun",poster,,,,,,,,, Towards Memory- and Time-Efficient Backpropagation for Training Spiking Neural Networks,"Meng, Qingyan*; Xiao, Mingqing; Yan, Shen; Wang, Yisen; Lin, Zhouchen; Luo, Zhiquan",poster,,,,,,,,, Domain Generalization Guided by Gradient Signal to Noise Ratio of Parameters,"Michalkiewicz, Mateusz*; Faraki, Masoud; Yu, Xiang; Chandraker, Manmohan; Baktashmotlagh, Mahsa",poster,,,,,,,,, @@ -547,7 +547,7 @@ Towards Fair and Comprehensive Comparisons for Image-Based 3D Object Detection," Monocular 3D Object Detection with Bounding Box Denoising in 3D by Perceiver,"Liu, Xianpeng*; Zheng, Ce; Cheng, Kelvin B; Xue, Nan; Qi, Guo-Jun; Wu, Tianfu",poster,2304.01289,https://arxiv.org/abs/2304.01289,,https://huggingface.co/papers/2304.01289,,,,6,0 Template-guided Hierarchical Feature Restoration for Anomaly Detection,"Guo, Hewei; ren, liping; Fu, Jingjing*; Wang, Yuwang; Zhang, Zhizheng; Lan, Cuiling; Wang, Haoqian; Hou, Xinwen",poster,,,,,,,,, ALWOD: Active Learning for Weakly-Supervised Object Detection,"Wang, Yuting*; Ilic, Velibor; Li, Jiatong; Kisacanin, Branislav; Pavlovic, Vladimir",poster,,,,,,,,, -ProtoFL: Unsupervised Federated Learning via Prototypical Distillation,"Kim, Hansol; Kwak, Youngjun*; Jung, Minyoung; Shin, Jinho; Kim, Youngsung; Kim, Changick",poster,2307.12450,https://arxiv.org/abs/2307.12450,,https://huggingface.co/papers/2307.12450,,,,6,0 +ProtoFL: Unsupervised Federated Learning via Prototypical Distillation,"Kim, Hansol; Kwak, Youngjun*; Jung, Minyoung; Shin, Jinho; Kim, Youngsung; Kim, Changick",poster,2307.1245,https://arxiv.org/abs/2307.12450,,https://huggingface.co/papers/2307.12450,,,,6,0 Efficient Adaptive Human-Object Interaction Detection with Concept-guided Memory,"Lei, Ting; Caba, Fabian; Chen, Qingchao; Jin, Hailin; Peng, Yuxin; Liu, Yang*",poster,,,,,,,,, Detection Transformer with Stable Matching,"Liu, Shilong*; Ren, Tianhe; Chen, Jiayu; Zeng, Zhaoyang; Li, Hongyang; Zhang, Hao; Li, Feng; Huang, Jun; Su, Hang; Zhu, Jun; Zhang, Lei",poster,2304.04742,https://arxiv.org/abs/2304.04742,https://github.com/IDEA-Research/Stable-DINO,https://huggingface.co/papers/2304.04742,,,,11,0 Distilling DETR with Visual-Linguistic Knowledge for Open-Vocabulary Object Detection,"Li, Liangqi*; Miao, Jiaxu; Shi, Dahu; Tan, Wenming; Ren, Ye; Yang, Yi; Pu, Shiliang",poster,,,,,,,,, @@ -558,7 +558,7 @@ Improved Plain DETR,"Lin, Yutong; Yuan, Yuhui; Zhang, Zheng; Li, Chen; Zheng, Na Deep Directly-Trained Spiking Neural Networks for Object Detection,"qiaoyi, su*; Li, Guoqi; Chou, Yuhong; Hu, Yifan; Li, Jianing; Mei, Shijie; Zhang, Ziyang ",poster,2307.11411,https://arxiv.org/abs/2307.11411,,https://huggingface.co/papers/2307.11411,,,,7,0 GACE: Geometry Aware Confidence Enhancement for Black-box 3D Object Detectors on LiDAR-Data,"Schinagl, David*; Krispel, Georg; Fruhwirth-Reisinger, Christian; Possegger, Horst; Bischof, Horst",poster,,,,,,,,, StageInteractor: Query-based Object Detector with Cross-stage Interaction,"Teng, Yao; Liu, Haisong; Guo, Sheng; Wang, Limin*",poster,2304.04978,https://arxiv.org/abs/2304.04978,,https://huggingface.co/papers/2304.04978,,,,4,0 -Adaptive Rotated Convolution for Rotated Object Detection,"Pu, Yifan; Wang, Yiru; Xia, Zhuofan; Han, Yizeng; Wang, Yulin; Gan, Weihao; Wang, ZiDong; Song, Shiji; Huang, Gao*",poster,2303.07820,https://arxiv.org/abs/2303.07820,,https://huggingface.co/papers/2303.07820,,,,9,0 +Adaptive Rotated Convolution for Rotated Object Detection,"Pu, Yifan; Wang, Yiru; Xia, Zhuofan; Han, Yizeng; Wang, Yulin; Gan, Weihao; Wang, ZiDong; Song, Shiji; Huang, Gao*",poster,2303.0782,https://arxiv.org/abs/2303.07820,,https://huggingface.co/papers/2303.07820,,,,9,0 Decoupled DETR: Spatially Disentangling Localization and Classification for Improved End-to-End Object Detection,"Zhang, Manyuan*; Song, Guanglu; Liu, Yu; Li, Hongsheng",poster,,,,,,,,, Exploring Transformers for Open-world Instance Segmentation,"Wu, Jiannan*; Jiang, Yi; Yan, Bin; Lu, Huchuan; Yuan, Zehuan; Luo, Ping",poster,2308.04206,https://arxiv.org/abs/2308.04206,,https://huggingface.co/papers/2308.04206,,,,6,0 DDG-Net: Discriminability-Driven Graph Network for Weakly-supervised Temporal Action Localization,"Tang, Xiaojun*; Fan, Junsong; Luo, Chuanchen; Zhang, Zhaoxiang; Zhang, Man; Yang, Zongyuan",poster,,,,,,,,, @@ -573,9 +573,9 @@ Cascade-DETR: Delving into High-Quality Universal Object Detection,"Ye, Mingqiao Representation Disparity-aware Distillation for 3D Object Detection,"Li, Yanjing*; Xu, Sheng; Lin, Mingbao; Yin, Jihao; Zhang, Baochang; Cao, Xianbin",poster,2308.10308,https://arxiv.org/abs/2308.10308,,https://huggingface.co/papers/2308.10308,,,,6,0 FeatEnHancer: Enhancing Hierarchical Features for Object Detection and Beyond Under Low-Light Vision,"Hashmi, Khurram Azeem*; Kallempudi, Goutham; Stricker, Didier; Afzal, Muhammad Zeshan",poster,2308.03594,https://arxiv.org/abs/2308.03594,,https://huggingface.co/papers/2308.03594,,,,4,0 DetZero: Rethinking Offboard 3D Object Detection with Long-term Sequential Point Clouds,"Ma, Tao*; Yang, Xuemeng; Zhou, Hongbin; Li, Xin; Shi, Botian; Liu, Junjie; Yang, Yuchen; Liu, Zhizheng; He, Liang; Li, Hongsheng; Li, Yikang; Qiao, Yu",poster,2306.06023,https://arxiv.org/abs/2306.06023,,https://huggingface.co/papers/2306.06023,,,,12,0 -DETRs with Collaborative Hybrid Assignments Training,"Zong, Zhuofan*; Song, Guanglu; Liu, Yu",poster,2211.12860,https://arxiv.org/abs/2211.12860,https://github.com/Sense-X/Co-DETR,https://huggingface.co/papers/2211.12860,,,,3,0 +DETRs with Collaborative Hybrid Assignments Training,"Zong, Zhuofan*; Song, Guanglu; Liu, Yu",poster,2211.1286,https://arxiv.org/abs/2211.12860,https://github.com/Sense-X/Co-DETR,https://huggingface.co/papers/2211.12860,,,,3,0 Open Vocabulary Object Detection With an Open Corpus,"Wang, Jiong*; zhang, huiming; Hong, Haiwen; Jin, Xuan; He, Yuan; xue, hui; Zhao, Zhou",poster,,,,,,,,, -SparseDet: Improving Sparsely Annotated Object Detection with Pseudo-positive Mining,"Suri, Saksham*; Rambhatla, Sai Saketh ; Chellappa, Rama; Shrivastava, Abhinav",poster,2201.04620,https://arxiv.org/abs/2201.04620,,https://huggingface.co/papers/2201.04620,,,,4,0 +SparseDet: Improving Sparsely Annotated Object Detection with Pseudo-positive Mining,"Suri, Saksham*; Rambhatla, Sai Saketh ; Chellappa, Rama; Shrivastava, Abhinav",poster,2201.0462,https://arxiv.org/abs/2201.04620,,https://huggingface.co/papers/2201.04620,,,,4,0 Unsupervised Anomaly Detection with Diffusion Probabilistic Model,"Zhang, Xinyi*; Li, Naiqi; Li, Jiawei; Dai, Tao; Jiang, Yong; Xia, Shu-Tao",poster,,,,,,,,, UniTR: A Unified and Efficient Multi-Modal Transformer for Bird's-Eye-View Representation,"Wang, Haiyang*; Tang, Hao; Shi, Shaoshuai; Li, Aoxue; Li, Zhenguo; Schiele, Bernt; Wang, Liwei",poster,,,,,,,,, Focus the Discrepancy: Intra- and Inter-Correlation Learning for Image Anomaly Detection,"Yao, Xincheng*; Li, Ruoqi; Qian, Zefeng; Luo, Yan; Zhang, Chongyang",poster,,,,,,,,, @@ -592,7 +592,7 @@ Delving into Motion-Aware Matching for Monocular 3D Object Tracking,"Huang, Kuan FB-BEV: BEV Representation from Forward-Backward View Transformations,"Li, Zhiqi*; Yu, Zhiding; Wang, Wenhai; Anandkumar, Animashree; Lu, Tong; Alvarez, Jose M",poster,,,,,,,,, Learning from Noisy Data for Semi-Supervised 3D Object Detection,"Chen, Zehui; Li, Zhenyu; Wang, Shuo; Fu, Dengpan; Zhao, Feng*",poster,,,,,,,,, Boosting Long-tailed Object Detection via Step-wise Learning on Smooth-tail Data,"Dong, Na*; Zhang, Yongqiang; Ding, Mingli; Lee, Gim Hee",poster,2305.12833,https://arxiv.org/abs/2305.12833,,https://huggingface.co/papers/2305.12833,,,,4,0 -Objects do not disappear: Video object detection by single-frame object location anticipation,"Liu, Xin*; Karimi Nejadasl, Fatemeh; van Gemert, Jan C; Booij, Olaf; Pintea, Silvia L",poster,2308.04770,https://arxiv.org/abs/2308.04770,https://github.com/L-KID/Videoobject-detection-by-location-anticipation,https://huggingface.co/papers/2308.04770,,,,5,0 +Objects do not disappear: Video object detection by single-frame object location anticipation,"Liu, Xin*; Karimi Nejadasl, Fatemeh; van Gemert, Jan C; Booij, Olaf; Pintea, Silvia L",poster,2308.0477,https://arxiv.org/abs/2308.04770,https://github.com/L-KID/Videoobject-detection-by-location-anticipation,https://huggingface.co/papers/2308.04770,,,,5,0 Unified Visual Relationship Detection with Vision and Language Models,"Zhao, Long*; Yuan, Liangzhe; Gong, Boqing; Cui, Yin; Schroff, Florian; Yang, Ming-Hsuan; Adam, Hartwig; Liu, Ting",poster,2303.08998,https://arxiv.org/abs/2303.08998,,https://huggingface.co/papers/2303.08998,,,,8,0 Universal Domain Adaptation via Compressive Attention Matching,"zhu, didi; Li, Yinchuan; Yuan, Junkun; Li, Zexi; Kuang, Kun; Wu, Chao*",poster,2304.11862,https://arxiv.org/abs/2304.11862,,https://huggingface.co/papers/2304.11862,,,,6,0 Unsupervised Domain Adaptive Detection with Network Stability Analysis,"Zhou, Wenzhang; Fan, Heng; Luo, Tiejian; Zhang, Libo*",poster,2308.08182,https://arxiv.org/abs/2308.08182,https://github.com/tiankongzhang/NSA,https://huggingface.co/papers/2308.08182,,,,4,0 @@ -605,7 +605,7 @@ Editing Implicit Assumptions in Text-to-Image Diffusion Models,"Orgad, Hadas; Ka DINAR: Diffusion Inpainting of Neural Textures for One-Shot Human Avatars,"Svitov, David*; Gudkov, Dmitrii; Bashirov, Renat; Lempitsky, Victor",poster,2303.09375,https://arxiv.org/abs/2303.09375,,https://huggingface.co/papers/2303.09375,,,,4,1 Smoothness Similarity Regularization for Few-Shot GAN Adaptation,"Sushko, Vadim*; Wang, Ruyu; Gall, Jürgen",poster,2308.09717,https://arxiv.org/abs/2308.09717,,https://huggingface.co/papers/2308.09717,,,,3,0 HSR-Diff: Hyperspectral Image Super-Resolution via Conditional Diffusion Models,"Wu, Chanyue*; Bai, Yunpeng; Wang, Dong; Mao, Hanyu; Li, Ying; Shen, Qiang",poster,,,,,,,,, -Long-Term Photometric Consistent Novel View Synthesis with Diffusion Models,"Yu, Jason J*; Forghani, Fereshteh; Brubaker, Marcus A; Derpanis, Konstantinos G",poster,2304.10700,https://arxiv.org/abs/2304.10700,,https://huggingface.co/papers/2304.10700,,,,4,0 +Long-Term Photometric Consistent Novel View Synthesis with Diffusion Models,"Yu, Jason J*; Forghani, Fereshteh; Brubaker, Marcus A; Derpanis, Konstantinos G",poster,2304.107,https://arxiv.org/abs/2304.10700,,https://huggingface.co/papers/2304.10700,,,,4,0 AutoDiffusion: Training-Free Optimization of Time Steps and Architectures for Automated Diffusion Model Acceleration,"Li, Lijiang; Li, Huixia; Zheng, Xiawu; Wu, Jie; Xiao, Xuefeng; Wang, Rui; Zheng, Min ; Pan, Xin; Chao, Fei*; Ji, Rongrong",poster,,,,,,,,, GaFET: Learning Geometry-aware Facial Expression Translation from In-The-Wild Images,"Ma, Tianxiang*; Li, Bingchuan; He, Qian; Dong, Jing; Tan, Tieniu",poster,2308.03413,https://arxiv.org/abs/2308.03413,,https://huggingface.co/papers/2308.03413,,,,5,0 Collecting The Puzzle Pieces: Disentangled Self-Driven Human Pose Transfer by Permuting Textures,"Li, Nannan*; Shih, Kevin; Plummer, Bryan",poster,2210.01887,https://arxiv.org/abs/2210.01887,https://github.com/NannanLi999/pt_square,https://huggingface.co/papers/2210.01887,,,,3,0 @@ -645,7 +645,7 @@ Deep Image Harmonization with Learnable Augmentation,"Niu, Li*; Cao, Junyan; Con Out-of-domain GAN inversion via Invertibility Decomposition for Photo-Realistic Human Face Manipulation,"YANG, Xin*; XU, Xiaogang; Chen, Yingcong",poster,2212.09262,https://arxiv.org/abs/2212.09262,,https://huggingface.co/papers/2212.09262,,,,3,0 Bidirectionally Deformable Motion Modulation For Video-based Human Pose Transfer,"Yu, Wing Yin*; Po, Lai-Man; Cheung, Ray; Zhao, Yuzhi; XUE, Yu; Li, Kun",poster,2307.07754,https://arxiv.org/abs/2307.07754,,https://huggingface.co/papers/2307.07754,,,,6,0 Size Does Matter: Size-aware Virtual Try-on via Clothing-oriented Transformation Try-on Network,"Chen, Chieh-Yun*; Chen, Yi-Chung; Shuai, Hong-Han; Cheng, Wen-Huang",poster,,,,,,,,, -VidStyleODE: Disentangled Video Editing via StyleGAN and NeuralODEs,"Haji Ali, Moayed; Bond, Andrew; Birdal, Tolga*; Karacan, Levent; Ceylan, Duygu; Erdem, Erkut; Erdem, Aykut",poster,2304.06020,https://arxiv.org/abs/2304.06020,,https://huggingface.co/papers/2304.06020,,,,7,0 +VidStyleODE: Disentangled Video Editing via StyleGAN and NeuralODEs,"Haji Ali, Moayed; Bond, Andrew; Birdal, Tolga*; Karacan, Levent; Ceylan, Duygu; Erdem, Erkut; Erdem, Aykut",poster,2304.0602,https://arxiv.org/abs/2304.06020,,https://huggingface.co/papers/2304.06020,,,,7,0 Learning Global-aware Kernel for Image Harmonization,"Shen, Xintian*; Zhang, Jiangning; Chen, Jun; Bai, Shipeng; Han, Yue; Wang, Yabiao; Wang, Chengjie; Liu, Yong",poster,2305.11676,https://arxiv.org/abs/2305.11676,https://github.com/XintianShen/GKNet,https://huggingface.co/papers/2305.11676,,,,8,0 Expressive Text-to-Image Generation with Rich-Text,"Ge, Songwei*; Park, Taesung; Zhu, Jun-Yan; Huang, Jia-Bin",poster,,,,,,,,, A Large-Scale Outdoor Multi-modal Dataset and Benchmark for Novel View Synthesis and Implicit Scene Reconstruction,"Lu, Chongshan; Yin, Fukun; Chen, Xin; Liu, Wen; Chen, Tao*; Yu, Gang; Fan, Jiayuan",poster,2301.06782,https://arxiv.org/abs/2301.06782,,https://huggingface.co/papers/2301.06782,,,,6,0 @@ -677,7 +677,7 @@ On the Audio-visual Synchronization for Lip-to-Speech Synthesis,"NIU, Zhe*; Mak, Be Everywhere - Hear Everything (BEE): Audio Scene Reconstruction by Sparse Audio-Visual Samples ,"Chen, Mingfei*; Su, Kun; Shlizerman, Eli",poster,,,,,,,,, Dense 2D-3D Indoor Prediction with Sound via Aligned Cross-Modal Distillation,"Yun, Heeseung*; Na, Joonil; Kim, Gunhee",poster,,,,,,,,, Hyperbolic Audio-visual Zero-shot Learning,"Hong, Jie*; Hayder, Zeeshan; Han, Junlin; Fang, Pengfei; Harandi, Mehrtash; Petersson, Lars",poster,2308.12558,https://arxiv.org/abs/2308.12558,,https://huggingface.co/papers/2308.12558,,,,6,2 -AdVerb: Visually Guided Audio Dereverberation,"Chowdhury, Sanjoy*; Ghosh, Sreyan; Dasgupta, Subhrajyoti; Ratnarajah, Anton J; Tyagi, Utkarsh; Manocha, Dinesh",poster,2308.12370,https://arxiv.org/abs/2308.12370,,https://huggingface.co/papers/2308.12370,,,,6,0 +AdVerb: Visually Guided Audio Dereverberation,"Chowdhury, Sanjoy*; Ghosh, Sreyan; Dasgupta, Subhrajyoti; Ratnarajah, Anton J; Tyagi, Utkarsh; Manocha, Dinesh",poster,2308.1237,https://arxiv.org/abs/2308.12370,,https://huggingface.co/papers/2308.12370,,,,6,0 Sound Localization from Motion: Jointly Learning Sound Direction and Camera Rotation,"Chen, Ziyang*; Qian, Shengyi; Owens, Andrew",poster,2303.11329,https://arxiv.org/abs/2303.11329,,https://huggingface.co/papers/2303.11329,,,,3,1 Learning Conditional Control for Pretrained Text-to-Image Diffusion Models,"Zhang, Lvmin*; Rao, Anyi; Agrawala, Maneesh",oral,,,,,,,,, Factorized Inverse Path Tracing for Efficient and Accurate Material-Lighting Estimation,"Zhu, Rui*; Wu, Liwen; Ramamoorthi, Ravi; Zhu, Yinhao; Cai, Hong; Matai, Janarbek; Li, Tzu-Mao; Yaldiz, Mustafa B; Porikli, Fatih; Chandraker, Manmohan",oral,2304.05669,https://arxiv.org/abs/2304.05669,https://github.com/lwwu2/fipt,https://huggingface.co/papers/2304.05669,,,,10,0 @@ -685,7 +685,7 @@ Manipulate by Seeing: Creating Manipulation Controllers from Pre-Trained Represe 3D Implicit Transporter for Temporally Consistent Keypoint Discovery,"Zhong, Chengliang*; Zheng, Yuhang; Zheng, Yupeng; Zhao, Hao; Wang, Ling; Mu, Xiaodong; Yi, Li; Zhao, Jian; zhang, liang xin; Li, Pengfei; Zhou, Guyue; Yang, Chao",oral,,,,,,,,, Chordal Averaging on Flag Manifolds and Its Applications,"Mankovich, Nathan; Birdal, Tolga*",oral,2303.13501,https://arxiv.org/abs/2303.13501,https://github.com/nmank/FlagAveraging,https://huggingface.co/papers/2303.13501,,,,2,0 UniDexGrasp++: Improving Universal Dexterous Grasping via Geometry-aware Curriculum Learning and Iterative Generalist-Specialist Learning,"Wan, Weikang; Geng, Haoran; Liu, Yun; Shan, Zikang; Yang, Yaodong; Yi, Li; Wang, He*",oral,,,,,,,,, -GameFormer: Game-theoretic Modeling and Learning of Transformer-based Interactive Prediction and Planning for Autonomous Driving,"Huang, Zhiyu*; Liu, Haochen; Lv, Chen",oral,2303.05760,https://arxiv.org/abs/2303.05760,,https://huggingface.co/papers/2303.05760,,,,3,0 +GameFormer: Game-theoretic Modeling and Learning of Transformer-based Interactive Prediction and Planning for Autonomous Driving,"Huang, Zhiyu*; Liu, Haochen; Lv, Chen",oral,2303.0576,https://arxiv.org/abs/2303.05760,,https://huggingface.co/papers/2303.05760,,,,3,0 PPR: Physically Plausible Reconstruction from Monocular Videos,"Yang, Gengshan*; Yang, Shuo; Zhang, John; Manchester, Zachary; Ramanan, Deva",oral,,,,,,,,, Zolly: Zoom Focal Length Correctly for Perspective-Distorted Human Mesh Reconstruction,"Wang, Wenjia*; Ge, Yongtao; Mei, Haiyi; Cai, Zhongang; Sun, Qingping; Wang, Yanjun; Shen, Chunhua; Yang, Lei; Komura, Taku",oral,2303.13796,https://arxiv.org/abs/2303.13796,,https://huggingface.co/papers/2303.13796,,,,9,0 ACLS: Adaptive and Conditional Label Smoothing for Network Calibration,"Park, Hyekang; Noh, Jongyoun; Oh, Youngmin; Baek, Donghyeon; Ham, Bumsub*",oral,2308.11911,https://arxiv.org/abs/2308.11911,,https://huggingface.co/papers/2308.11911,,,,5,0 @@ -720,8 +720,8 @@ Ref-NeuS: Ambiguity-Reduced Neural Implicit Surface Learning for Multi-View Reco Generative Diffusions in Augmented Spaces: A Complete Recipe,"Pandey, Kushagra*; Mandt, Stephan",oral,2303.01748,https://arxiv.org/abs/2303.01748,https://github.com/mandt-lab/PSLD,https://huggingface.co/papers/2303.01748,,,,2,0 MMVP: Motion-Matrix-based Video Prediction,"Zhong, Yiqi*; Liang, Luming; Zharkov, Ilya; Neumann, Ulrich",oral,2308.16154,https://arxiv.org/abs/2308.16154,,https://huggingface.co/papers/2308.16154,,,,4,0 Robust Monocular Depth Estimation under Challenging Conditions,"Gasperini, Stefano*; Morbitzer, Nils; Jung, HyunJun; Navab, Nassir; Tombari, Federico",poster,2308.09711,https://arxiv.org/abs/2308.09711,,https://huggingface.co/papers/2308.09711,,,,5,1 -UMC: A Unified Bandwidth-efficient and Multi-resolution based Collaborative Perception Framework,"Wang, Tianhang; Chen, Guang*; Chen, Kai; Liu, Zhengfa; bo, zhang; Knoll, Alois C.; Jiang, Changjun",poster,2303.12400,https://arxiv.org/abs/2303.12400,,https://huggingface.co/papers/2303.12400,,,,7,0 -View Consistent Purification for Accurate Cross-View Localization,"Wang, Shan*; Zhang, Yanhao; Vora, Ankit; Perincherry, Akhil; LI, HONGDONG",poster,2308.08110,https://arxiv.org/abs/2308.08110,,https://huggingface.co/papers/2308.08110,,,,5,0 +UMC: A Unified Bandwidth-efficient and Multi-resolution based Collaborative Perception Framework,"Wang, Tianhang; Chen, Guang*; Chen, Kai; Liu, Zhengfa; bo, zhang; Knoll, Alois C.; Jiang, Changjun",poster,2303.124,https://arxiv.org/abs/2303.12400,,https://huggingface.co/papers/2303.12400,,,,7,0 +View Consistent Purification for Accurate Cross-View Localization,"Wang, Shan*; Zhang, Yanhao; Vora, Ankit; Perincherry, Akhil; LI, HONGDONG",poster,2308.0811,https://arxiv.org/abs/2308.08110,,https://huggingface.co/papers/2308.08110,,,,5,0 Semi-supervised Semantics-guided Adversarial Training for Robust Trajectory Prediction,"Jiao, Ruochen*; Liu, Xiangguo; SATO, TAKAMI; Chen, Alfred; Qi, Zhu",poster,,,,,,,,, NeRF-LOAM: Neural Implicit Representation for Large-Scale Incremental LiDAR Odometry and Mapping,"DENG, Junyuan; Wu, Qi; Chen, Xieyuanli*; Xia, Songpengcheng; Sun, Zhen; Liu, Guoqing; Yu, Wenxian; Pei, Ling",poster,,,,,,,,, MapPrior: A Generative Approach for Bird’s-Eye View Perception,"Zhu, Xiyue*; Zyrianov, Vlas; Liu, Zhijian; Wang, Shenlong",poster,,,,,,,,, @@ -811,7 +811,7 @@ Vanishing Point Estimation in Uncalibrated Images with Prior Gravity Direction," Detailed Clothed Avatar Reconstruction from Implicit Distribution Fields,"Yang, Xueting; Luo, Yihao; Xiu, Yuliang; Wei, Wang; Xu, Hao; Fan, Zhaoxin*",poster,,,,,,,,, 3D Distillation: Improving Self-Supervised Monocular Depth Estimation on Reflective Surfaces,"Shi, Xuepeng*; Dikov, Georgi; Reitmayr, Gerhard; Kim, Tae-Kyun (T-K); Ghafoorian, Mohsen",poster,,,,,,,,, DeformToon3D: Deformable 3D Toonification from Neural Radiance Fields,"Zhang, Junzhe*; Lan, Yushi; Yang, Shuai; Hong, Fangzhou; Wang, Quan; Yeo, Chai Kiat; Liu, Ziwei; Loy, Chen Change",poster,,,,,,,,, -MonoDETR: Depth-guided Transformer for Monocular 3D Object Detection,"Zhang, Renrui*; Qiu, Han; Wang, Tai; Guo, Ziyu; Cui, Ziteng; Gao, Peng; Qiao, Yu; Li, Hongsheng",poster,2203.13310,https://arxiv.org/abs/2203.13310,https://github.com/ZrrSkywalker/MonoDETR,https://huggingface.co/papers/2203.13310,,,,9,0 +MonoDETR: Depth-guided Transformer for Monocular 3D Object Detection,"Zhang, Renrui*; Qiu, Han; Wang, Tai; Guo, Ziyu; Cui, Ziteng; Gao, Peng; Qiao, Yu; Li, Hongsheng",poster,2203.1331,https://arxiv.org/abs/2203.13310,https://github.com/ZrrSkywalker/MonoDETR,https://huggingface.co/papers/2203.13310,,,,9,0 ReLeaPS : Reinforcement Learning-based Illumination Planning for Generalized Photometric Stereo,"Chan, Jun Hoong*; Yu, Bohan; Guo, Heng; Ren, Jieji; Lu, Zongqing; Shi, Boxin",poster,,,,,,,,, Convex Decomposition of Indoor Scenes,"Vavilala, Vaibhav S*; Forsyth, David",poster,2307.04246,https://arxiv.org/abs/2307.04246,,https://huggingface.co/papers/2307.04246,,,,2,0 NeRO: Neural Fields for Single-View 3D Reconstruction of Outdoor Scenes,"Irshad, Muhammad Zubair*; Zakharov, Sergey; Liu, Katherine; Guizilini, Vitor; Kollar, Thomas; Gaidon, Adrien; Ambru?, Rare? A; Kira, Zsolt",poster,,,,,,,,, @@ -821,7 +821,7 @@ Distribution-Aligned Diffusion for Human Mesh Recovery,"Foo, Lin Geng*; Gong, Ji Towards Zero-Shot Scale-Aware Monocular Depth Estimation,"Guizilini, Vitor*; Vasiljevic, Igor; Chen, Dian; Ambru?, Rare? A; Gaidon, Adrien",poster,2306.17253,https://arxiv.org/abs/2306.17253,,https://huggingface.co/papers/2306.17253,,,,5,0 Learning Depth Estimation for Transparent and Mirror Surfaces,"Costanzino, Alex*; Zama Ramirez, Pierluigi; Poggi, Matteo; Tosi, Fabio; Mattoccia, Stefano; Di Stefano, Luigi",poster,2307.15052,https://arxiv.org/abs/2307.15052,,https://huggingface.co/papers/2307.15052,,,,6,0 Uni-3D: A Universal Model for Panoptic 3D Scene Reconstruction,"Zhang, Xiang*; Chen, Zeyuan; Wei, Fangyin; Tu, Zhuowen",poster,,,,,,,,, -3D VR Sketch Guided 3D Shape Prototyping and Exploration,"Luo, Ling*; Chowdhury, Pinaki Nath; Xiang, Tao; Song, Yi-Zhe; Gryaditskaya, Yulia",poster,2306.10830,https://arxiv.org/abs/2306.10830,https://github.com/Rowl1ng/3Dsketch2shape,https://huggingface.co/papers/2306.10830,,,,5,0 +3D VR Sketch Guided 3D Shape Prototyping and Exploration,"Luo, Ling*; Chowdhury, Pinaki Nath; Xiang, Tao; Song, Yi-Zhe; Gryaditskaya, Yulia",poster,2306.1083,https://arxiv.org/abs/2306.10830,https://github.com/Rowl1ng/3Dsketch2shape,https://huggingface.co/papers/2306.10830,,,,5,0 Transparent Shape from a Single View Polarization Image,"Mingqi, Shao*; Xia, Chongkun; Yang, Zhendong; Huang, Junnan; Wang, Xueqian",poster,2204.06331,https://arxiv.org/abs/2204.06331,,https://huggingface.co/papers/2204.06331,,,,5,0 Get3DHuman: Lifting StyleGAN-Human into a 3D Generative Model using Pixel-aligned Reconstruction Priors,"XIONG, Zhangyang*; Kang, Di; Jin, Derong; Chen, Weikai; Bao, Linchao; Cui, Shuguang; Han, Xiaoguang",poster,2302.01162,https://arxiv.org/abs/2302.01162,,https://huggingface.co/papers/2302.01162,,,,7,0 Turn-the-Camera: Towards Zero-Shot Novel View Synthesis and 3D Reconstruction,"Liu, Ruoshi*; Wu, Rundi; Van Hoorick, Basile; Tokmakov, Pavel; Zakharov, Sergey; Vondrick, Carl",poster,,,,,,,,, @@ -850,13 +850,13 @@ HumanMAC: Masked Motion Completion for Human Motion Prediction,"Chen, Ling-Hao*; Geometrized Transformer for Self-Supervised Homography Estimation,"Liu, Jiazhen; Li, Xirong*",poster,,,,,,,,, SemARFlow: Injecting Semantics into Unsupervised Optical Flow Estimation for Autonomous Driving,"Yuan, Shuai *; Yu, Shuzhi; Kim, Hannah H; Tomasi, Carlo",poster,2303.06209,https://arxiv.org/abs/2303.06209,https://github.com/duke-vision/semantic-unsup-flow-release,https://huggingface.co/papers/2303.06209,,,,4,0 Shi-NeSS: Detecting Good and Stable Keypoints with a Neural Stability Score,"Pakulev, Konstantin*; Ferrer, Gonzalo; Vakhitov, Alexander",poster,,,,,,,,, -Robust Object Modeling for Visual Tracking,"Cai, Yidong; Liu, Jie*; Tang, Jie; Wu, Gangshan",poster,2308.05140,https://arxiv.org/abs/2308.05140,,https://huggingface.co/papers/2308.05140,,,,4,0 +Robust Object Modeling for Visual Tracking,"Cai, Yidong; Liu, Jie*; Tang, Jie; Wu, Gangshan",poster,2308.0514,https://arxiv.org/abs/2308.05140,,https://huggingface.co/papers/2308.05140,,,,4,0 Social Diffusion: Long-term Multiple Human Motion Anticipation,"Tanke, Julian*; Zhang, Linguang; Zhao, Amy; Tang, Chengcheng; Cai, Yujun; Wang, Lezi; WU, PO-CHEN; Gall, Jürgen; Keskin, Cem",poster,,,,,,,,, Exploring Lightweight Hierarchical Vision Transformers for Efficient Visual Tracking,"Kang, Ben*; Chen, Xin; Wang, Dong; Peng, Houwen; Lu, Huchuan",poster,2308.06904,https://arxiv.org/abs/2308.06904,,https://huggingface.co/papers/2308.06904,,,,5,0 HMD-NeMo: Online 3D Avatar Motion Generation From Sparse Observations,"Aliakbarian, Sadegh*; Saleh, Fatemeh; Collier, David; Cameron, Pashmina; Cosker, Darren P",poster,,,,,,,,, Learning Fine-Graied Features for Pixel-wise Video Correspondences,"Li, Rui; Zhou, Shenglong; Liu, Dong*",poster,,,,,,,,, GAFlow: Incorporating Gaussian Attention into Optical Flow,"Luo, Ao; Yang, Fan; Li, Xin; Nie, Lang; Lin, Chunyu; Fan, Haoqiang; Liu, Shuaicheng*",poster,,,,,,,,, -Occ$^2$Net: Robust Image Matching Based on 3D Occupancy Estimation for Occluded Regions,"Fan, Miao*; Chen, Mingrui; Hu, Chen; Zhou, Shuchang",poster,2308.16160,https://arxiv.org/abs/2308.16160,,https://huggingface.co/papers/2308.16160,,,,4,0 +Occ$^2$Net: Robust Image Matching Based on 3D Occupancy Estimation for Occluded Regions,"Fan, Miao*; Chen, Mingrui; Hu, Chen; Zhou, Shuchang",poster,2308.1616,https://arxiv.org/abs/2308.16160,,https://huggingface.co/papers/2308.16160,,,,4,0 Locomotion-Action-Manipulation: Synthesizing Human-Scene Interactions in Complex 3D Environments,"Lee, Jiye*; Joo, Hanbyul",poster,,,,,,,,, Trajectory Unified Transformer for Pedestrian Trajectory Prediction,"Shi, Liushuai; Wang, Le*; Zhou, Sanping; Hua, Gang",poster,,,,,,,,, TMA: Temporal Motion Aggregation for Event-based Optical Flow,"Liu, Haotian; Chen, Guang; Qu, Sanqing; Zhang, Yanping; Li, Zhijun*; Knoll, Alois C.; Jiang, Changjun",poster,2303.11629,https://arxiv.org/abs/2303.11629,https://github.com/ispc-lab/TMA,https://huggingface.co/papers/2303.11629,,,,7,0 @@ -879,7 +879,7 @@ Persistent-Transient Duality: A Multi-mechanism Approach for Modeling Human-Obje Deep Homography Mixture for Single Image Rolling Shutter Correction,"Yan, Weilong; Tan, Robby T.; Zeng, Bing; Liu, Shuaicheng*",poster,,,,,,,,, Fast Neural Scene Flow,"Li, Xueqian*; Zheng, Jianqiao; Ferroni, Francesco; Kaesemodel Pontes, Jhony; Lucey, Simon",poster,2304.09121,https://arxiv.org/abs/2304.09121,,https://huggingface.co/papers/2304.09121,,,,5,0 RLSAC: Reinforcement Learning enhanced Sample Consensus for End-to-End Robust Estimation,"Nie, Chang; Wang, Guangming; Liu, Zhe; Cavalli, Luca; Pollefeys, Marc; Wang, Hesheng*",poster,2308.05318,https://arxiv.org/abs/2308.05318,https://github.com/IRMVLab/RLSAC,https://huggingface.co/papers/2308.05318,,,,6,0 -MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Tracking,"Gao, Ruopeng*; Wang, Limin",poster,2307.15700,https://arxiv.org/abs/2307.15700,https://github.com/MCG-NJU/MeMOTR,https://huggingface.co/papers/2307.15700,,,,2,0 +MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Tracking,"Gao, Ruopeng*; Wang, Limin",poster,2307.157,https://arxiv.org/abs/2307.15700,https://github.com/MCG-NJU/MeMOTR,https://huggingface.co/papers/2307.15700,,,,2,0 MBPTrack: Improving 3D Point Cloud Tracking with Memory Networks and Box Priors,"Xu, Tianxing*; Guo, Yuan-Chen; Lai, Yu-Kun; Zhang, Song-Hai ",poster,2303.05071,https://arxiv.org/abs/2303.05071,,https://huggingface.co/papers/2303.05071,,,,4,0 SportsMOT: A Large Multi-Object Tracking Dataset in Diverse Sports Scenes,"Cui, Yutao; Zeng, Chenkai; Zhao, Xiaoyu; Yang, YiChun; Wu, Gangshan; Wang, Limin*",poster,,,,,,,,, Heterogeneous Diversity Driven Active Learning for Multi-Object Tracking,"Li, Rui; Zhang, Baopeng; Liu, Jun; Liu, Wei; Zhao, Jian; Teng, Zhu *",poster,,,,,,,,, @@ -915,7 +915,7 @@ SOAR: Scene-debiasing Open-set Action Recognition,"Zhai, Yuanhao*; Liu, Ziyi; Wu Leveraging Spatio-Temporal Dependency for Skeleton-Based Action Recognition,"Lee, Jungho*; Lee, Minhyeok; Cho, Suhwan; Woo, Sungmin; Jang, Sungjun; Lee, Sangyoun",poster,2212.04761,https://arxiv.org/abs/2212.04761,,https://huggingface.co/papers/2212.04761,,,,6,0 Cross-Modal Learning with 3D Deformable Attention for Action Recognition,"Kim, Sangwon*; Ahn, Dasom; Ko, Byoung Chul",poster,2212.05638,https://arxiv.org/abs/2212.05638,,https://huggingface.co/papers/2212.05638,,,,3,0 Generative Action Description Prompts for Skeleton-based Action Recognition,"Xiang, Wangmeng*; Li, Chao; Zhou, Yuxuan; wang, biao; Zhang, Lei",poster,,,,,,,,, -Self-Feedback DETR for Temporal Action Detection,"Kim, Jihwan*; Lee, Miso; Heo, Jae-Pil",poster,2308.10570,https://arxiv.org/abs/2308.10570,,https://huggingface.co/papers/2308.10570,,,,3,0 +Self-Feedback DETR for Temporal Action Detection,"Kim, Jihwan*; Lee, Miso; Heo, Jae-Pil",poster,2308.1057,https://arxiv.org/abs/2308.10570,,https://huggingface.co/papers/2308.10570,,,,3,0 Skip-Plan: Procedure Planning in Instructional Videos via Condensed Action Space Learning,"Li, Zhiheng*; Geng, Wenjia; Li, Muheng; Chen, Lei; Tang, Yansong; Lu, Jiwen; Zhou, Jie",poster,,,,,,,,, The Unreasonable Effectiveness of Large Language-Vision Models for Source-free Video Domain Adaptation,"Zara, Giacomo*; Conti, Alessandro; Roy, Subhankar; LathuiliÚre, Stéphane; Rota, Paolo; Ricci, Elisa",poster,2308.09139,https://arxiv.org/abs/2308.09139,,https://huggingface.co/papers/2308.09139,,,,6,1 Multimodal Motion Conditioned Diffusion Model for Skeleton-based Video Anomaly Detection,"Flaborea, Alessandro*; Collorone, Luca; D'Amely di Melendugno, Guido Maria; D'Arrigo, Stefano; Prenkaj, Bardh; Galasso, Fabio",poster,2307.07205,https://arxiv.org/abs/2307.07205,,https://huggingface.co/papers/2307.07205,,,,6,1 @@ -934,7 +934,7 @@ Tiled Multiplane Images for Practical 3D Photography,"Khan, Numair*; Lanman, Dou Eulerian Single-Photon Vision,"Gupta, Shantanu*; Gupta, Mohit",poster,,,,,,,,, ProPainter: Improving Video Inpainting with Enhanced Propagation and Efficient Transformer,"Zhou, Shangchen*; Li, Chongyi; Chan, Kelvin C.K.; Loy, Chen Change",poster,,,,,,,,, Autoregressive for Neural Processes,"Tai, Jinyang*",poster,,,,,,,,, -DOLCE: A Model-Based Probabilistic Diffusion Framework for Limited-Angle CT Reconstruction,"Liu, Jiaming*; Anirudh, Rushil; J. Thiagarajan, Jayaraman; He, Stewart; Mohan, Kadri Aditya; Kamilov, Ulugbek S.; Kim, Hyojin",poster,2211.12340,https://arxiv.org/abs/2211.12340,,https://huggingface.co/papers/2211.12340,,,,7,0 +DOLCE: A Model-Based Probabilistic Diffusion Framework for Limited-Angle CT Reconstruction,"Liu, Jiaming*; Anirudh, Rushil; J. Thiagarajan, Jayaraman; He, Stewart; Mohan, Kadri Aditya; Kamilov, Ulugbek S.; Kim, Hyojin",poster,2211.1234,https://arxiv.org/abs/2211.12340,,https://huggingface.co/papers/2211.12340,,,,7,0 GlowGAN: Unsupervised Learning of HDR Images from LDR Images in the Wild,"Wang, Chao*; Serrano, Ana; Pan, Xingang; Chen, Bin; Myszkowski, Karol ; Seidel, Hans-Peter; Theobalt, Christian; Leimkuehler, Thomas",poster,2211.12352,https://arxiv.org/abs/2211.12352,,https://huggingface.co/papers/2211.12352,,,,8,0 Score-Based Diffusion Models as Principled Priors for Inverse Imaging,"Feng, Berthy T*; Smith, Jamie; Rubinstein, Michael; Chang, Huiwen; Bouman, Katherine; Freeman, William T.",poster,2304.11751,https://arxiv.org/abs/2304.11751,,https://huggingface.co/papers/2304.11751,,,,6,0 NLOS-NeuS: Non-line-of-sight Neural Implicit Surface,"Fujimura, Yuki*; Kushida, Takahiro; Funatomi, Takuya; Mukaigawa, Yasuhiro",poster,,,,,,,,, @@ -954,7 +954,7 @@ Generalized Lightness Adaptation with Channel Selective Normalization,"Yao, Ming Towards Nonlinear-Motion-Aware and Occlusion-Robust Rolling Shutter Correction,"Qu, Delin*; Lao, Yizhen; Wang, Zhigang; Wang, Dong; Zhao, Bin; Li, Xuelong",poster,2303.18125,https://arxiv.org/abs/2303.18125,https://github.com/DelinQu/qrsc,https://huggingface.co/papers/2303.18125,,,,6,0 FCCNs: Fully Complex-valued Convolutional Networks using Complex-valued Color Model and Loss Function,"Yadav, Saurabh*; Jerripothula, Koteswar Rao",poster,,,,,,,,, Event Camera Data Pre-training,"Yang, Yan*; Pan, Liyuan; liu, Liu",poster,2301.01928,https://arxiv.org/abs/2301.01928,,https://huggingface.co/papers/2301.01928,,,,3,0 -Improving 3D Imaging with Pre-Trained Perpendicular 2D Diffusion Models,"Lee, Suhyeon*; Chung, Hyungjin; Park, Min Young; Park, Jonghyeok; Ryu, Wi-Sun; Ye, Jong Chul",poster,2303.08440,https://arxiv.org/abs/2303.08440,,https://huggingface.co/papers/2303.08440,,,,6,0 +Improving 3D Imaging with Pre-Trained Perpendicular 2D Diffusion Models,"Lee, Suhyeon*; Chung, Hyungjin; Park, Min Young; Park, Jonghyeok; Ryu, Wi-Sun; Ye, Jong Chul",poster,2303.0844,https://arxiv.org/abs/2303.08440,,https://huggingface.co/papers/2303.08440,,,,6,0 Multiscale Structure Guided Diffusion for Image Deblurring,"Ren, Mengwei*; Delbracio, Mauricio; Talebi, Hossein ; Gerig, Guido; Milanfar, Peyman",poster,2212.01789,https://arxiv.org/abs/2212.01789,,https://huggingface.co/papers/2212.01789,,,,5,0 Generalizing Event-Based Motion Deblurring in Real-World Scenarios,"Zhang, Xiang; Yu, Lei*; Yang, Wen; Liu, Jianzhuang; Xia, Gui-Song",poster,2308.05932,https://arxiv.org/abs/2308.05932,,https://huggingface.co/papers/2308.05932,,,,5,0 On the Robustness of Normalizing Flows for Inverse Problems in Imaging,"Hong, Seongmin; PARK, INBUM; Chun, Se Young*",poster,2212.04319,https://arxiv.org/abs/2212.04319,,https://huggingface.co/papers/2212.04319,,,,3,0 @@ -1011,14 +1011,14 @@ Part-Aware Transformer for Generalizable Person Re-identification,"Ni, Hao; Li, Towards Universal Image Embeddings: A Large-Scale Dataset and Challenge for Generic Image Representations,"Ypsilantis, Nikolaos-Antonios*; Chen, Kaifeng; Cao, Bingyi; LipovskÃœ, Mário; Dogan-Schonberger, Pelin; Makosa, Grzegorz; Bluntschli, Boris; Seyedhosseini, Mojtaba; Araujo, Andre; Chum, Ondrej",poster,,,,,,,,, Dual Learning with Dynamic Knowledge Distillation for Partially Relevant Video Retrieval,"Dong, Jianfeng*; Zhang, Minsong; zhang, zheng; Chen, Xianke; Liu, Daizong; Qu, Xiaoye; Liu, Baolong; Wang, Xun",poster,,,,,,,,, Fine-grained Unsupervised Domain Adaptation for Gait Recognition,"Ma, Kang; Fu, Ying*; Zheng, Dezhi; Peng, Yunjie; Cao, Chunshui; Huang, Yongzhen",poster,,,,,,,,, -FashionNTM: Multi-turn Fashion Image Retrieval via Cascaded Memory,"Pal, Anwesan*; Wadhwa, Sahil; Jaiswal, Ayush; Zhang, Xu; Wu, Yue; Chada, Rakesh; Natarajan, Pradeep; Christensen, Henrik I",poster,2308.10170,https://arxiv.org/abs/2308.10170,,https://huggingface.co/papers/2308.10170,,,,8,1 +FashionNTM: Multi-turn Fashion Image Retrieval via Cascaded Memory,"Pal, Anwesan*; Wadhwa, Sahil; Jaiswal, Ayush; Zhang, Xu; Wu, Yue; Chada, Rakesh; Natarajan, Pradeep; Christensen, Henrik I",poster,2308.1017,https://arxiv.org/abs/2308.10170,,https://huggingface.co/papers/2308.10170,,,,8,1 CrossLoc3D: Aerial-Ground Cross-Source 3D Place Recognition ,"Guan, Tianrui*; Muthuselvam, Aswath; Hoover, Montana; Wang, Xijun; Liang, Jing; Sathyamoorthy, Adarsh Jagan ; Conover, Damon; Manocha, Dinesh",poster,,,,,,,,, ImbSAM: A Closer Look at Sharpness-Aware Minimization in Class-Imbalanced Recognition,"Zhou, Yixuan; Qu, Yi; Xu, Xing*; Shen, Heng Tao",poster,2308.07815,https://arxiv.org/abs/2308.07815,https://github.com/cool-xuan/Imbalanced_SAM,https://huggingface.co/papers/2308.07815,,,,4,0 LFS-GAN: Lifelong Few-Shot Image Generation,"Seo, Juwon*; Kang, Jisu; Park, Gyeong-Moon",poster,,,,,,,,, Augmented Box Replay: Overcoming Foreground Shift for Incremental Object Detection,"Liu, Yuyang*; Cong, Yang; Goswami, Dipam; Liu, Xialei; van de Weijer, Joost",poster,2307.12427,https://arxiv.org/abs/2307.12427,,https://huggingface.co/papers/2307.12427,,,,5,0 Contrastive Model Adaptation for Cross-Condition Robustness in Semantic Segmentation,"BrÃŒggemann, David*; Sakaridis, Christos; Broedermann, Tim; Van Gool, Luc",poster,2303.05194,https://arxiv.org/abs/2303.05194,https://github.com/brdav/cma,https://huggingface.co/papers/2303.05194,,,,4,0 Towards Effective Instance Discrimination Contrastive Loss for Unsupervised Domain Adaptation,"Zhang, Yixin; Wang, Zilei*; li, junjie; Zhuang, Jiafan; Lin, Zihan",poster,,,,,,,,, -Adversarial Bayesian Augmentation for Single-Source Domain Generalization,"Cheng, Sheng*; Gokhale, Tejas; Yang, Yezhou",poster,2307.09520,https://arxiv.org/abs/2307.09520,,https://huggingface.co/papers/2307.09520,,,,3,1 +Adversarial Bayesian Augmentation for Single-Source Domain Generalization,"Cheng, Sheng*; Gokhale, Tejas; Yang, Yezhou",poster,2307.0952,https://arxiv.org/abs/2307.09520,,https://huggingface.co/papers/2307.09520,,,,3,1 Measuring Asymmetric Gradient Discrepancy in Parallel Continual Learning,"Lyu, Fan; Sun, Qing; Shang, Fanhua; Wan, Liang; Feng, Wei*",poster,,,,,,,,, CSDA: Learning Category-Scale Joint Feature for Domain Adaptive Object Detection,"Gao, Changlong; Liu, Chengxu*; Dun, Yujie; Qian, Xueming",poster,,,,,,,,, Distilling from Similar Tasks for Transfer Learning on a Budget,"Borup, Kenneth*; Phoo, Cheng Perng; Hariharan, Bharath",poster,2304.12314,https://arxiv.org/abs/2304.12314,,https://huggingface.co/papers/2304.12314,,,,3,1 @@ -1026,7 +1026,7 @@ Complementary Domain Adaptation and Generalization for Unsupervised Continual Do Camera-driven Representation Learning for Unsupervised Domain Adaptive Person Re-identification,"Lee, Geon; Lee, Sanghoon; KIM, DOHYUNG; Shin, Younghoon; Yoon, Yongsang; Ham, Bumsub*",poster,2308.11901,https://arxiv.org/abs/2308.11901,,https://huggingface.co/papers/2308.11901,,,,6,0 Introducing Language Guidance in Prompt-based Continual Learning,"Khan, Muhammad Gul Zain Ali*; Naeem, Muhammad Ferjad; Van Gool, Luc; Stricker, Didier; Tombari, Federico; Afzal, Muhammad Zeshan",poster,2308.15827,https://arxiv.org/abs/2308.15827,,https://huggingface.co/papers/2308.15827,,,,6,0 Fast and Accurate Transferability Measurement by Evaluating Intra-class Feature Variance,"Xu, Huiwen; Kang, U*",poster,2308.05986,https://arxiv.org/abs/2308.05986,,https://huggingface.co/papers/2308.05986,,,,2,0 -A Unified Continual Learning Framework with General Parameter-Efficient Tuning,"Gao, Qiankun; Zhao, Chen; Sun, Yifan; Xi, Teng; zhang, gang; Ghanem, Bernard; Zhang, Jian*",poster,2303.10070,https://arxiv.org/abs/2303.10070,https://github.com/gqk/LAE,https://huggingface.co/papers/2303.10070,,,,7,0 +A Unified Continual Learning Framework with General Parameter-Efficient Tuning,"Gao, Qiankun; Zhao, Chen; Sun, Yifan; Xi, Teng; zhang, gang; Ghanem, Bernard; Zhang, Jian*",poster,2303.1007,https://arxiv.org/abs/2303.10070,https://github.com/gqk/LAE,https://huggingface.co/papers/2303.10070,,,,7,0 SFHarmony: Source Free Domain Adaptation for Distributed Neuroimaging Analysis,"Dinsdale, Nicola K*; Jenkinson, Mark ; Namburete, Ana Ineyda L",poster,2303.15965,https://arxiv.org/abs/2303.15965,https://github.com/nkdinsdale/SFHarmony,https://huggingface.co/papers/2303.15965,,,,3,0 Towards Realistic Evaluation of Industrial Continual Learning Scenarios with an emphasis on Energy Consumption and Computational Footprint,"Chavan, Vivek*; Koch, Paul; SchlÃŒter, Marian; Briese, Clemens",poster,,,,,,,,, Exploring Consistency in Cross-Domain Transformer for Domain Adaptive Semantic Segmentation,"Wang, Kaihong; Kim, Donghyun*; Feris, Rogerio; Betke, Margrit",poster,2211.14703,https://arxiv.org/abs/2211.14703,,https://huggingface.co/papers/2211.14703,,,,5,0 @@ -1046,7 +1046,7 @@ Regularized Mask Tuning: Uncovering Hidden Knowledge in Pre-trained Vision-Langu NAPA-VQ: Neighborhood-Aware Prototype Augmentation with Vector Quantization for Continual Learning,"Malepathirana, Tamasha A*; Senanayake, Damith A; Halgamuge, Saman",poster,,,,,,,,, A Sentence Speaks a Thousand Images: Domain Generalization through Distilling CLIP with Language Guidance,"Huang, Zeyi*; Zhou, Andy; Ling, Zijian; Cai, Mu; Wang, Haohan; Lee, Yong Jae",poster,,,,,,,,, ViM: Vision Middleware for Unified Downstream Transferring,"Feng, Yutong*; Gong, Biao; Jiang, Jianwen; Lv, Yiliang; Shen, Yujun; Zhao, Deli; Zhou, Jingren",poster,2303.06911,https://arxiv.org/abs/2303.06911,,https://huggingface.co/papers/2303.06911,,,,7,0 -Learning to Learn: How to Continuously Teach Humans and Machines,"Singh, Parantak*; Li, You; Sikarwar, Ankur; Lei, Stan Weixian; Gao, Difei; Talbot , Morgan B; Sun, Ying; Shou, Mike Zheng; Kreiman, Gabriel; Zhang, Mengmi",poster,2211.15470,https://arxiv.org/abs/2211.15470,,https://huggingface.co/papers/2211.15470,,,,10,0 +Learning to Learn: How to Continuously Teach Humans and Machines,"Singh, Parantak*; Li, You; Sikarwar, Ankur; Lei, Stan Weixian; Gao, Difei; Talbot , Morgan B; Sun, Ying; Shou, Mike Zheng; Kreiman, Gabriel; Zhang, Mengmi",poster,2211.1547,https://arxiv.org/abs/2211.15470,,https://huggingface.co/papers/2211.15470,,,,10,0 A Good Student is Cooperative and Reliable: CNN-Transformer Collaborative Learning for Semantic Segmentation,"ZHU, Jinjing*; Luo, Yunhao; Zheng, Xu; Wang, Hao; Wang, Lin ",poster,2307.12574,https://arxiv.org/abs/2307.12574,,https://huggingface.co/papers/2307.12574,,,,5,1 Online Class Incremental Learning on Stochastic Blurry Task Boundary via Mask and Visual Prompt Tuning,"Moon, Jun Yeong*; Park, KeonHee; Kim, Jung Uk; Park, Gyeong-Moon",poster,2308.09303,https://arxiv.org/abs/2308.09303,,https://huggingface.co/papers/2308.09303,,,,4,0 Heterogeneous Forgetting Compensation for Class-Incremental Learning,"Dong, Jiahua*; Cong, Yang; liang, wenqi; Sun, Gan",poster,2308.03374,https://arxiv.org/abs/2308.03374,https://github.com/JiahuaDong/HFC,https://huggingface.co/papers/2308.03374,,,,4,0 @@ -1065,13 +1065,13 @@ Dynamic Point Fields,"Prokudin, Sergey*; Ma, Qianli; Raafat, Maxime; Valentin, J Generalizing Neural Human Fitting to Unseen Pose With Articulated E(3) Equivariance,"Feng, Haiwen*; Kulits, Peter; Liu, Shichen; Black, Michael J.; Fernandez Abrevaya, Victoria",oral,,,,,,,,, Probabilistic Human Mesh Recovery in 3D Scenes from Egocentric Views,"Zhang, Siwei*; Ma, Qianli; Zhang, Yan; Aliakbarian, Sadegh; Cosker, Darren P; Tang, Siyu",oral,2304.06024,https://arxiv.org/abs/2304.06024,,https://huggingface.co/papers/2304.06024,,,,6,0 DECO: Dense Estimation of 3D Human-Scene Contact In The Wild ,"Tripathi, Shashank*; Chatterjee, Agniv; Passy, Jean-Claude; Yi, Hongwei; Tzionas, Dimitrios; Black, Michael J.",oral,,,,,,,,, -Decoupled Iterative Refinement Framework for Interacting Hands Reconstruction from a Single RGB Image,"Ren, Pengfei*; Wen, Chao; Zheng, Xiaozheng; Xue, Zhou; Sun, Haifeng; Qi, Qi; Wang, Jingyu; Liao, Jianxin",oral,2302.02410,https://arxiv.org/abs/2302.02410,,https://huggingface.co/papers/2302.02410,,,,8,0 +Decoupled Iterative Refinement Framework for Interacting Hands Reconstruction from a Single RGB Image,"Ren, Pengfei*; Wen, Chao; Zheng, Xiaozheng; Xue, Zhou; Sun, Haifeng; Qi, Qi; Wang, Jingyu; Liao, Jianxin",oral,2302.0241,https://arxiv.org/abs/2302.02410,,https://huggingface.co/papers/2302.02410,,,,8,0 Chasing clouds: Differentiable volumetric rendering of point clouds as a highly efficient and accurate loss for large-scale deformable 3D registration,"Heinrich, Mattias Paul*; Bigalke, Alexander; Großbröhmer, Christoph; Hansen, Lasse",oral,,,,,,,,, Rehearsal-Free Domain Continual Face Anti-Spoofing: Generalize More and Forget Less,"Cai, Rizhao*; Cui, Yawen; Li, Zhi; Yu, Zitong; Li, Haoliang; Hu, Yongjian; Kot, Alex",oral,,,,,,,,, A 5-Point Minimal Solver for Event Camera Relative Motion Estimation,"Gao, Ling*; Su, Hang; Gehrig, Daniel; Cannici, Marco; Scaramuzza, Davide; Kneip, Laurent",oral,,,,,,,,, General Planar Motion from a 3D point pair,"Dibene Simental, Juan Carlos*; Min, Zhixiang; Dunn, Enrique",oral,,,,,,,,, Beyond the Pixel: a Photometrically Calibrated HDR Dataset for Luminance and Color Temperature Prediction,"Bolduc, Christophe; Giroux, Justine; Marc, Hébert; Demers, Claude MH; Lalonde, Jean-Francois*",oral,,,,,,,,, -DDFM: Denoising Diffusion Model for Multi-Modality Image Fusion,"Zhao, Zixiang*; Bai, Haowen; Zhu, Yuanzhi; Zhang, Jiangshe; Xu, Shuang; Zhang, Yulun; Zhang, Kai; Meng, Deyu; Timofte, Radu; Van Gool, Luc",oral,2303.06840,https://arxiv.org/abs/2303.06840,https://github.com/Zhaozixiang1228/MMIF-DDFM,https://huggingface.co/papers/2303.06840,,,,10,0 +DDFM: Denoising Diffusion Model for Multi-Modality Image Fusion,"Zhao, Zixiang*; Bai, Haowen; Zhu, Yuanzhi; Zhang, Jiangshe; Xu, Shuang; Zhang, Yulun; Zhang, Kai; Meng, Deyu; Timofte, Radu; Van Gool, Luc",oral,2303.0684,https://arxiv.org/abs/2303.06840,https://github.com/Zhaozixiang1228/MMIF-DDFM,https://huggingface.co/papers/2303.06840,,,,10,0 Iterative Prompt Learning for Unsupervised Backlit Image Enhancement,"Liang, Zhexin*; Li, Chongyi; Zhou, Shangchen; Feng, Ruicheng; Loy, Chen Change",oral,2303.17569,https://arxiv.org/abs/2303.17569,,https://huggingface.co/papers/2303.17569,,,,5,0 Similarity Min-Max: Zero-Shot Day-Night Domain Adaptation,"Luo, Rundong*; Wang, Wenjing; Yang, Wenhan; Liu, Jiaying",oral,,,,,,,,, Multi-interactive Feature Learning and a Full-time Multi-modality Benchmark for Image Fusion and Segmentation,"Liu, Jinyuan; Liu, Zhu; Wu, Guanyao; Ma, Long; Liu, Risheng; Zhong, Wei; Luo, Zhongxuan; Fan, Xin*",oral,2308.02097,https://arxiv.org/abs/2308.02097,https://github.com/JinyuanLiu-CV/SegMiF,https://huggingface.co/papers/2308.02097,,,,8,0 @@ -1112,12 +1112,12 @@ Learning Non-Local Spatial-Angular Correlation for Light Field Image Super-Resol Both Diverse and Realism Matter: Physical Attribute and Style Alignment for Rainy Image Generation,"Yu, Changfeng; Chen, Shiming; Chang, Yi*; Song, Yibing; Yan, Luxin",poster,,,,,,,,, Learned Image Reasoning Prior Penetrates Deep Unfolding Network for Panchromatic and Multi-spectral Image Fusion,"zhou, man*; Huang, Jie; Zheng, Naishan; Li, Chongyi",poster,2308.16083,https://arxiv.org/abs/2308.16083,,https://huggingface.co/papers/2308.16083,,,,4,0 The Devil is in the Upsampling: Architecture Decisions Made Simpler for Denoising with Deep Image Prior,"Liu, Yilin; Li, Jiang; Pang, Yunkui; Nie, Dong; Yap, Pew-Thian*",poster,,,,,,,,, -SimFIR: A Simple Framework for Fisheye Image Rectification with Self-supervised Representation Learning,"Feng, Hao; Wang, Wendi; Deng, Jiajun; Zhou, Wengang ; Li, Li*; Li, Houqiang",poster,2308.09040,https://arxiv.org/abs/2308.09040,,https://huggingface.co/papers/2308.09040,,,,6,0 +SimFIR: A Simple Framework for Fisheye Image Rectification with Self-supervised Representation Learning,"Feng, Hao; Wang, Wendi; Deng, Jiajun; Zhou, Wengang ; Li, Li*; Li, Houqiang",poster,2308.0904,https://arxiv.org/abs/2308.09040,,https://huggingface.co/papers/2308.09040,,,,6,0 Exploring Temporal Frequency Spectrum in Deep Video Deblurring,"Zhu, Qi; zhou, man; Zheng, Naishan; Li, Chongyi; Huang, Jie; Zhao, Feng*",poster,,,,,,,,, -ExposureDiffusion: Learning to Expose for Low-light Image Enhancement,"Wang, Yufei*; Yu, Yi; Yang, Wenhan; Guo, Lanqing; Chau, Lap-Pui; Kot, Alex; Wen, Bihan",poster,2307.07710,https://arxiv.org/abs/2307.07710,,https://huggingface.co/papers/2307.07710,,,,7,0 +ExposureDiffusion: Learning to Expose for Low-light Image Enhancement,"Wang, Yufei*; Yu, Yi; Yang, Wenhan; Guo, Lanqing; Chau, Lap-Pui; Kot, Alex; Wen, Bihan",poster,2307.0771,https://arxiv.org/abs/2307.07710,,https://huggingface.co/papers/2307.07710,,,,7,0 High-resolution Document Shadow Removal via A Large-scale Real-world Dataset and A Frequency-aware Shadow Erasing Net,"Chen, Xuhang*; Cun, Xiaodong; Li, Zinuo; Pun, Chi-Man",poster,2308.14221,https://arxiv.org/abs/2308.14221,https://github.com/CXH-Research/DocShadow-SD7K,https://huggingface.co/papers/2308.14221,,,,4,0 Towards Saner Deep Image Registration,"Duan, Bin*; Zhong, Ming; Yan, Yan",poster,2307.09696,https://arxiv.org/abs/2307.09696,https://github.com/tuffr5/Saner-deep-registration,https://huggingface.co/papers/2307.09696,,,,3,0 -VideoFlow: Exploiting Temporal Cues for Multi-frame Optical Flow Estimation,"Shi, Xiaoyu*; Huang, Zhaoyang; BIAN, Weikang; Li, dasong; Zhang, Manyuan; Cheung, Ka Chun; See, Simon; Qin, Hongwei; Dai, Jifeng; Li, Hongsheng",poster,2303.08340,https://arxiv.org/abs/2303.08340,https://github.com/XiaoyuShi97/VideoFlow,https://huggingface.co/papers/2303.08340,,,,10,0 +VideoFlow: Exploiting Temporal Cues for Multi-frame Optical Flow Estimation,"Shi, Xiaoyu*; Huang, Zhaoyang; BIAN, Weikang; Li, dasong; Zhang, Manyuan; Cheung, Ka Chun; See, Simon; Qin, Hongwei; Dai, Jifeng; Li, Hongsheng",poster,2303.0834,https://arxiv.org/abs/2303.08340,https://github.com/XiaoyuShi97/VideoFlow,https://huggingface.co/papers/2303.08340,,,,10,0 Scene Matters: Model-based Deep Video Compression,"Tang, Lv*; zhang, xinfeng; Zhang, Gai; Ma, xiaoqi",poster,2303.04557,https://arxiv.org/abs/2303.04557,,https://huggingface.co/papers/2303.04557,,,,4,0 Non-Coaxial Event-guided Motion Deblurring with Spatial Alignment,"Cho, Hoonhee*; Jeong, Yuhwan; Kim, Taewoo; Yoon, Kuk-Jin",poster,,,,,,,,, Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement,"Cai, Yuanhao*; Bian, Hao; Lin, Jing; Wang, Haoqian; Timofte, Radu; Zhang, Yulun",poster,2303.06705,https://arxiv.org/abs/2303.06705,https://github.com/caiyuanhao1998/Retinexformer,https://huggingface.co/papers/2303.06705,,,,6,0 @@ -1128,7 +1128,7 @@ Spherical Space Feature Decomposition for Guided Depth Map Super-Resolution,"Zha Empowering Low-Light Image Enhancer through Customized Learnable Priors,"Zheng, Naishan; Dong, Yanmeng; Rui, Xiangyu; Huang, Jie; Li, Chongyi; zhou, man; Zhao, Feng*",poster,,,,,,,,, Learning Image Harmonization in the Linear Color Space,"Xu, Ke*; Hancke, Gerhard P.; Lau, Rynson W.H.",poster,,,,,,,,, Under-Display Camera Image Restoration with Scattering Effect,"SONG, Binbin; Chen, Xiangyu; Xu, Shuning; Zhou, Jiantao*",poster,2308.04163,https://arxiv.org/abs/2308.04163,https://github.com/NamecantbeNULL/SRUDC,https://huggingface.co/papers/2308.04163,,,,4,0 -Iterative Soft Shrinkage Learning for Efficient Image Super-Resolution,"wang, jiamian*; Wang, Huan; Zhang, Yulun; FU, YUN; Tao, Zhiqiang",poster,2303.09650,https://arxiv.org/abs/2303.09650,https://github.com/Jiamian-Wang/Iterative-Soft-Shrinkage-SR,https://huggingface.co/papers/2303.09650,,,,5,0 +Iterative Soft Shrinkage Learning for Efficient Image Super-Resolution,"wang, jiamian*; Wang, Huan; Zhang, Yulun; FU, YUN; Tao, Zhiqiang",poster,2303.0965,https://arxiv.org/abs/2303.09650,https://github.com/Jiamian-Wang/Iterative-Soft-Shrinkage-SR,https://huggingface.co/papers/2303.09650,,,,5,0 Single Image Defocus Deblurring via Inverse Kernel Modeling and Prediction,"Quan, Yuhui*; Yao, Xin; Ji, Hui",poster,,,,,,,,, Degradation-Resistant Unfolding Network for Heterogeneous Image Fusion,"He, Chunming*; Li, Kai; Xu, Guoxia; Zhang, Yulun; Hu, Runze; Guo, Zhenhua; Li, Xiu",poster,,,,,,,,, Graphics2RAW: Mapping Computer Graphics Images to Sensor RAW Images,"Seo, Donghwan Ian*; Punnappurath, Abhijith; Zhao, Luxi; Abdelhamed, Abdelrahman; Tedla, SaiKiran K; Park, Sang Uk; Choe, Jihwan; Brown, Michael S",poster,,,,,,,,, @@ -1163,7 +1163,7 @@ Implicit Neural Representation for Cooperative Low-light Image Enhancement,"Yang Physically-plausible illumination distribution estimation,"Ershov, Egor; Tesalin, Vasily; Ermakov, Ivan A*; Brown, Michael S",poster,,,,,,,,, Score Priors Guided Deep Variational Inference for Unsupervised Real-World Single Image Denoising,"Cheng, Jun; Liu, Tao; Tan, Shan*",poster,2308.04682,https://arxiv.org/abs/2308.04682,,https://huggingface.co/papers/2308.04682,,,,3,0 Semantic-Aware Dynamic Parameter for Video Inpainting Transformer,"Lee, Eunhye; Yoo, Jinsu; Yang, Yunjeong; Baik, Sungyong; Kim, Tae Hyun*",poster,,,,,,,,, -Pixel Adaptive Deep Unfolding Transformer for Hyperspectral Image Reconstruction,"Li, Miaoyu; Fu, Ying*; Liu, Ji; Zhang, Yulun",poster,2308.10820,https://arxiv.org/abs/2308.10820,https://github.com/MyuLi/PADUT,https://huggingface.co/papers/2308.10820,,,,4,0 +Pixel Adaptive Deep Unfolding Transformer for Hyperspectral Image Reconstruction,"Li, Miaoyu; Fu, Ying*; Liu, Ji; Zhang, Yulun",poster,2308.1082,https://arxiv.org/abs/2308.10820,https://github.com/MyuLi/PADUT,https://huggingface.co/papers/2308.10820,,,,4,0 Improving Lens Flare Removal with General-Purpose Pipeline and Multiple Light,"Yuyan, Zhou; Liang, Dong*; Chen, Songcan; Huang, Sheng-Jun; Yang, Shuo; Li, Chongyi",poster,,,,,,,,, RFD-ECNet: Extreme Underwater Image Compression with Reference to Feature Dictionary,"Li, Mengyao; Shen, Liquan*; Ye, Peng; Feng, Guorui; Wang, Zheyin",poster,,,,,,,,, Learning Continuous Exposure Value Representations for Single-Image HDR Reconstruction,"Chen, Sykai*; Yen, Hung-Lin; Liu, Yu-Lun; Chen, Min-Hung; Hu, Hou-Ning; Peng, Wen-Hsiao; Lin, Yen-Yu",poster,,,,,,,,, @@ -1173,19 +1173,19 @@ Beyond Image Borders: Learning Feature Extrapolation for Unbounded Image Composi MetaF2N: Blind Image Super-Resolution by Learning Efficient Model Adaptation from Faces,"Yin, Zhicun; Liu, Ming*; Li, Xiaoming; Yang, Hui; Xiao, Longan; Zuo, Wangmeng",poster,,,,,,,,, Boundary-Aware Divide and Conquer: A Diffusion-based Solution for Unsupervised Shadow Removal,"Guo, Lanqing*; Wang, Chong; Yang, Wenhan; Wang, Yufei; Wen, Bihan",poster,,,,,,,,, Leveraging Inpainting for Single-Image Shadow Removal,"Li, Xiaoguang*; Guo, Qing; Abdelfattah, Rabab; Lin, Di; Feng, Wei; Tsang, Ivor; Wang, Song",poster,2302.05361,https://arxiv.org/abs/2302.05361,,https://huggingface.co/papers/2302.05361,,,,7,0 -Hybrid Spectral Denoising Transformer with Guided Attention,"Lai, Zeqiang; Yan, Chenggang; Fu, Ying*",poster,2303.09040,https://arxiv.org/abs/2303.09040,,https://huggingface.co/papers/2303.09040,,,,3,0 +Hybrid Spectral Denoising Transformer with Guided Attention,"Lai, Zeqiang; Yan, Chenggang; Fu, Ying*",poster,2303.0904,https://arxiv.org/abs/2303.09040,,https://huggingface.co/papers/2303.09040,,,,3,0 Examining Autoexposure for Challenging Scenes,"Tedla, SaiKiran K*; Yang, Beixuan; Brown, Michael S",poster,,,,,,,,, Self-supervised Learning to Bring Dual Reversed Rolling Shutter Images Alive,"Shang, Wei; Ren, Dongwei*; feng, chaoyu; Xiaotao, Wang; LEI, LEI; Zuo, Wangmeng",poster,2305.19862,https://arxiv.org/abs/2305.19862,https://github.com/shangwei5/SelfDRSC,https://huggingface.co/papers/2305.19862,,,,6,0 DiffIR: Efficient Diffusion Model for Image Restoration,"xia, bin; Zhang, Yulun; Wang, Shiyin; Wang, Yitong; Xinglong, Wu; Tian, Yapeng; Yang, Wenming*; Van Gool, Luc",poster,2303.09472,https://arxiv.org/abs/2303.09472,https://github.com/Zj-BinXia/DiffIR,https://huggingface.co/papers/2303.09472,,,,8,0 Sparse Sampling Transformer with Uncertainty-Driven Ranking for Unified Removal of Raindrops and Rain Streaks,"Chen, Sixiang*; Ye, Tian; Bai, Jinbin; Chen, Erkang; Jun, Shi; Zhu, Lei",poster,2308.14153,https://arxiv.org/abs/2308.14153,,https://huggingface.co/papers/2308.14153,,,,6,0 -LMR: A Large-Scale Multi-Reference Dataset for Reference-based Super-Resolution,"Zhang, Lin; Li, Xin; He, Dongliang; Li, Fu; Ding, Errui; Zhang, Zhaoxiang*",poster,2303.04970,https://arxiv.org/abs/2303.04970,,https://huggingface.co/papers/2303.04970,,,,5,0 -Low-Light Image Enhancement with Illumination-Aware Gamma Correction and Complete Image Modelling Network,"Wang, Yinglong*; Liu, Zhen; Liu, Jianzhuang; Xu, Songcen; Liu, Shuaicheng",poster,2308.08220,https://arxiv.org/abs/2308.08220,,https://huggingface.co/papers/2308.08220,,,,5,0 +LMR: A Large-Scale Multi-Reference Dataset for Reference-based Super-Resolution,"Zhang, Lin; Li, Xin; He, Dongliang; Li, Fu; Ding, Errui; Zhang, Zhaoxiang*",poster,2303.0497,https://arxiv.org/abs/2303.04970,,https://huggingface.co/papers/2303.04970,,,,5,0 +Low-Light Image Enhancement with Illumination-Aware Gamma Correction and Complete Image Modelling Network,"Wang, Yinglong*; Liu, Zhen; Liu, Jianzhuang; Xu, Songcen; Liu, Shuaicheng",poster,2308.0822,https://arxiv.org/abs/2308.08220,,https://huggingface.co/papers/2308.08220,,,,5,0 Single Image Reflection Separation via Component Synergy,"Hu, Qiming; Guo, Xiaojie*",poster,2308.10027,https://arxiv.org/abs/2308.10027,https://github.com/mingcv/DSRNet,https://huggingface.co/papers/2308.10027,,,,2,0 Learning Rain Location Prior for Nighttime Deraining,"Zhang, Fan; Li, Yu; You, Shaodi; Fu, Ying*",poster,,,,,,,,, Exploring Positional Characteristics of Dual-Pixel Data for Camera Autofocus,"Choi, Myungsub; Lee, Hana; Lee, Hyong-Euk*",poster,,,,,,,,, Continuously Masked Transformer for Image Inpainting,"Ko, Keunsoo*; Kim, Chang-Su",poster,,,,,,,,, Learning Data-Driven Vector-Quantized Degradation Model for Animation Video Super-Resolution,"Tuo, Zixi; Yang, Huan*; Fu, Jianlong; Dun, Yujie; Qian, Xueming",poster,2303.09826,https://arxiv.org/abs/2303.09826,,https://huggingface.co/papers/2303.09826,,,,5,1 -Spatially-Adaptive Feature Modulation for Efficient Image Super-Resolution,"Sun, Long*; Dong, Jiangxin; Tang, Jinhui; Pan, Jinshan",poster,2302.13800,https://arxiv.org/abs/2302.13800,https://github.com/sunny2109/SAFMN,https://huggingface.co/papers/2302.13800,,,,4,0 +Spatially-Adaptive Feature Modulation for Efficient Image Super-Resolution,"Sun, Long*; Dong, Jiangxin; Tang, Jinhui; Pan, Jinshan",poster,2302.138,https://arxiv.org/abs/2302.13800,https://github.com/sunny2109/SAFMN,https://huggingface.co/papers/2302.13800,,,,4,0 Video Adverse-Weather-Component Suppression Network via Weather Messenger and Adversarial Backpropagation,"Yang, Yijun*; Aviles-Rivero, Angelica I; Liu, Ye; Fu, Huazhu; Wang, Weiming; Zhu, Lei",poster,,,,,,,,, Snow Removal in Video: A New Dataset and A Novel Method,"Chen, Haoyu*; Ren, Jingjing; Gu, Jinjin; Wu, Hongtao; Lu, Xuequan; CAI, Haoming; Zhu, Lei",poster,,,,,,,,, Boosting Single Image Super-Resolution via Partial Channel Shifting,"Zhang, XiaoMing*; Li, Tianrui; Zhao, Xiaole",poster,,,,,,,,, @@ -1271,7 +1271,7 @@ Tracking by 3D Model Estimation of Unknown Objects in Videos,"Rozumnyi, Denys*; Algebraically rigorous quaternion framework for the neural network pose estimation problem,"Lin, Chen; Hanson, Andrew J; Hanson, Sonya M*",poster,,,,,,,,, Linear-Covariance Loss for End-to-End Learning of 6D Pose Estimation,"Liu, Fulin*; Hu, Yinlin; Salzmann, Mathieu",poster,2303.11516,https://arxiv.org/abs/2303.11516,,https://huggingface.co/papers/2303.11516,,,,3,0 2D3D-MATR: 2D-3D Matching Transformer for Detection-free Registration between Images and Point Clouds,"Li, Minhao; Qin, Zheng; Gao, Zhirui; Yi, Renjiao; Zhu, Chenyang; Guo, Yulan; Xu, Kai*",poster,,,,,,,,, -Learning Versatile 3D Shape Generation with Improved AR Models,"Luo, Simian; Qian, Xuelin*; Fu, Yanwei; Zhang, Yinda; Tai, Ying; Zhang, Zhenyu; Wang, Chengjie; Xue, Xiangyang",poster,2303.14700,https://arxiv.org/abs/2303.14700,,https://huggingface.co/papers/2303.14700,,,,8,0 +Learning Versatile 3D Shape Generation with Improved AR Models,"Luo, Simian; Qian, Xuelin*; Fu, Yanwei; Zhang, Yinda; Tai, Ying; Zhang, Zhenyu; Wang, Chengjie; Xue, Xiangyang",poster,2303.147,https://arxiv.org/abs/2303.14700,,https://huggingface.co/papers/2303.14700,,,,8,0 CaPhy: Capturing Physical Properties for Animatable Human Avatars,"Su, Zhaoqi; Hu, Liangxiao; Lin, Siyou; Zhang, Hongwen; Zhang, Shengping; Thies, Justus; Liu, Yebin*",poster,2308.05925,https://arxiv.org/abs/2308.05925,,https://huggingface.co/papers/2308.05925,,,,7,0 Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud Models,"Zha, Yaohua*; Wang, Jinpeng; Dai, Tao; Chen, Bin; Wang, Zhi; Xia, Shu-Tao",poster,2304.07221,https://arxiv.org/abs/2304.07221,https://github.com/zyh16143998882/ICCV23-IDPT,https://huggingface.co/papers/2304.07221,,,,6,0 Structure-Aware Surface Reconstruction via Primitive Assembling,"Jiang, Jingen; Zhao, Mingyang*; Xin, Shiqing; Yang, Yanchao; Wang, Hanxiao; Jia, Xiaohong; Yan, Dong-Ming",poster,,,,,,,,, @@ -1283,7 +1283,7 @@ SurfsUP: Learning Fluid Simulation for Novel Surfaces,"Mani, Arjun*; Chandratrey DeFormer: Integrating Transformers with Deformable Models for 3D Shape Abstraction from a Single Image,"Liu, Di*; Yu, Xiang; Ye, Meng; Zhangli, Qilong; Li, Zhuowei; Zhang, Zhixing; Metaxas, Dimitris N.",poster,,,,,,,,, Neural Deformable Models for 3D Bi-Ventricular Heart Shape Reconstruction and Modeling from 2D Sparse Cardiac Magnetic Resonance Imaging,"Ye, Meng*; Yang, Dong; Kanski, Mikael; Axel, Leon; Metaxas, Dimitris N.",poster,2307.07693,https://arxiv.org/abs/2307.07693,,https://huggingface.co/papers/2307.07693,,,,5,0 DiffFacto: Controllable Part-Based 3D Point Cloud Generation with Cross Diffusion,"Nakayama, Kiyohiro*; Uy, Mikaela Angelina; Huang, Jiahui; Hu, Shi-Min; Li, Ke; Guibas, Leonidas",poster,2305.01921,https://arxiv.org/abs/2305.01921,,https://huggingface.co/papers/2305.01921,,,,6,0 -Self-supervised Learning of Implicit Shape Representation with Dense Correspondence for Deformable Objects,"Zhang, Baowen*; Li, Jiahe; Deng, Xiaoming; Zhang, Yinda; Ma, Cuixia; Wang, Hongan",poster,2308.12590,https://arxiv.org/abs/2308.12590,,https://huggingface.co/papers/2308.12590,,,,6,0 +Self-supervised Learning of Implicit Shape Representation with Dense Correspondence for Deformable Objects,"Zhang, Baowen*; Li, Jiahe; Deng, Xiaoming; Zhang, Yinda; Ma, Cuixia; Wang, Hongan",poster,2308.1259,https://arxiv.org/abs/2308.12590,,https://huggingface.co/papers/2308.12590,,,,6,0 Neural Implicit Surface Evolution,"Novello, Tiago*; da Silva, Vinícius; Schardong, Guilherme G; Schirmer, Luiz; Lopes, Hélio; Velho, Luiz",poster,2201.09636,https://arxiv.org/abs/2201.09636,,https://huggingface.co/papers/2201.09636,,,,6,2 Unsupervised Semantic Segmentation of 3D Point Clouds via Cross-modal Distillation and Super-Voxel Clustering,"Chen, Zisheng; Xu, Hongbin*; Chen, WeiTao; Zhou, Zhipeng; Sun, Baigui; Xiao, Haihong; Kang, Wenxiong",poster,2304.08965,https://arxiv.org/abs/2304.08965,,https://huggingface.co/papers/2304.08965,,,,2,0 HyperDiffusion: Generating Implicit Neural Fields with Weight-Space Diffusion,"Erkoç, Ziya*; Ma, Fangchang; Shan, Qi; Niessner, Matthias; Dai, Angela",poster,2303.17015,https://arxiv.org/abs/2303.17015,,https://huggingface.co/papers/2303.17015,,,,5,1 @@ -1331,7 +1331,7 @@ Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregation,"Shan Towards Robust and Smooth 3D Multi-Person Pose Estimation from Monocular Videos in the Wild,"Park, Sungchan; Lyou, Eunyi; Lee, Inhoe; Lee, Joonseok*",poster,,,,,,,,, Humans in 4D: Reconstructing and Tracking Humans with Transformers,"Goel, Shubham*; Pavlakos, Georgios; Rajasegaran, Jathushan; Kanazawa, Angjoo; Malik, Jitendra",poster,2305.20091,https://arxiv.org/abs/2305.20091,,https://huggingface.co/papers/2305.20091,,,,5,4 NPC: Neural Point Characters from Video,"Su, Shih-Yang*; Bagautdinov, Timur; Rhodin, Helge",poster,2304.02013,https://arxiv.org/abs/2304.02013,,https://huggingface.co/papers/2304.02013,,,,3,0 -Priority-Centric Human Motion Generation in Discrete Latent Space,"Kong, Hanyang*; Gong, Kehong; Lian, Dongze; Bi Mi, Michael; Wang, Xinchao",poster,2308.14480,https://arxiv.org/abs/2308.14480,,https://huggingface.co/papers/2308.14480,,,,5,0 +Priority-Centric Human Motion Generation in Discrete Latent Space,"Kong, Hanyang*; Gong, Kehong; Lian, Dongze; Bi Mi, Michael; Wang, Xinchao",poster,2308.1448,https://arxiv.org/abs/2308.14480,,https://huggingface.co/papers/2308.14480,,,,5,0 Unsupervised Learning for Neural 3D Composition of Humans and Objects,"Kim, Taeksoo*; Saito, Shunsuke; Joo, Hanbyul",poster,,,,,,,,, Cyclic Test-Time Adaptation on Monocular Video for 3D Human Mesh Reconstruction,"Nam, Hyeongjin; Jung, Daniel Sungho; Oh, Yeonguk; Lee, Kyoung Mu*",poster,2308.06554,https://arxiv.org/abs/2308.06554,https://github.com/hygenie1228/CycleAdapt_RELEASE,https://huggingface.co/papers/2308.06554,,,,4,0 Multiple Hypotheses Meet Entropy for Pose and Shape Recovery,"Chen, Rongyu*; Yang, Linlin; Yao, Angela",poster,,,,,,,,, @@ -1369,7 +1369,7 @@ Learning Self-regulating Prompts for Vision-Language Models,"Khattak, Muhammad U Learning To Ground Instructional Articles In Videos Through Narrations,"Mavroudi, Effrosyni*; Afouras, Triantafyllos; Torresani, Lorenzo",poster,2306.03802,https://arxiv.org/abs/2306.03802,,https://huggingface.co/papers/2306.03802,,,,3,0 Ref-Egocentric: Referring Expression Comprehension Dataset from First-Person Perception of Ego4D,"Kurita, Shuhei*; Katsura, Naoki; Onami, Eri",poster,,,,,,,,, Multi3DRefer: Grounding Text Description to Multiple 3D Objects,"Zhang, Yiming*; Gong, ZeMing; Chang, Angel X",poster,,,,,,,,, -Bayesian Prompt Learning for Image-Language Model Generalization,"Derakhshani, Mohammad Mahdi*; Sanchez, Enrique; Bulat, Adrian; Turrisi da Costa, Victor G.; Snoek, Cees; Tzimiropoulos, Georgios; Martinez, Brais",poster,2210.02390,https://arxiv.org/abs/2210.02390,https://github.com/saic-fi/Bayesian-Prompt-Learning,https://huggingface.co/papers/2210.02390,,,,7,1 +Bayesian Prompt Learning for Image-Language Model Generalization,"Derakhshani, Mohammad Mahdi*; Sanchez, Enrique; Bulat, Adrian; Turrisi da Costa, Victor G.; Snoek, Cees; Tzimiropoulos, Georgios; Martinez, Brais",poster,2210.0239,https://arxiv.org/abs/2210.02390,https://github.com/saic-fi/Bayesian-Prompt-Learning,https://huggingface.co/papers/2210.02390,,,,7,1 Who are you referring to? Coreference resolution in image narrations,"Goel, Arushi*; Fernando, Basura; Keller, Frank; Bilen, Hakan",poster,2211.14563,https://arxiv.org/abs/2211.14563,,https://huggingface.co/papers/2211.14563,,,,4,0 Guiding image captioning models toward more specific captions,"Kornblith, Simon*; Li, Lala; Wang, Zirui; Nguyen, Thao T",poster,2307.16686,https://arxiv.org/abs/2307.16686,,https://huggingface.co/papers/2307.16686,,,,4,2 PreSTU: Pre-Training for Scene-Text Understanding,"Kil, Jihyung*; Changpinyo, Soravit; Chen, Xi; Hu, Hexiang; Goodman, Sebastian; Chao, Wei-Lun; Soricut, Radu",poster,2209.05534,https://arxiv.org/abs/2209.05534,,https://huggingface.co/papers/2209.05534,,,,7,0 @@ -1476,7 +1476,7 @@ Towards Open-Set Test-Time Adaptation Utilizing the Wisdom of Crowds in Entropy Gradient-based Sampling for Class Imbalanced Semi-supervised Object Detection,"Li, Jiaming; Lin, Xiangru; Zhang, Wei; Tan, Xiao; Li, Yingying; Han, Junyu; Ding, Errui; Wang, Jingdong; Li, Guanbin*",poster,,,,,,,,, Remembering Normality: Memory-guided Knowledge Distillation for Unsupervised Anomaly Detection,"Gu, Zhihao*; Liu, Liang; Chen, Xu; Yi, Ran; Zhang, Jiangning; Wang, Yabiao; Wang, Chengjie; Shu, Annan; Jiang, Guannan; Ma, Lizhuang",poster,,,,,,,,, Semi-Supervised Learning via Weight-aware Distillation under Class Distribution Mismatch,"Du, Pan; Zhao, Suyun*; Zisen, Sheng; Li, Cuiping; Chen, Hong",poster,2308.11874,https://arxiv.org/abs/2308.11874,https://github.com/RUC-DWBI-ML/research/tree/main/WAD-master,https://huggingface.co/papers/2308.11874,,,,5,0 -Label Shift Adapter for Test-Time Adaptation under Covariate and Label Shifts,"Park, Sunghyun *; Yang, Seunghan; Choo, Jaegul; Yun, Sungrack",poster,2308.08810,https://arxiv.org/abs/2308.08810,,https://huggingface.co/papers/2308.08810,,,,4,0 +Label Shift Adapter for Test-Time Adaptation under Covariate and Label Shifts,"Park, Sunghyun *; Yang, Seunghan; Choo, Jaegul; Yun, Sungrack",poster,2308.0881,https://arxiv.org/abs/2308.08810,,https://huggingface.co/papers/2308.08810,,,,4,0 GraphMatch: Semi-Supervised Learning with Graph Consistency,"Zheng, Mingkai*; You, Shan; Huang, Lang; luo, chen; Wang, Fei; Qian, Chen; Xu, Chang",poster,,,,,,,,, Unsupervised Accuracy Estimation of Deep Visual Models using Domain-Adaptive Adversarial Perturbation without Source Samples,"Lee, JoonHo*; Woo, Jae Oh; Moon, Hankyu; Lee, Kwonho",poster,2307.10062,https://arxiv.org/abs/2307.10062,,https://huggingface.co/papers/2307.10062,,,,4,0 Learning by Sorting: Self-supervised Learning with Group Ordering Constraints,"Shvetsova, Nina*; Petersen, Felix; Kukleva, Anna; Schiele, Bernt; Kuehne, Hilde",poster,2301.02009,https://arxiv.org/abs/2301.02009,,https://huggingface.co/papers/2301.02009,,,,5,0 @@ -1499,7 +1499,7 @@ Learning Semi-supervised Gaussian Mixture Models for Generalized Category Discov Learning Multiscale 3D-consistent Features from Posed Images,"Kloepfer, Dominik A*; Campbell, Dylan; Henriques, Joao F",poster,,,,,,,,, Stable Cluster Discrimination for Deep Clustering,"Qian, Qi*",poster,,,,,,,,, Cross-modal Scalable Hierarchical Clustering in Hyperbolic space,"Long, Teng*; Noord, Nanne van",poster,,,,,,,,, -Collaborative Propagation on Multiple Instance Graphs for 3D Instance Segmentation with Single-point Supervision,"Dong, Shichao*; Li, Ruibo; Wei, Jiacheng; Liu, Fayao; Lin, Guosheng",poster,2208.05110,https://arxiv.org/abs/2208.05110,,https://huggingface.co/papers/2208.05110,,,,5,1 +Collaborative Propagation on Multiple Instance Graphs for 3D Instance Segmentation with Single-point Supervision,"Dong, Shichao*; Li, Ruibo; Wei, Jiacheng; Liu, Fayao; Lin, Guosheng",poster,2208.0511,https://arxiv.org/abs/2208.05110,,https://huggingface.co/papers/2208.05110,,,,5,1 Semantics Meets Temporal Correspondence: Self-supervised Object-centric Learning in Videos,"Qian, Rui*; Ding, Shuangrui; Liu, Xian; Lin, Dahua",poster,2308.09951,https://arxiv.org/abs/2308.09951,https://github.com/shvdiwnkozbw/SMTC,https://huggingface.co/papers/2308.09951,,,,4,0 Proxy Anchor-based Unsupervised Learning for Continuous Generalized Category Discovery,"Kim, Hyungmin*; Suh, Sungho; Kim, Daehwan; Jeong, Daun; Cho, Hansang; Kim, Junmo",poster,2307.10943,https://arxiv.org/abs/2307.10943,,https://huggingface.co/papers/2307.10943,,,,6,0 DreamTeacher: Pretraining Image Backbones with Deep Generative Models,"Li, Daiqing*; Ling, Huan; Kar, Amlan; Acuna, David ; Kim, Seung Wook; Kreis, Karsten; Torralba, Antonio; Fidler, Sanja",poster,2307.07487,https://arxiv.org/abs/2307.07487,,https://huggingface.co/papers/2307.07487,,,,8,4 @@ -1511,7 +1511,7 @@ Deep Multiview Clustering by Contrasting Cluster Assignments,"Chen, Jie; Mao, Hu Re:PolyWorld - A Graph Neural Network for Polygonal Scene Parsing,"Zorzi, Stefano*; Fraundorfer, Friedrich",poster,,,,,,,,, Satlas: A Large-Scale Dataset for Remote Sensing Image Understanding,"Bastani, Favyen*; Wolters, Piper S; Gupta, Ritwik; Ferdinando, Joseph G; Kembhavi, Aniruddha",poster,,,,,,,,, Large-Scale Land Cover Mapping with Fine-Grained Classes via Class-Aware Semi-Supervised Semantic Segmentation,"Dong, Runmin*; Mou, Lichao; Chen, Mengxuan; Li, Weijia; Tong, Xin-Yi; Yuan, Shuai; Zhang, Lixian; Zheng, Juepeng; Zhu, Xiaoxiang; Fu, Haohuan",poster,,,,,,,,, -Large Selective Kernel Network for Remote Sensing Object Detection,"Li, Yuxuan*; Hou, Qibin; Zheng, Zhaohui; Cheng, Ming-Ming; Yang, Jian; Li, Xiang",poster,2303.09030,https://arxiv.org/abs/2303.09030,https://github.com/zcablii/Large-Selective-Kernel-Network,https://huggingface.co/papers/2303.09030,,,,6,0 +Large Selective Kernel Network for Remote Sensing Object Detection,"Li, Yuxuan*; Hou, Qibin; Zheng, Zhaohui; Cheng, Ming-Ming; Yang, Jian; Li, Xiang",poster,2303.0903,https://arxiv.org/abs/2303.09030,https://github.com/zcablii/Large-Selective-Kernel-Network,https://huggingface.co/papers/2303.09030,,,,6,0 GFM: Building Geospatial Foundation Models via Continual Pretraining,"Mendieta, Matias*; Han, Boran; Shi, Xingjian; Zhu, Yi; Chen, Chen",poster,2302.04476,https://arxiv.org/abs/2302.04476,,https://huggingface.co/papers/2302.04476,,,,5,0 Regularized Primitive Graph Learning for Unified Vector Mapping,"Wang, Lei*; Dai, Min; He, Jianan; Huang, Jingwei",poster,,,,,,,,, Class Prior-Free Positive-Unlabeled Learning with Taylor Variational Loss for Hyperspectral Remote Sensing Imagery,"Zhao, Hengwei*; Wang, Xinyu; Li, Jingtao; Zhong, Yanfei",poster,2308.15081,https://arxiv.org/abs/2308.15081,https://github.com/Hengwei-Zhao96/T-HOneCls,https://huggingface.co/papers/2308.15081,,,,4,0 @@ -1564,7 +1564,7 @@ INSTA-BNN: Binary Neural Network with INSTAnce-aware Threshold,"Lee, Changhun; K Deep Incubation: Training Large Models by Divide-and-Conquering,"Ni, Zanlin*; Wang, Yulin; Yu, Jiangwei; Jiang, Haojun; Cao, Yue; Huang, Gao",poster,2212.04129,https://arxiv.org/abs/2212.04129,https://github.com/LeapLabTHU/Deep-Incubation,https://huggingface.co/papers/2212.04129,,,,6,0 AdaMV-MoE: Adaptive Multi-Task Vision Mixture-of-Experts,"Chen, Tianlong*; Chen, Xuxi; Du, Xianzhi; Rashwan, Abdullah; Yang, Fan; Chen, Huizhong; Wang, Zhangyang; Li, Yeqing",poster,,,,,,,,, Overcoming Forgetting Catastrophe in Quantization-Aware Training,"Chen, Ting-An*; Yang, De-Nian; Chen, Ming-Syan",poster,,,,,,,,, -Window-Based Early-Exit Cascades for Uncertainty Estimation: When Deep Ensembles are More Efficient than Single Models,"Xia, Guoxuan*; Bouganis, Christos-Savvas",poster,2303.08010,https://arxiv.org/abs/2303.08010,https://github.com/Guoxoug/window-early-exit,https://huggingface.co/papers/2303.08010,,,,2,0 +Window-Based Early-Exit Cascades for Uncertainty Estimation: When Deep Ensembles are More Efficient than Single Models,"Xia, Guoxuan*; Bouganis, Christos-Savvas",poster,2303.0801,https://arxiv.org/abs/2303.08010,https://github.com/Guoxoug/window-early-exit,https://huggingface.co/papers/2303.08010,,,,2,0 ORC: Network Group-based Knowledge Distillation using Online Role Change,"Choi, Junyong; Cho, Hyeon; Cheung, Seokhwa; Hwang, Wonjun*",poster,2206.01186,https://arxiv.org/abs/2206.01186,,https://huggingface.co/papers/2206.01186,,,,4,0 RMP-Loss: Regularizing Membrane Potential Distribution for Spiking Neural Networks,"Guo, Yufei*; Zhang, Liwen; Chen, Yuanpei; Liu, Xiaode; peng, weihang; Zhang, Yuhan; Huang, Xuhui; Ma, Zhe",poster,,,,,,,,, Structural Alignment for Network Pruning through Partial Regularization,"Gao, Shangqian*; Zhang, Zeyu; Zhang, Yanfu; Huang, Feihu; Huang, Heng",poster,,,,,,,,, @@ -1575,7 +1575,7 @@ Efficient Joint Optimization of Layer-Adaptive Weight Pruning in Deep Neural Net Automatic Network Pruning via Hilbert-Schmidt Independence Criterion Lasso under Information Bottleneck Principle,"guo, song*; Zhang, Lei; Zheng, Xiawu; Wang, Yan; Li, Yuchao; Chao, Fei; Zhang, ShengChuan; Wu, Chenglin; Ji, Rongrong",poster,,,,,,,,, Distribution Shift Matters for Knowledge Distillation with Webly Collected Images,"Tang, Jialiang; Chen, Shuo; Niu, Gang; Sugiyama, Masashi; Gong, Chen*",poster,2307.11469,https://arxiv.org/abs/2307.11469,,https://huggingface.co/papers/2307.11469,,,,5,0 FastRecon: Few-shot Industrial Anomaly Detection via Fast Feature Reconstruction,"Zheng, Fang; Wang, Xiaoyang; HaoCheng, Li; Liu, Jiejie; Hu, Qiugui; Xiao, Jimin*",poster,,,,,,,,, -E^2VPT: An Effective and Efficient Approach for Visual Prompt Tuning,"Han, Cheng*; Wang, Qifan; Cui, Yiming; Cao, Zhiwen; Wang, Wenguan; Qi, Siyuan; Liu, Dongfang",poster,2307.13770,https://arxiv.org/abs/2307.13770,https://github.com/ChengHan111/E2VPT,https://huggingface.co/papers/2307.13770,,,,7,0 +E^2VPT: An Effective and Efficient Approach for Visual Prompt Tuning,"Han, Cheng*; Wang, Qifan; Cui, Yiming; Cao, Zhiwen; Wang, Wenguan; Qi, Siyuan; Liu, Dongfang",poster,2307.1377,https://arxiv.org/abs/2307.13770,https://github.com/ChengHan111/E2VPT,https://huggingface.co/papers/2307.13770,,,,7,0 Bridging Vision and Language Encoders: Parameter-Efficient Tuning for Referring Image Segmentation,"Xu, Zunnan; Chen, Zhihong; Zhang, Yong; Song, Yibing; Wan, Xiang; Li, Guanbin*",poster,2307.11545,https://arxiv.org/abs/2307.11545,https://github.com/kkakkkka/ETRIS,https://huggingface.co/papers/2307.11545,,,,6,0 SHACIRA - Scalable HAsh-grid Compression for Implicit Neural Representations,"Girish, Sharath*; Gupta, Kamal; Shrivastava, Abhinav",poster,,,,,,,,, Efficient Deep Space Filling Curve,"Chen, Wanli *; Yao, Xufeng; Zhang, Xinyun; Yu, Bei",poster,,,,,,,,, @@ -1584,13 +1584,13 @@ Lossy and Lossless (L$^2$) Post-training Model Size Compression,"Shi, Yumeng*; b Robustifying Token Attention for Vision Transformers,"Guo, Yong*; Stutz, David; Schiele, Bernt",poster,2303.11126,https://arxiv.org/abs/2303.11126,,https://huggingface.co/papers/2303.11126,,,,3,0 Strivec: Sparse Tri-Vector Radiance Fields,"Xu, Qiangeng; Gao, Quankai*; Su, Hao; Neumann, Ulrich; Xu, Zexiang",poster,2307.13226,https://arxiv.org/abs/2307.13226,,https://huggingface.co/papers/2307.13226,,,,5,2 Image Features with Formal Privacy Guarantees,"Pittaluga, Francesco*; Zhuang, Bingbing",poster,,,,,,,,, -SparseFusion: Fusing Multi-Modal Sparse Representations for Multi-Sensor 3D Object Detection,"Xie, Yichen*; Xu, Chenfeng; Rakotosaona, Marie-Julie; Rim, Patrick; Tombari, Federico; Keutzer, Kurt; TOMIZUKA, Masayoshi; Zhan, Wei",poster,2304.14340,https://arxiv.org/abs/2304.14340,https://github.com/yichen928/SparseFusion,https://huggingface.co/papers/2304.14340,,,,8,0 +SparseFusion: Fusing Multi-Modal Sparse Representations for Multi-Sensor 3D Object Detection,"Xie, Yichen*; Xu, Chenfeng; Rakotosaona, Marie-Julie; Rim, Patrick; Tombari, Federico; Keutzer, Kurt; TOMIZUKA, Masayoshi; Zhan, Wei",poster,2304.1434,https://arxiv.org/abs/2304.14340,https://github.com/yichen928/SparseFusion,https://huggingface.co/papers/2304.14340,,,,8,0 Strata-NeRF : Neural Radiance fields for Stratified Scenes,"Dhiman, Ankit*; R, Srinath; Rangwani, Harsh; Parihar, Rishubh; Boregowda, Lokesh; Sridhar, Srinath; RADHAKRISHNAN, Venkatesh Babu",poster,2308.10337,https://arxiv.org/abs/2308.10337,,https://huggingface.co/papers/2308.10337,,,,7,0 -"CRN: Camera Radar Net for Accurate, Robust, Efficient 3D Perception","Kim, Youngseok; Shin, Juyeb; Kim, Sanmin; Lee, In-Jae; Choi, Jun Won; Kum, Dongsuk*",poster,2304.00670,https://arxiv.org/abs/2304.00670,,https://huggingface.co/papers/2304.00670,,,,5,0 +"CRN: Camera Radar Net for Accurate, Robust, Efficient 3D Perception","Kim, Youngseok; Shin, Juyeb; Kim, Sanmin; Lee, In-Jae; Choi, Jun Won; Kum, Dongsuk*",poster,2304.0067,https://arxiv.org/abs/2304.00670,,https://huggingface.co/papers/2304.00670,,,,5,0 LightGlue: Local Feature Matching at Light Speed,"Lindenberger, Philipp*; Sarlin, Paul-Edouard; Pollefeys, Marc",poster,2306.13643,https://arxiv.org/abs/2306.13643,https://github.com/cvg/LightGlue,https://huggingface.co/papers/2306.13643,,,,3,0 ExBluRF: Efficient Radiance Fields for Extreme Motion Blurred Images,"Lee, Dongwoo; Oh, Jeongtaek; Rim, Jaesung; Cho, Sunghyun; Lee, Kyoung Mu*",poster,,,,,,,,, Generalized Differentiable RANSAC,"Wei, Tong*; Patel, Yash; Shekhovtsov, Alexander; Matas, Jiri; Barath, Daniel",poster,2212.13185,https://arxiv.org/abs/2212.13185,https://github.com/weitong8591/differentiable_ransac,https://huggingface.co/papers/2212.13185,,,,5,0 -Constraining Depth Map Geometry for Multi-View Stereo: A Dual-Depth Approach with Saddle-shaped Depth Cells,"Ye, Xinyi; Zhao, Weiyue; Liu, Tianqi; Huang, Zihao; Cao, Zhiguo*; Li, Xin",poster,2307.09160,https://arxiv.org/abs/2307.09160,,https://huggingface.co/papers/2307.09160,,,,6,0 +Constraining Depth Map Geometry for Multi-View Stereo: A Dual-Depth Approach with Saddle-shaped Depth Cells,"Ye, Xinyi; Zhao, Weiyue; Liu, Tianqi; Huang, Zihao; Cao, Zhiguo*; Li, Xin",poster,2307.0916,https://arxiv.org/abs/2307.09160,,https://huggingface.co/papers/2307.09160,,,,6,0 Total-Recon: Deformable Scene Reconstruction for Motion-based View Synthesis,"Song, Chonghyuk*; Yang, Gengshan; Deng, Kangle; Zhu, Jun-Yan; Ramanan, Deva",poster,,,,,,,,, Seal-3D: Interactive Pixel-Level Editing for Neural Radiance Fields,"Wang, Xiangyu; Zhu, Jingsen; Ran, Yunlong; Zhong, Zhihua; Huo, Yuchi; Chen, Jiming; Ye, Qi*",poster,,,,,,,,, PointMBF: A Multi-scale Bidirectional Fusion Network for Unsupervised RGB-D Point Cloud Registration,"Yuan, Mingzhi*; Fu, Kexue; Li, Zhihao; Meng, Yucong; Wang, Manning",poster,,,,,,,,, @@ -1645,7 +1645,7 @@ TransIFF: An Instance-Level Feature Fusion Framework for Vehicle-Infrastructure Density-invariant Features for Distant Point Cloud Registration,"Liu, Quan*; Zhu, Hongzi; Zhou, Yunsong; Li, Hongyang; Chang, Shan; Guo, Minyi",poster,2307.09788,https://arxiv.org/abs/2307.09788,https://github.com/liuQuan98/GCL,https://huggingface.co/papers/2307.09788,,,,6,0 UMIFormer: Mining the Correlations between Similar Tokens for Multi-View 3D Reconstruction,"Zhu, Zhenwei; Yang, Liying; li, ning; Jiang, Chaohao; Liang, Yanyan*",poster,2302.13987,https://arxiv.org/abs/2302.13987,https://github.com/GaryZhu1996/UMIFormer,https://huggingface.co/papers/2302.13987,,,,5,0 Neural LiDAR Fields for Novel View Synthesis,"Huang, Shengyu*; Gojcic, Zan; Wang, Zian; Williams, Francis; Kasten, Yoni; Fidler, Sanja; Schindler, Konrad; Litany, Or",poster,2305.01643,https://arxiv.org/abs/2305.01643,,https://huggingface.co/papers/2305.01643,,,,8,0 -Learning Unified Decompositional and Compositional NeRF for Editable Novel View Synthesis,"WANG, Yuxin*; Wu, Wayne; Xu, Dan",poster,2308.02840,https://arxiv.org/abs/2308.02840,,https://huggingface.co/papers/2308.02840,,,,3,0 +Learning Unified Decompositional and Compositional NeRF for Editable Novel View Synthesis,"WANG, Yuxin*; Wu, Wayne; Xu, Dan",poster,2308.0284,https://arxiv.org/abs/2308.02840,,https://huggingface.co/papers/2308.02840,,,,3,0 Long-Range Grouping Transformer for Multi-View 3D Reconstruction,"Yang, Liying; Zhu, Zhenwei; Lin, Xuxin; Nong, Jian; Liang, Yanyan*",poster,2308.08724,https://arxiv.org/abs/2308.08724,https://github.com/LiyingCV/Long-Range-Grouping-Transformer,https://huggingface.co/papers/2308.08724,,,,5,0 Cross Modal Transformer: Towards Fast and Robust 3D Object Detection,"Yan, Junjie; Liu, Yingfei; Sun, Jianjian; Jia, Fan; Li, Shuailin; Wang, Tiancai; Zhang, Xiangyu*",poster,2301.01283,https://arxiv.org/abs/2301.01283,https://github.com/junjie18/CMT,https://huggingface.co/papers/2301.01283,,,,7,0 KECOR: Kernel Coding Rate Maximization for Active 3D Object Detection,"Luo, Yadan*; Chen, Zhuoxiao; Fang, Zhen; Zhang, Zheng; Huang, Zi Helen; Baktashmotlagh, Mahsa",poster,2307.07942,https://arxiv.org/abs/2307.07942,,https://huggingface.co/papers/2307.07942,,,,6,0 @@ -1661,14 +1661,14 @@ Optimizing the Placement of Roadside LiDARs for Autonomous Driving,"Jiang, Wenta ActorsNeRF: Animatable Few-shot Human Rendering with Generalizable NeRFs,"Mu, Jiteng*; Sang, Shen; Vasconcelos, Nuno; Wang, Xiaolong",poster,2304.14401,https://arxiv.org/abs/2304.14401,,https://huggingface.co/papers/2304.14401,,,,4,0 NeRFrac: Neural Radiance Fields through Refractive Surface,"Zhan, Yifan; Nobuhara, Shohei; Nishino, Ko; Zheng, Yinqiang*",poster,,,,,,,,, CPCM: Contextual Point Cloud Modeling for Weakly-supervised Point Cloud Semantic Segmentation,"Liu, Lizhao; Zhuang, Zhuangwei; Huang, Shangxin; Xiao, Xunlong; Xiang, Tianhang; Chen, Cen; Wang, Jingdong; Tan, Mingkui*",poster,2307.10316,https://arxiv.org/abs/2307.10316,,https://huggingface.co/papers/2307.10316,,,,8,0 -FineRecon: Depth-aware Feed-forward Network for Detailed 3D Reconstruction,"Stier, Noah*; Ranjan, Anurag; Colburn, Alex; yan, yajie; Yang, Liang; Ma, Fangchang; Angles, Baptiste",poster,2304.01480,https://arxiv.org/abs/2304.01480,,https://huggingface.co/papers/2304.01480,,,,7,0 +FineRecon: Depth-aware Feed-forward Network for Detailed 3D Reconstruction,"Stier, Noah*; Ranjan, Anurag; Colburn, Alex; yan, yajie; Yang, Liang; Ma, Fangchang; Angles, Baptiste",poster,2304.0148,https://arxiv.org/abs/2304.01480,,https://huggingface.co/papers/2304.01480,,,,7,0 Point-SLAM: Dense Neural Point Cloud-based SLAM,"Sandström, Erik; Li, Yue; Van Gool, Luc; Oswald, Martin R.*",poster,2304.04278,https://arxiv.org/abs/2304.04278,https://github.com/tfy14esa/Point-SLAM,https://huggingface.co/papers/2304.04278,,,,4,0 You Never Get a Second Chance To Make a Good First Impression: Seeding Active Learning for 3D Semantic Segmentation,"Samet, Nermin*; Siméoni, Oriane; Puy, Gilles; Ponimatkin, Georgy; Marlet, Renaud; Lepetit, Vincent",poster,2304.11762,https://arxiv.org/abs/2304.11762,https://github.com/nerminsamet/seedal,https://huggingface.co/papers/2304.11762,,,,6,0 Tetra-NeRF: Representing Neural Radiance Fields Using Tetrahedra,"Kulhanek, Jonas*; Sattler, Torsten",poster,,,,,,,,, Active Stereo Without Pattern Projector,"Bartolomei, Luca*; Poggi, Matteo; Tosi, Fabio; Conti, Andrea; Mattoccia, Stefano",poster,,,,,,,,, HOSNeRF: Dynamic Human-Object-Scene Neural Radiance Fields from a Single Video,"Liu, Jia-Wei*; Cao, Yan-Pei; Yang, Tianyuan; Xu, Zhongcong; Keppo, Jussi; Shan, Ying; Qie, Xiaohu; Shou, Mike Zheng",poster,2304.12281,https://arxiv.org/abs/2304.12281,,https://huggingface.co/papers/2304.12281,,,,8,0 PlankAssembly: Robust 3D Reconstruction from Three Orthographic Views with Learnt Shape Programs,"Hu, Wentao; Zheng, Jia*; Zhang, Zixin; Yuan, Xiaojun; Yin, Jian; Zhou, Zihan",poster,2308.05744,https://arxiv.org/abs/2308.05744,,https://huggingface.co/papers/2308.05744,,,,6,1 -Efficient View Synthesis with Neural Radiance Distribution Field,"Wu, Yushuang*; Li, Xiao; Wang, Jinglu; Han, Xiaoguang; Cui, Shuguang; Lu, Yan",poster,2308.11130,https://arxiv.org/abs/2308.11130,,https://huggingface.co/papers/2308.11130,,,,6,0 +Efficient View Synthesis with Neural Radiance Distribution Field,"Wu, Yushuang*; Li, Xiao; Wang, Jinglu; Han, Xiaoguang; Cui, Shuguang; Lu, Yan",poster,2308.1113,https://arxiv.org/abs/2308.11130,,https://huggingface.co/papers/2308.11130,,,,6,0 Query Refinement Transformer for 3D Instance Segmentation,"lu, jiahao*; Deng, Jiacheng; Wang, Chuxin; He, Jianfeng; Zhang, Tianzhu",poster,,,,,,,,, TrajectoryFormer: 3D Object Tracking Transformer with Predictive Trajectory Hypotheses,"Chen, Xuesong*; Shi, Shaoshuai; Zhang, Chao; Zhu, Benjin; Wang, Qiang; Cheung, Ka Chun; See, Simon; Li, Hongsheng",poster,2306.05888,https://arxiv.org/abs/2306.05888,https://github.com/poodarchu/EFG,https://huggingface.co/papers/2306.05888,,,,8,0 NerfAcc: Efficient Sampling Accelerates NeRFs,"Li, Ruilong*; Gao, Hang; Tancik, Matthew; Kanazawa, Angjoo",poster,2305.04966,https://arxiv.org/abs/2305.04966,,https://huggingface.co/papers/2305.04966,,,,4,2 @@ -1723,10 +1723,10 @@ CAFA: Class-aware Feature Alignment for Test-time Adaptaion,"Jung, Sanghun*; Lee Image-free Classifier Injection for Zero-Shot Classification,"Christensen, Anders*; Mancini, Massimiliano; Koepke, A. Sophia; Winther, Ole; Akata, Zeynep",poster,2308.10599,https://arxiv.org/abs/2308.10599,https://github.com/ExplainableML/ImageFreeZSL,https://huggingface.co/papers/2308.10599,,,,5,0 CBA: Improving Online Continual Learning via Continual Bias Adaptor,"Wang, Quanziang*; Wang, Renzhen; Wu, Yichen; Jia, Xixi; Meng, Deyu",poster,2308.06925,https://arxiv.org/abs/2308.06925,,https://huggingface.co/papers/2308.06925,,,,5,0 AdaptGuard: Defending Against Universal Attacks for Model Adaptation,"Sheng, Lijun*; Liang, Jian; He, Ran; Wang, Zilei; Tan, Tieniu",poster,2303.10594,https://arxiv.org/abs/2303.10594,,https://huggingface.co/papers/2303.10594,,,,5,0 -Masked Autoencoders are Efficient Class Incremental Learners,"Zhai, Jiang-Tian; Liu, Xialei*; Bagdanov, Andy; Li, Ke; Cheng, Ming-Ming",poster,2308.12510,https://arxiv.org/abs/2308.12510,https://github.com/scok30/MAE-CIL,https://huggingface.co/papers/2308.12510,,,,5,0 +Masked Autoencoders are Efficient Class Incremental Learners,"Zhai, Jiang-Tian; Liu, Xialei*; Bagdanov, Andy; Li, Ke; Cheng, Ming-Ming",poster,2308.1251,https://arxiv.org/abs/2308.12510,https://github.com/scok30/MAE-CIL,https://huggingface.co/papers/2308.12510,,,,5,0 DomainDrop: Suppressing Domain-Sensitive Channels for Domain Generalization,"Guo, Jintao*; Qi, Lei; Shi, Yinghuan",poster,2308.10285,https://arxiv.org/abs/2308.10285,https://github.com/lingeringlight/DomainDrop,https://huggingface.co/papers/2308.10285,,,,3,0 Preventing Zero-Shot Transfer Degradation in Continual Learning of Vision-Language Models,"Zheng, Zangwei*; MA, Mingyuan; Wang, Kai; Qin, Ziheng; Yue, Xiangyu; You, Yang",poster,2303.06628,https://arxiv.org/abs/2303.06628,https://github.com/Thunderbeee/ZSCL,https://huggingface.co/papers/2303.06628,,,,6,0 -Incremental Generalized Category Discovery,"Zhao, Bingchen*; Mac Aodha, Oisin",poster,2304.14310,https://arxiv.org/abs/2304.14310,,https://huggingface.co/papers/2304.14310,,,,2,0 +Incremental Generalized Category Discovery,"Zhao, Bingchen*; Mac Aodha, Oisin",poster,2304.1431,https://arxiv.org/abs/2304.14310,,https://huggingface.co/papers/2304.14310,,,,2,0 SLCA: Slow Learner with Classifier Alignment for Continual Learning on a Pre-trained Model,"Zhang, Gengwei*; Wang, Liyuan; Kang, Guoliang; Chen, Ling; Wei, Yunchao",poster,2303.05118,https://arxiv.org/abs/2303.05118,https://github.com/GengDavid/SLCA,https://huggingface.co/papers/2303.05118,,,,5,0 Efficient Model Personalization in Federated Learning via Client-Specific Prompt Generation,"Yang, Fu-En*; Wang, Chien-Yi; Wang, Yu-Chiang Frank",poster,2308.15367,https://arxiv.org/abs/2308.15367,,https://huggingface.co/papers/2308.15367,,,,3,0 iDAG: Invariant DAG Searching for Domain Generalization,"Huang, Zenan*; Wang, Haobo; Zhao, Junbo; Zheng, Nenggan",poster,,,,,,,,, @@ -1794,7 +1794,7 @@ Simulating Fluids in Real-World Still Images,"Fan, Siming; Piao, Jingtan; Qian, FateZero: Fusing Attentions for Zero-shot Text-based Video Editing,"QI, Chenyang; Cun, Xiaodong; Zhang, Yong; Lei, Chenyang; Wang, Xintao; Shan, Ying; Chen, Qifeng*",oral,2303.09535,https://arxiv.org/abs/2303.09535,https://github.com/ChenyangQiQi/FateZero,https://huggingface.co/papers/2303.09535,https://huggingface.co/spaces/chenyangqi/FateZero,,,7,1 ELITE: Encoding Visual Concepts into Textual Embeddings for Customized Text-to-Image Generation,"Wei, Yuxiang; Yabo, Zhang; ji, zhilong; Bai, Jinfeng; Zhang, Lei; Zuo, Wangmeng*",oral,2302.13848,https://arxiv.org/abs/2302.13848,https://github.com/csyxwei/ELITE,https://huggingface.co/papers/2302.13848,https://huggingface.co/spaces/ELITE-library/ELITE,https://huggingface.co/ELITE-library/ELITE,,6,0 Get-a-Video-for-Free: Text-to-Image Diffusion Models are Zero-Shot Video Generators,"Khachatryan, Levon; Movsisyan, Andranik; Tadevosyan, Vahram; Henschel, Roberto*; Wang, Zhangyang; Navasardyan, Shant; Shi, Humphrey",oral,,,,,,,,, -Chupa: Carving 3D Clothed Humans from Skinned Shape Priors using 2D Diffusion Probabilistic Models,"Kim, Byungjun*; Kwon, Patrick; Lee, Kwangho; Lee, Myunggi; Han, Sookwan; Kim, Daesik; Joo, Hanbyul",oral,2305.11870,https://arxiv.org/abs/2305.11870,,https://huggingface.co/papers/2305.11870,,,,7,2 +Chupa: Carving 3D Clothed Humans from Skinned Shape Priors using 2D Diffusion Probabilistic Models,"Kim, Byungjun*; Kwon, Patrick; Lee, Kwangho; Lee, Myunggi; Han, Sookwan; Kim, Daesik; Joo, Hanbyul",oral,2305.1187,https://arxiv.org/abs/2305.11870,,https://huggingface.co/papers/2305.11870,,,,7,2 DiffPose: Multi-hypothesis Human Pose Estimation using Diffusion Models,"Holmquist, Karl*; Wandt, Bastian",oral,2211.16487,https://arxiv.org/abs/2211.16487,,https://huggingface.co/papers/2211.16487,,,,2,0 HumanSD: A Native Skeleton-Guided Diffusion Model for Human Image Generation,"Ju, Xuan*; Zeng, Ailing; ZHAO, Chenchen; Wang, Jianan; Zhang, Lei; Xu, Qiang",oral,2304.04269,https://arxiv.org/abs/2304.04269,,https://huggingface.co/papers/2304.04269,,,,6,0 Role-aware Interaction Generation from Textual Description,"Tanaka, Mikihiro*; Fujiwara, Kent",oral,,,,,,,,, @@ -1805,7 +1805,7 @@ DNA-Rendering : A Diverse Neural Actor Repository for High-Fidelity Human-centri Robo3D: Towards Robust and Reliable 3D Perception against Corruptions,"Kong, Lingdong*; Liu, Youquan; Li, Xin; Chen, Runnan; Zhang, Wenwei; Ren, Jiawei; Pan, Liang; Chen, Kai; Liu, Ziwei",poster,2303.17597,https://arxiv.org/abs/2303.17597,,https://huggingface.co/papers/2303.17597,,,,9,1 Efficient Discovery and Effective Evaluation of Visual Similarities: A Benchmark and Beyond,"Barkan, Oren*; Reiss, Tal; Weill, Jonathan; Kats, Ori; Hirsch, Roy; Malkiel, Itzik; Koenigstein, Noam ",poster,,,,,,,,, DetermiNet: A Large-Scale Diagnostic Dataset for Complex Visually-Grounded Referencing using Determiners,"Lee, Clarence*; Kumar, M Ganesh; Tan, Cheston",poster,,,,,,,,, -Beyond Object Recognition: A New Benchmark towards Object Concept Learning,"Li, Yong-Lu*; Xu, Yue; Xu, Xinyu; Mao, Xiaohan; Yao, Yuan; Liu, Siqi; Lu, Cewu",poster,2212.02710,https://arxiv.org/abs/2212.02710,,https://huggingface.co/papers/2212.02710,,,,7,0 +Beyond Object Recognition: A New Benchmark towards Object Concept Learning,"Li, Yong-Lu*; Xu, Yue; Xu, Xinyu; Mao, Xiaohan; Yao, Yuan; Liu, Siqi; Lu, Cewu",poster,2212.0271,https://arxiv.org/abs/2212.02710,,https://huggingface.co/papers/2212.02710,,,,7,0 "HRS-Bench: Holistic, Reliable and Scalable Benchmark for Text-to-Image Models","abdelrahman, eslam mohamed*; Sun, Pengzhan; shen, xiaoqian; Khan, Faizan Farooq; Li, Li Erran; Elhoseiny, Mohamed",poster,,,,,,,,, SegRCDB: Semantic Segmentation via Formula-Driven Supervised Learning,"Shinoda, Risa*; Hayamizu, Ryo; Nakashima, Kodai; Inoue, Nakamasa; Yokota, Rio; Kataoka, Hirokatsu",poster,,,,,,,,, LoTE-Animal: A Long Time-span Dataset for Endangered Animal Behavior Understanding,"Liu, Dan*; Hou, Jin; Huang, Shaoli; Liu, Jing; He, Yuxin; zheng, bochuan; Ning, Jifeng; Zhang, Jingdong",poster,,,,,,,,, @@ -1816,7 +1816,7 @@ EgoObjects: A Large-Scale Egocentric Dataset for Fine-Grained Object Understandi Contrastive Automatic Model Evaluation,"Peng, Ru; Duan, Qiuyang; Wang, Haobo; Ma, Jiachen; Jiang, Yanbo; Tu, Yongjun; Jiang, Xiu; Zhao, Junbo*",poster,,,,,,,,, Aria Digital Twin: A New Benchmark Dataset for Egocentric 3D Machine Perception,"Pan, Xiaqing*; Charron, Nicholas; Yang, Yongqian; Peters, Scott C; Whelan, Thomas; Kong, Chen; Parkhi, Omkar M; Newcombe, Richard; Ren, Yuheng",poster,2306.06362,https://arxiv.org/abs/2306.06362,,https://huggingface.co/papers/2306.06362,,,,9,0 Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives,"Wu, Haoning*; Zhang, Erli; Liao, Liang; Chen, Chaofeng; Hou, Jingwen; Wang, Annan; Sun, Wenxiu; Yan, Qiong; Lin, Weisi",poster,2211.04894,https://arxiv.org/abs/2211.04894,https://github.com/VQAssessment/DOVER,https://huggingface.co/papers/2211.04894,,,,9,0 -Going Beyond Nouns With Vision & Language Models Using Synthetic Data,"Cascante-Bonilla, Paola*; Shehada, Khaled; Smith, James S; Doveh, Sivan; Kim, Donghyun; Panda, Rameswar; Varol, Gul; Oliva, Aude; Ordonez, Vicente; Feris, Rogerio; Karlinsky, Leonid",poster,2303.17590,https://arxiv.org/abs/2303.17590,,https://huggingface.co/papers/2303.17590,,,,11,0 +Going Beyond Nouns With Vision & Language Models Using Synthetic Data,"Cascante-Bonilla, Paola*; Shehada, Khaled; Smith, James S; Doveh, Sivan; Kim, Donghyun; Panda, Rameswar; Varol, Gul; Oliva, Aude; Ordonez, Vicente; Feris, Rogerio; Karlinsky, Leonid",poster,2303.1759,https://arxiv.org/abs/2303.17590,,https://huggingface.co/papers/2303.17590,,,,11,0 H3WB: Human3.6M 3D WholeBody Dataset and Benchmark,"Zhu, Yue*; Samet, Nermin; Picard, David",poster,2211.15692,https://arxiv.org/abs/2211.15692,https://github.com/wholebody3d/wholebody3d,https://huggingface.co/papers/2211.15692,,,,3,1 ZOD: A large-scale and diverse multimodal dataset for autonomous driving,"Alibeigi, Mina*; Ljungbergh, William; Tonderski, Adam; Hess, Georg; Lilja, Adam; Lindström, Carl; Motorniuk, Daria; Fu, Junsheng; Widahl, Jenny; Petersson, Christoffer",poster,,,,,,,,, CAD-Estate: Large-scale CAD Model Annotation in RGB Videos,"Maninis, Kevis-Kokitsi*; Popov, Stefan; Niessner, Matthias; Ferrari, Vittorio",poster,,,,,,,,, @@ -1834,7 +1834,7 @@ Joint Metrics Matter: A Better Standard for Trajectory Forecasting,"Weng, Erica* LPFF: A Portrait Dataset for Face Generators Across Large Poses,"Wu, Yiqian; Zhang, Jing; Fu, Hongbo ; Jin, Xiaogang*",poster,2303.14407,https://arxiv.org/abs/2303.14407,,https://huggingface.co/papers/2303.14407,,,,4,0 Replay: Multi-modal Multi-view Acted Videos for Casual Holography,"Shapovalov, Roman*; Kleiman, Yanir; Rocco, Ignacio; Novotny, David; Vedaldi, Andrea; Graham, Ben; Kokkinos, Filippos; Chen, Changan; Neverova, Natalia",poster,2307.12067,https://arxiv.org/abs/2307.12067,,https://huggingface.co/papers/2307.12067,,,,9,0 Human-centric Scene Understanding in 3D Large-scale Scenarios,"Xu, Yiteng; Cong, Peishan; Yao, Yichen; Chen, Runnan; HOU, Yuenan; Zhu, Xinge; He, Xuming; Yu, Jingyi; Ma, Yuexin*",poster,,,,,,,,, -Pre-training Vision Transformers with Very Limited Synthesized Images,"Nakamura, Ryo*; Kataoka, Hirokatsu; Takashima, Sora; MARTINEZ-NORIEGA, Edgar Josafat; Yokota, Rio; Inoue, Nakamasa",poster,2307.14710,https://arxiv.org/abs/2307.14710,,https://huggingface.co/papers/2307.14710,,,,6,0 +Pre-training Vision Transformers with Very Limited Synthesized Images,"Nakamura, Ryo*; Kataoka, Hirokatsu; Takashima, Sora; MARTINEZ-NORIEGA, Edgar Josafat; Yokota, Rio; Inoue, Nakamasa",poster,2307.1471,https://arxiv.org/abs/2307.14710,,https://huggingface.co/papers/2307.14710,,,,6,0 FACET: Fairness in Computer Vision Evaluation Benchmark,"Gustafson, Laura *; Rolland, Chloe; Ravi, Nikhila; Duval, Quentin; Adcock, Aaron; Fu, Cheng-Yang; Hall, Melissa; Ross, Candace",poster,,,,,,,,, EmoSet: A Large-scale Visual Emotion Dataset with Rich Attributes,"Yang, Jingyuan; Huang, Qirui; Ding, Tingting; Lischinski, Dani; Cohen-Or, Danny; Huang, Hui*",poster,2307.07961,https://arxiv.org/abs/2307.07961,,https://huggingface.co/papers/2307.07961,,,,6,0 RenderIH: A large-scale synthetic dataset for 3D interacting hand pose estimation,"Li, Lijun*; Tian, Linrui; Zhang, Xindi; Wang, Qi; Zhang, Bang; Liefeng, Bo; Liu, Mengyuan; Chen, Chen",poster,,,,,,,,, @@ -1852,13 +1852,13 @@ BEAR: A BEnchmark on video Action Recognition,"Deng, Andong*; Yang, Taojiannan; SQAD: Automatic Smartphone Camera Quality Assessment and Benchmarking,"Fang, Zilin; Ignatov, Andrey; Zamfir, Eduard; Timofte, Radu*",poster,,,,,,,,, Revisiting Scene Text Recognition: A Data Perspective,"Jiang, Qing*; Wang, Jiapeng; Peng, Dezhi; Liu, Chongyu; Jin, Lianwen ",poster,2307.08723,https://arxiv.org/abs/2307.08723,,https://huggingface.co/papers/2307.08723,,,,5,0 Will Large-scale Generative Models Corrupt Future Datasets?,"Hataya, Ryuichiro*; Bao, Han; Arai, Hiromi",poster,2211.08095,https://arxiv.org/abs/2211.08095,https://github.com/moskomule/dataset-contamination,https://huggingface.co/papers/2211.08095,,,,3,0 -360VOT: A New Benchmark Dataset for Omnidirectional Visual Object Tracking,"Huang, Huajian*; Xu, Yinzhe; Chen, Yingshu; Yeung, Sai-Kit",poster,2307.14630,https://arxiv.org/abs/2307.14630,,https://huggingface.co/papers/2307.14630,,,,4,0 +360VOT: A New Benchmark Dataset for Omnidirectional Visual Object Tracking,"Huang, Huajian*; Xu, Yinzhe; Chen, Yingshu; Yeung, Sai-Kit",poster,2307.1463,https://arxiv.org/abs/2307.14630,,https://huggingface.co/papers/2307.14630,,,,4,0 DeePoint: Pointing Recognition and Direction Estimation From A Fixed View,"Nakamura, Shu; Kawanishi, Yasutomo; Nobuhara, Shohei*; Nishino, Ko",poster,2304.06977,https://arxiv.org/abs/2304.06977,,https://huggingface.co/papers/2304.06977,,,,4,0 Contactless Pulse Estimation Leveraging Pseudo Labels and Self-Supervision,"Li, Zhihua*; Yin, Lijun",poster,,,,,,,,, Most Important Person-guided Dual-branch Cross-Patch Attention for Group Affect Recognition,"Xie, Hongxia*; Lee, Ming-Xian; Chen, Tzu Jui; Chen, Hung-Jen; Liu, Hou-I; Shuai, Hong-Han; Cheng, Wen-Huang",poster,,,,,,,,, Object-centric Contact Field for Grasp Generation,"Liu, Shaowei*; Zhou, Yang; Yang, Jimei; Gupta, Saurabh; Wang, Shenlong",poster,,,,,,,,, Imitator: Personalized Speech-driven 3D Facial Animation,"Thambiraja, Balamurugan*; Habibie, Ikhsanul; Aliakbarian, Sadegh; Cosker, Darren P; Theobalt, Christian; Thies, Justus",poster,2301.00023,https://arxiv.org/abs/2301.00023,,https://huggingface.co/papers/2301.00023,,,,6,0 -DVGaze: Dual-view Gaze Estimation,"Cheng, Yihua; Lu, Feng*",poster,2308.10310,https://arxiv.org/abs/2308.10310,https://github.com/yihuacheng/DVGaze,https://huggingface.co/papers/2308.10310,,,,2,0 +DVGaze: Dual-view Gaze Estimation,"Cheng, Yihua; Lu, Feng*",poster,2308.1031,https://arxiv.org/abs/2308.10310,https://github.com/yihuacheng/DVGaze,https://huggingface.co/papers/2308.10310,,,,2,0 TransFace: Calibrating Transformer Training for Face Recognition from a Data-Centric Perspective,"Dan, Jun*; Liu, Yang; Xie, Haoyu; Deng, Jiankang; xie, haoran; Xie, Xuansong; Sun, Baigui",poster,2308.10133,https://arxiv.org/abs/2308.10133,https://github.com/DanJun6737/TransFace,https://huggingface.co/papers/2308.10133,,,,7,0 Towards Unsupervised Domain Generalization for Face Anti-Spoofing,"Liu, Yuchen*; Chen, Yabo; Gou, Mengran; Huang, Chun-Ting; Wang, Yaoming; Dai, Wenrui; Xiong, Hongkai",poster,,,,,,,,, Reinforced Disentanglement for Face Swapping without Skip Connection,"ren, xiaohang*; Chen, Xingyu; Yao, Pengfei; Shum, Heung-Yeung; Wang, Baoyuan",poster,2307.07928,https://arxiv.org/abs/2307.07928,,https://huggingface.co/papers/2307.07928,,,,5,0 @@ -1885,7 +1885,7 @@ Contrastive Pseudo Learning for Open-world Deepfake Attribution,"Sun, Zhimin*; C Continual Learning for Personalized Co-speech Gesture Generation,"Ahuja, Chaitanya*; Joshi, Pratik; Ishii, Ryo; Morency, Louis-Philippe",poster,,,,,,,,, HandR2N2: Iterative 3D Hand Pose Estimation Using a Residual Recurrent Neural Network,"CHENG, WENCAN; Ko, Jong Hwan*",poster,,,,,,,,, SPACE: Speech-driven Portrait Animation with Controllable Expression,"Gururani, Siddharth*; Mallya, Arun; Wang, Ting-Chun; Valle, Rafael; Liu, Ming-Yu",poster,2211.09809,https://arxiv.org/abs/2211.09809,,https://huggingface.co/papers/2211.09809,,,,5,0 -How to Boost Face Recognition with StyleGAN?,"Sevastopolskiy, Artem*; Malkov, Yury A.; Durasov, Nikita; Verdoliva, Luisa; Niessner, Matthias",poster,2210.10090,https://arxiv.org/abs/2210.10090,https://github.com/seva100/stylegan-for-facerec,https://huggingface.co/papers/2210.10090,,,,5,0 +How to Boost Face Recognition with StyleGAN?,"Sevastopolskiy, Artem*; Malkov, Yury A.; Durasov, Nikita; Verdoliva, Luisa; Niessner, Matthias",poster,2210.1009,https://arxiv.org/abs/2210.10090,https://github.com/seva100/stylegan-for-facerec,https://huggingface.co/papers/2210.10090,,,,5,0 ChildPlay: A New Benchmark for Understanding Children’s Gaze Behaviour,"Tafasca, Samy; Gupta, Anshul*; ODOBEZ, Jean-Marc",poster,,,,,,,,, Robust One-Shot Face Video Re-enactment using Hybrid Latent Spaces of StyleGAN2,"Oorloff, Trevine S J*; Yacoob, Yaser",poster,,,,,,,,, Data-Free Class-Incremental Hand Gesture Recognition,"Aich, Shubhra*; Ruiz-Santaquiteria, Jesus; Garg, Prachi; Lu, Zhenyu; K J, Joseph; Fernandez Garcia, Alvaro; Kin, Kenrick; Wan, Chengde; N Balasubramanian, Vineeth; Camgoz, Necati Cihan; Ma, Shugao; de la Torre, Fernando",poster,,,,,,,,, @@ -1894,7 +1894,7 @@ Knowledge-Spreader: Learning Facial Action Dynamics from Single Label Clips via Face Clustering via Graph Convolutional Networks with Confidence Edges,"Wu, Yang; Ge, Zhiwei; Luo, Yuhao*; Liu, Lin; Xu, Sulong",poster,,,,,,,,, StyleGANEX: StyleGAN-Based Manipulation Beyond Cropped Aligned Faces ,"Yang, Shuai*; Jiang, Liming; Liu, Ziwei; Loy, Chen Change",poster,,,,,,,,, SeeABLE: Soft Discrepancies and Bounded Contrastive Learning for Exposing Deepfakes,"Larue, nicolas*; Vu, Ngoc-Son; Struc, Vitomir; Peer, Peter; Christophides, Vassilis",poster,2211.11296,https://arxiv.org/abs/2211.11296,,https://huggingface.co/papers/2211.11296,,,,5,0 -Adaptive Nonlinear Latent Transformation for Conditional Face Editing,"Huang, Zhizhong*; Ma, Siteng; Zhang, Junping; Shan, Hongming",poster,2307.07790,https://arxiv.org/abs/2307.07790,https://github.com/Hzzone/AdaTrans,https://huggingface.co/papers/2307.07790,,,,4,0 +Adaptive Nonlinear Latent Transformation for Conditional Face Editing,"Huang, Zhizhong*; Ma, Siteng; Zhang, Junping; Shan, Hongming",poster,2307.0779,https://arxiv.org/abs/2307.07790,https://github.com/Hzzone/AdaTrans,https://huggingface.co/papers/2307.07790,,,,4,0 Semi-supervised Speech-driven 3D Facial Animation via Cross-modal Encoding,"Yang, Peiji; Wei, Huawei*; Zhong, Yicheng; Wang, Zhisheng",poster,,,,,,,,, ICD-Face: Intra-class Compactness Distillation for Face Recognition,"yu, zhipeng; Liu, Jiaheng*; Qin, Haoyu; Wu, Yichao; Hu, Kun; Tian, Jiayi; Liang, Ding",poster,,,,,,,,, C$^2$ST: Cross-modal Contextualized Sequence Transduction for Continuous Sign Language Recognition,"Zhang, Huaiwen*; guo, zihang; Yang, Yang; Liu, Xin; Hu, De",poster,,,,,,,,, @@ -1914,7 +1914,7 @@ Learning to Distill Global Representation for Sparse-View CT,"Li, ZiLong; Ma, Ch Preserving Tumor Volumes for Unsupervised Meical Image Registration,"Dong, Qihua*; Du, Hao; Song, Ying; Xu, Yan; Liao, Jing",poster,,,,,,,,, uSplit: image decomposition for fluorescence microscopy,"Ashesh, Ashesh*; Krull, Alexander; di sante, moises; Pasqualini, Francesco; Jug, Florian",poster,,,,,,,,, Rethinking Multi-Contrast MRI Super-Resolution: Rectangle-Window Cross-Attention Transformer and Arbitrary-Scale Upsampling,"Li, Guangyuan*; Zhao, Lei; Sun, Jiakai; Lan, Zehua; Zhang, Zhanjie; Chen, Jiafu; Lin, Zhijie; Lin, Huaizhong; Xing, Wei",poster,,,,,,,,, -Multimodal Optimal Transport-based Co-Attention Transformer with Global Structure Consistency for Survival Prediction,"XU, Yingxue*; Chen, Hao",poster,2306.08330,https://arxiv.org/abs/2306.08330,,https://huggingface.co/papers/2306.08330,,,,2,0 +Multimodal Optimal Transport-based Co-Attention Transformer with Global Structure Consistency for Survival Prediction,"XU, Yingxue*; Chen, Hao",poster,2306.0833,https://arxiv.org/abs/2306.08330,,https://huggingface.co/papers/2306.08330,,,,2,0 4D Myocardium Reconstruction with Decoupled Motion and Shape Model,"Yuan, Xiaohan; Liu, Cong; Wang, Yangang*",poster,2308.14083,https://arxiv.org/abs/2308.14083,,https://huggingface.co/papers/2308.14083,,,,3,0 Unsupervised Learning of Object-Centric Embeddings for Cell Instance Segmentation in Microscopy Images,"Wolf, Steffen; Lalit, Manan; McDole, Katie; Funke, Jan*",poster,,,,,,,,, LightDepth: Single-View Depth Self-Supervision from Illumination Decline,"Rodriguez-Puigvert, Javier*; Batlle, Víctor M.; Montiel, J. M. M.; Martinez-Cantin, Ruben; Fua, Pascal; Tardós, Juan D.; Civera, Javier",poster,2308.10525,https://arxiv.org/abs/2308.10525,,https://huggingface.co/papers/2308.10525,,,,7,0 @@ -1948,7 +1948,7 @@ CMDA: Cross-Modality Domain Adaptation for Nighttime Semantic Segmentation,"Xia, VQA-GNN: Fusing Multimodal Knowledge via Graph Neural Networks for Visual Question Answering,"Wang, Yanan*; Yasunaga, Michihiro; Ren, Hongyu; Wada, Shinya; Leskovec, Jure",poster,,,,,,,,, Disentangle then Parse: Night-time Semantic Segmentation with Illumination Disentanglement,"Wei, Zhixiang*; Chen, Lin; Tu, Tao; Ling, Pengyang; Chen, Huaian; Jin, Yi",poster,,,,,,,,, Visual Traffic Knowledge Graph Generation from Scene Images,"Guo, Yunfei*; yin, Fei; Li, Xiao-Hui; YAN, XUDONG; XUE, TAO; mei, shuqi; Liu, Cheng-Lin",poster,,,,,,,,, -Agglomerative Transformer for Human-Object Interaction Detection,"Tu, Danyang*; Sun, Wei; Zhai, Guangtao; Shen, Wei",poster,2308.08370,https://arxiv.org/abs/2308.08370,,https://huggingface.co/papers/2308.08370,,,,4,0 +Agglomerative Transformer for Human-Object Interaction Detection,"Tu, Danyang*; Sun, Wei; Zhai, Guangtao; Shen, Wei",poster,2308.0837,https://arxiv.org/abs/2308.08370,,https://huggingface.co/papers/2308.08370,,,,4,0 3D Neural Embedding Likelihood for Robust Probabilistic Inverse Graphics,"Zhou, Guangyao*; Gothoskar, Nishad; Wang, Lirui; Tenenbaum, Joshua; Gutfreund, Dan; Lázaro-Gredilla, Miguel; George, Dileep; Mansinghka, Vikash",poster,2302.03744,https://arxiv.org/abs/2302.03744,,https://huggingface.co/papers/2302.03744,,,,8,0 HiLo: Exploiting High Low Frequency Relations for Unbiased Panoptic Scene Graph Generation,"Zhou, Zijian*; Shi, Miaojing; Caesar, Holger",poster,2303.15994,https://arxiv.org/abs/2303.15994,https://github.com/franciszzj/HiLo,https://huggingface.co/papers/2303.15994,,,,3,1 SRLIP: Fast Scaling of Relational Language-Image Pre-training,"Yuan, Hangjie*; Zhang, Shiwei; Wang, Xiang; Albanie, Samuel; Pan, Yining; Feng, Tao; Jiang, Jianwen; Ni, Dong; Zhang, Yingya; Zhao, Deli",poster,,,,,,,,, @@ -2008,7 +2008,7 @@ Robust Referring Video Object Segmentation with Cyclic Structural Consensus,"Li, Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation,"chen, rui; Chen, Yongwei; Jiao, Ningxin; Jia, Kui*",poster,2303.13873,https://arxiv.org/abs/2303.13873,,https://huggingface.co/papers/2303.13873,,,,4,0 CTP:Towards Vision-Language Continual Pretraining via Compatible Momentum Contrast and Topology Preservation,"Zhu, hongguang*; Wei, Yunchao; Liang, Xiaodan; Zhang, Chunjie; Zhao, Yao",poster,,,,,,,,, Teaching CLIP to Count to Ten,"Paiss, Roni*; Ephrat, Ariel; Tov, Omer; Zada, Shiran; Mosseri, Inbar; Irani, Michal; Dekel, Tali",poster,2302.12066,https://arxiv.org/abs/2302.12066,,https://huggingface.co/papers/2302.12066,,,,7,0 -Narrator: Towards Natural Control of Human-Scene Interaction Generation via Relationship Reasoning,"Xuan, Haibiao; Li, Xiongzheng; Zhang, Jinsong; Zhang, Hongwen; Liu, Yebin; Li, Kun*",poster,2303.09410,https://arxiv.org/abs/2303.09410,,https://huggingface.co/papers/2303.09410,,,,6,0 +Narrator: Towards Natural Control of Human-Scene Interaction Generation via Relationship Reasoning,"Xuan, Haibiao; Li, Xiongzheng; Zhang, Jinsong; Zhang, Hongwen; Liu, Yebin; Li, Kun*",poster,2303.0941,https://arxiv.org/abs/2303.09410,,https://huggingface.co/papers/2303.09410,,,,6,0 Knowledge-Aware Federated Active Learning with Non-IID Data,"Cao, Yu-Tong*; Shi, Ye; Yu, Baosheng; Wang, Jingya; Tao, Dacheng",poster,2211.13579,https://arxiv.org/abs/2211.13579,,https://huggingface.co/papers/2211.13579,,,,5,0 SimpleClick: Interactive Image Segmentation with Simple Vision Transformers,"Liu, Qin *; Xu, Zhenlin; Bertasius, Gedas; Niethammer, Marc",poster,2210.11006,https://arxiv.org/abs/2210.11006,,https://huggingface.co/papers/2210.11006,,,,4,0 InterFormer: Real-time Interactive Image Segmentation,"Huang, You*; Yang, Hao; Sun, Ke; Zhang, ShengChuan; Cao, Liujuan; Jiang, Guannan; Ji, Rongrong",poster,2304.02942,https://arxiv.org/abs/2304.02942,https://github.com/YouHuang67/InterFormer,https://huggingface.co/papers/2304.02942,,,,7,0 @@ -2030,7 +2030,7 @@ The Stable Signature: Rooting Watermarks in Latent Diffusion Models,"Fernandez, Get the Best of Both Worlds: Discriminative and Transferable Features by Grassmannian Class Representation,"Li, Zhizhong; Wang, Haoqi*; Zhang, Wayne",poster,,,,,,,,, 4D Panoptic Segmentation as Invariant and Equivariant Field Prediction,"Zhu, Minghan*; Han, Shizhong; Cai, Hong; Borse, Shubhankar; Porikli, Fatih; Ghaffari Jadidi, Maani",poster,2303.15651,https://arxiv.org/abs/2303.15651,,https://huggingface.co/papers/2303.15651,,,,6,0 SiLK: Simple Learned Keypoints,"Gleize, Pierre*; Wang, Weiyao; Feiszli, Matt",poster,,,,,,,,, -"SC3K: Self-supervised and Coherent 3D Keypoints Estimation from Rotated, Noisy, and Decimated Point Cloud Data","Zohaib, Mohammad*; Del Bue, Alessio",poster,2308.05410,https://arxiv.org/abs/2308.05410,https://github.com/IITPAVIS/SC3K,https://huggingface.co/papers/2308.05410,,,,2,0 +"SC3K: Self-supervised and Coherent 3D Keypoints Estimation from Rotated, Noisy, and Decimated Point Cloud Data","Zohaib, Mohammad*; Del Bue, Alessio",poster,2308.0541,https://arxiv.org/abs/2308.05410,https://github.com/IITPAVIS/SC3K,https://huggingface.co/papers/2308.05410,,,,2,0 Geometric Viewpoint Learning with Hyper-Rays and Harmonics Encoding,"Min, Zhixiang*; Dibene Simental, Juan Carlos; Dunn, Enrique",poster,,,,,,,,, Surface Extraction from Neural Unsigned Distance Fields,"Zhang, Congyi*; Lin, Guying; Yang, Lei; Li, Xin; Komura, Taku; SCHAEFER, Scott; Keyser, John; Wang, Wenping",poster,,,,,,,,, Learning Adaptive Neighborhoods for Graph Neural Networks,"Saha, Avishkar*; Mendez, Oscar; Russell, Chris; Bowden, Richard",poster,2307.09065,https://arxiv.org/abs/2307.09065,,https://huggingface.co/papers/2307.09065,,,,4,0 @@ -2042,7 +2042,7 @@ MagicFusion: Boosting Text-to-Image Generation Performance by Fusing Diffusion M PODIA-3D: Domain Adaptation of 3D Generative Model Across Large Domain Gap Using Pose-Preserved Text-to-Image Diffusion,"Kim, Gwanghyun; jang, jiha; Chun, Se Young*",poster,,,,,,,,, Pluralistic Aging Diffusion Autoencoder,"Li, Peipei*; Wang, Rui; Huang, Huaibo; He, Ran; He, Zhaofeng",poster,2303.11086,https://arxiv.org/abs/2303.11086,,https://huggingface.co/papers/2303.11086,,,,5,0 DPM-OT: A New Diffusion Probabilistic Model Based on Optimal Transport,"Li, Zezeng; Li, Shenghao; Wang, Zhanpeng; Lei, Na*; Luo, Zhongxuan; GU, Xianfeng",poster,,,,,,,,, -Efficient Emotional Adaptation for Audio-driven Talking-Head Generation,"Gan, Yuan; Yang, Zongxin; Yue, Xihang; Sun, Lingyun; Yang, Yi*",poster,,,,,,,,, +Efficient Emotional Adaptation for Audio-driven Talking-Head Generation,"Gan, Yuan; Yang, Zongxin; Yue, Xihang; Sun, Lingyun; Yang, Yi*",poster,2309.04946,https://arxiv.org/abs/2309.04946,https://github.com/yuangan/EAT_code,https://huggingface.co/papers/2309.04946,,,,5,1 Diffusion Face Relighting,"Ponglertnapakorn, Puntawat -*; Tritrong, Nontawat; Suwajanakorn, Supasorn",poster,,,,,,,,, TALL: Thumbnail Layout for Deepfake Video Detection,"Xu, Yuting*; Liang, Jian; Jia, Gengyun; Yang, Ziming; Zhang, Yanhao; He, Ran",poster,2307.07494,https://arxiv.org/abs/2307.07494,https://github.com/rainy-xu/TALL4Deepfake,https://huggingface.co/papers/2307.07494,,,,6,0 LAW-Diffusion: Complex Scene Generation by Diffusion with Layouts,"Yang, Binbin*; Luo, Yi; Chen, Ziliang; Wang, Guangrun; Liang, Xiaodan; Lin, Liang",poster,,,,,,,,, @@ -2074,7 +2074,7 @@ Learning Human View Synthesis from Internet Videos,"Dong, Junting*; Fang, Qi; Ya ECG: Image Classification and Generation via a Single Energy-Based Model,"Guo, Qiushan*; Ma, Chuofan; Jiang, Yi; Yuan, Zehuan; Yu, Yizhou; Luo, Ping",poster,,,,,,,,, Automatic Animation of Hair Blowing in Still Portrait Photos,"Xiao, Wenpeng ; Liu, Wentao; Wang, Yitong; Ghanem, Bernard; Li, Bing*",poster,,,,,,,,, HoloFusion: Towards Photo-realistic 3D Generative Modeling,"Karnewar, Animesh*; Vedaldi, Andrea; mitra, niloy; Novotny, David",poster,2308.14244,https://arxiv.org/abs/2308.14244,,https://huggingface.co/papers/2308.14244,,,,4,0 -Foreground Object Search by Distilling Composite Image Feature,"Zhang, Bo*; Sui, Jiacheng; Niu, Li",poster,2308.04990,https://arxiv.org/abs/2308.04990,https://github.com/bcmi/Foreground-Object-Search-Dataset-FOSD,https://huggingface.co/papers/2308.04990,,,,3,0 +Foreground Object Search by Distilling Composite Image Feature,"Zhang, Bo*; Sui, Jiacheng; Niu, Li",poster,2308.0499,https://arxiv.org/abs/2308.04990,https://github.com/bcmi/Foreground-Object-Search-Dataset-FOSD,https://huggingface.co/papers/2308.04990,,,,3,0 OrthoPlanes: A Novel Representation for Better 3D-Awareness of GANs,"He, Honglin; Yang, Zhuoqian; Li, Shikai; Dai, Bo; Wu, Wayne*",poster,,,,,,,,, 3DHumanGAN: 3D-Aware Human Image Generation with Photorealism,"Yang, Zhuoqian; Li, Shikai; Wu, Wayne*; Dai, Bo",poster,,,,,,,,, MODA: Mapping-Once Audio-driven Portrait Animation with Dual Attentions,"Liu, Yunfei*; Lin, Lijian; Zhou, Changyin; YU, Fei; Li, Yu",poster,2307.10008,https://arxiv.org/abs/2307.10008,,https://huggingface.co/papers/2307.10008,,,,5,0 @@ -2082,7 +2082,7 @@ Minimum Latency Deep Online Video Stabilization,"Zhang, Zhuofan; Liu, Zhen; Tan, StableVideo: Text-driven Consistency-aware Diffusion Video Editing,"Chai, Wenhao; Guo, Xun*; Wang, Gaoang; Lu, Yan",poster,2308.09592,https://arxiv.org/abs/2308.09592,https://github.com/rese1f/StableVideo,https://huggingface.co/papers/2308.09592,,,,4,1 Localizing Object-level Shape Variations with Text-to-Image Diffusion Models,"Patashnik, Or*; Garibi, Daniel; Azuri, Idan; Averbuch-Elor, Hadar; Cohen-Or, Danny",poster,2303.11306,https://arxiv.org/abs/2303.11306,,https://huggingface.co/papers/2303.11306,,,,5,1 Implicit Identity Representation Conditioned Memory Compensation Network for Talking Head video Generation,"Hong, Fa-Ting*; Xu, Dan",poster,2307.09906,https://arxiv.org/abs/2307.09906,https://github.com/harlanhong/ICCV2023-MCNET,https://huggingface.co/papers/2307.09906,,,,2,0 -ESSAformer: Efficient Transformer for Hyperspectral Image Super-resolution,"Zhang, Mingjin; Zhang, Chi; Zhang, Qiming; Guo, Jie; Gao, Xinbo*; Zhang, Jing",poster,2307.14010,https://arxiv.org/abs/2307.14010,,https://huggingface.co/papers/2307.14010,,,,6,0 +ESSAformer: Efficient Transformer for Hyperspectral Image Super-resolution,"Zhang, Mingjin; Zhang, Chi; Zhang, Qiming; Guo, Jie; Gao, Xinbo*; Zhang, Jing",poster,2307.1401,https://arxiv.org/abs/2307.14010,,https://huggingface.co/papers/2307.14010,,,,6,0 GlueNet: Plug and Play Multi-modal Encoders for X-to-image Generation,"Qin, Can*; Yu, Ning; Xing, Chen; Zhang, Shu; Chen, Zeyuan; Ermon, Stefano ; FU, YUN; Xiong, Caiming; Xu, Ran",poster,,,,,,,,, UHDNeRF: Ultra-High-Definition Neural Radiance Fields,"Li, Quewei*; Li, Feichao; Guo, Jie; Guo, Yanwen",poster,,,,,,,,, All-to-key Attention for Arbitrary Style Transfer,"Zhu, Mingrui; He, Xiao; Wang, Nannan*; Wang, Xiaoyu; Gao, Xinbo",poster,2212.04105,https://arxiv.org/abs/2212.04105,,https://huggingface.co/papers/2212.04105,,,,5,0 @@ -2108,7 +2108,7 @@ Counting Crowds in Bad Weather,"Huang, Zhi-Kai; Chen, Wei-Ting; Chiang, Yuan-Chu NeRF-Det: Learning Geometry-Aware Volumetric Representation for Multi-View Indoor 3D Object Detection,"Xu, Chenfeng*; Wu, Bichen; Hou, Ji; Tsai, Sam; Li, Ruilong; Wang, Jialiang; Zhan, Wei; He, Zijian; Vajda, Peter; Keutzer, Kurt; TOMIZUKA, Masayoshi",poster,,,,,,,,, MEGA: Multimodal Alignment Aggregation and Distillation For Cinematic Video Segmentation,"Sadoughi, Najmeh*; Li, Xinyu; Vajpayee, Avijit; Fan, David; Shuai, Bing; Santos-Villalobos, Hector J; Bhat, Vimal; MV, Rohith",poster,2308.11185,https://arxiv.org/abs/2308.11185,,https://huggingface.co/papers/2308.11185,,,,8,0 Bring Clipart to Life,"Zhao, Nanxuan*; Dang, Shengqi; Lin, Hexun; Shi, Yang; Cao, Nan",poster,,,,,,,,, -UpCycling: Semi-supervised 3D Object Detection without Sharing Raw-level Unlabeled Scenes,"Hwang, Sunwook*; Kim, Youngseok; Kim, Seongwon; Bahk, Saewoong ; Kim, Hyung-Sin",poster,2211.11950,https://arxiv.org/abs/2211.11950,,https://huggingface.co/papers/2211.11950,,,,5,0 +UpCycling: Semi-supervised 3D Object Detection without Sharing Raw-level Unlabeled Scenes,"Hwang, Sunwook*; Kim, Youngseok; Kim, Seongwon; Bahk, Saewoong ; Kim, Hyung-Sin",poster,2211.1195,https://arxiv.org/abs/2211.11950,,https://huggingface.co/papers/2211.11950,,,,5,0 Graph Matching with Bi-level Noisy Correspondence,"Lin, Yijie; Yang, Mouxing; Yu, Jun; Hu, Peng; Zhang, Changqing; Peng, Xi*",poster,2212.04085,https://arxiv.org/abs/2212.04085,https://github.com/XLearning-SCU/2023-ICCV-COMMON,https://huggingface.co/papers/2212.04085,,,,6,0 Anomaly Detection using Score-based Perturbation Resilience,"Shin, Woosang*; Lee, Jong-Hyeon; Lee, Taehan; Lee, Sangmoon; Yun, Jong Pil",poster,,,,,,,,, Spatio-Temporal Domain Awareness for Multi-Agent Collaborative Perception,"yang, kun*; Yang, Dingkang; Zhang, Jingyu; Li, Mingcheng; Liu, Yang; Liu, Jing; Wang, Hanqi; Sun, Peng; Song, Liang ",poster,2307.13929,https://arxiv.org/abs/2307.13929,,https://huggingface.co/papers/2307.13929,,,,9,0 @@ -2128,21 +2128,21 @@ One-shot recognition of any material anywhere using contrastive learning with ph Fast Full-frame Video Stabilization with Iterative Optimization,"Zhao, Weiyue; Li, Xin; Peng, Zhan; Luo, Xianrui; Ye, Xinyi; Lu, Hao; Cao, Zhiguo*",poster,2307.12774,https://arxiv.org/abs/2307.12774,,https://huggingface.co/papers/2307.12774,,,,7,0 "Two Birds, One Stone: A Unified Framework for Joint Learning of Image and Video Style Transfers","gu, bohai; Fan, Heng; Zhang, Libo*",poster,2304.11335,https://arxiv.org/abs/2304.11335,,https://huggingface.co/papers/2304.11335,,,,3,0 Multi-modal Gated Mixture of Local-to-Global Experts for Dynamic Image Fusion,"Sun, Yiming*; Cao, Bing; Zhu, Pengfei; Hu, Qinghua",poster,2302.01392,https://arxiv.org/abs/2302.01392,https://github.com/SunYM2020/MoE-Fusion,https://huggingface.co/papers/2302.01392,,,,4,0 -SAFE: Sensitivity-Aware Features for Out-of-Distribution Object Detection,"Wilson, Samuel James*; Fischer, Tobias; Dayoub, Feras; Miller, Dimity; Suenderhauf, Niko",poster,2208.13930,https://arxiv.org/abs/2208.13930,,https://huggingface.co/papers/2208.13930,,,,5,0 +SAFE: Sensitivity-Aware Features for Out-of-Distribution Object Detection,"Wilson, Samuel James*; Fischer, Tobias; Dayoub, Feras; Miller, Dimity; Suenderhauf, Niko",poster,2208.1393,https://arxiv.org/abs/2208.13930,,https://huggingface.co/papers/2208.13930,,,,5,0 GeT: Generative Target Structure Debiasing for Domain Adaptation,"Zhang, Can*; Lee, Gim Hee",poster,2308.10205,https://arxiv.org/abs/2308.10205,,https://huggingface.co/papers/2308.10205,,,,2,0 HairCLIPv2: Unifying Hair Editing via Proxy Feature Blending,"Wei, Tianyi*; Chen, Dongdong; Zhou, Wenbo; Liao, Jing; Zhang, Weiming; Hua, Gang; Yu, Nenghai",poster,,,,,,,,, Deformer: Dynamic Fusion Transformer for Robust Hand Pose Estimation,"Fu, Qichen*; Liu, Xingyu; Xu, Ran; Niebles, Juan Carlos; Kitani, Kris",poster,2303.04991,https://arxiv.org/abs/2303.04991,,https://huggingface.co/papers/2303.04991,,,,5,1 Improving Continuous Sign Language Recognition with Cross-Lingual Signs,"Chen, Yutong; Wei, Fangyun*",poster,2308.10809,https://arxiv.org/abs/2308.10809,,https://huggingface.co/papers/2308.10809,,,,2,0 -A Parse-Then-Place Approach for Generating Graphic Layouts from Textual Descriptions,"Lin, Jiawei*; Guo, Jiaqi; Sun, Shizhao; Xu, Weijiang; Liu, Ting; Lou, Jian-Guang; Zhang, Dongmei",poster,2308.12700,https://arxiv.org/abs/2308.12700,,https://huggingface.co/papers/2308.12700,,,,7,0 +A Parse-Then-Place Approach for Generating Graphic Layouts from Textual Descriptions,"Lin, Jiawei*; Guo, Jiaqi; Sun, Shizhao; Xu, Weijiang; Liu, Ting; Lou, Jian-Guang; Zhang, Dongmei",poster,2308.127,https://arxiv.org/abs/2308.12700,,https://huggingface.co/papers/2308.12700,,,,7,0 DISeR: Designing Imaging Systems with Reinforcement Learning,"Klinghoffer, Tzofi M*; Tiwary, Kushagra; Behari, Nikhil; Agrawalla, Bhavya K; Raskar, Ramesh",poster,,,,,,,,, Segmentation of Tubular Structures Using Iterative Training With Tailored Samples,"Liao, Wei*",poster,,,,,,,,, Time-to-Contact Map by Joint Estimation of Up-to-Scale Inverse Depth and Global Motion using a Single Event Camera,"Nunes, Urbano Miguel G.*; Perrinet, Laurent U; Ieng, Sio-Hoi",poster,,,,,,,,, Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fields,"Barron, Jonathan T*; Mildenhall, Ben; Verbin, Dor; Srinivasan, Pratul; Hedman, Peter",oral,,,,,,,,, -Mixed Neural Voxels for Fast Multi-view Video Synthesis,"Wang, Feng*; Tan, Sinan; Li, Xinghang; Tian, Zeyue; Song, Yafei; Liu, Huaping",oral,2212.00190,https://arxiv.org/abs/2212.00190,https://github.com/fengres/mixvoxels,https://huggingface.co/papers/2212.00190,,,,5,0 +Mixed Neural Voxels for Fast Multi-view Video Synthesis,"Wang, Feng*; Tan, Sinan; Li, Xinghang; Tian, Zeyue; Song, Yafei; Liu, Huaping",oral,2212.0019,https://arxiv.org/abs/2212.00190,https://github.com/fengres/mixvoxels,https://huggingface.co/papers/2212.00190,,,,5,0 Diffusion-Guided Reconstruction of Everyday Hand-Object Interaction Clips,"Ye, Yufei*; Hebbar, Poorvi; Gupta, Abhinav; Tulsiani, Shubham",oral,,,,,,,,, LERF: Language Embedded Radiance Fields,"Kerr, Justin; Kim, Chung Min*; Goldberg, Ken; Kanazawa, Angjoo; Tancik, Matthew",oral,2303.09553,https://arxiv.org/abs/2303.09553,,https://huggingface.co/papers/2303.09553,,,,5,0 Instruct-NeRF2NeRF: Editing 3D Scenes with Instructions,"Haque, Ayaan*; Tancik, Matthew; Efros, Alexei A; Holynski, Aleksander; Kanazawa, Angjoo",oral,2303.12789,https://arxiv.org/abs/2303.12789,,https://huggingface.co/papers/2303.12789,,,,5,0 -P1AC: Revisiting Absolute Pose From a Single Affine Correspondence,"Ventura, Jonathan*; Kukelova, Zuzana; Sattler, Torsten; Barath, Daniel",oral,2011.08790,https://arxiv.org/abs/2011.08790,https://github.com/jonathanventura/P1AC,https://huggingface.co/papers/2011.08790,,,,4,0 +P1AC: Revisiting Absolute Pose From a Single Affine Correspondence,"Ventura, Jonathan*; Kukelova, Zuzana; Sattler, Torsten; Barath, Daniel",oral,2011.0879,https://arxiv.org/abs/2011.08790,https://github.com/jonathanventura/P1AC,https://huggingface.co/papers/2011.08790,,,,4,0 Prior-Guided Strand-Based Hair Reconstruction,"Skliarova, Vanessa Valerievna; Chelishev, Jenya; Dogaru, Andreea; Medvedev, Igor; Lempitsky, Victor; Zakharov, Egor*",oral,,,,,,,,, Tri-MipRF: Tri-Mip Representation for Efficient Anti-Aliasing Neural Radiance Fields,"Hu, Wenbo*; Wang, Yuling; Ma, Lin; Yang, Bangbang; Gao, Lin; Liu, Xiao; Ma, Yuewen",oral,,,,,,,,, LiDAR-UDA: Self-ensembling Through Time for Unsupervised LiDAR Domain Adaptation,"Shaban, Amirreza*; Lee, JoonHo; Jung, Sanghun; Meng, Xiangyun; Boots, Byron",oral,,,,,,,,,