,task,count
0,general classification,7530
1,image classification,6215
2,semantic segmentation,5691
3,object detection,5645
4,translation,4428
5,reinforcement learning,4265
6,classification,3350
7,language modelling,3299
8,representation learning,3089
9,question answering,2831
10,machine translation,2684
11,transfer learning,2583
12,image generation,2258
13,sentiment analysis,2172
14,frame,2157
15,data augmentation,2106
16,time series,1782
17,text classification,1675
18,domain adaptation,1525
19,super resolution,1517
20,pose estimation,1450
21,natural language inference,1449
22,real time object detection,1446
23,instance segmentation,1425
24,decision making,1310
25,person re identification,1307
26,named entity recognition,1284
27,image to image translation,1276
28,word embeddings,1247
29,denoising,1179
30,text generation,1161
31,style transfer,1152
32,recommendation systems,1119
33,natural language understanding,1091
34,self supervised learning,1044
35,speech recognition,1005
36,meta learning,999
37,multi task learning,945
38,text summarization,939
39,medical image segmentation,918
40,contrastive learning,918
41,neural architecture search,909
42,action recognition,895
43,autonomous driving,887
44,image super resolution,882
45,abstractive text summarization,877
46,variational inference,874
47,anomaly detection,872
48,q learning,838
49,link prediction,823
50,few shot learning,812
51,object recognition,811
52,knowledge distillation,779
53,node classification,778
54,atari games,773
55,common sense reasoning,769
56,quantization,740
57,thermal image segmentation,731
58,image captioning,730
59,visual question answering,720
60,face recognition,714
61,sentence classification,711
62,dimensionality reduction,684
63,information retrieval,656
64,knowledge graphs,648
65,conditional image generation,646
66,reading comprehension,645
67,continuous control,638
68,semantic textual similarity,634
69,fairness,633
70,multi tissue nucleus segmentation,626
71,depth estimation,620
72,bayesian inference,612
73,conversational response selection,601
74,region proposal,600
75,constituency parsing,593
76,retinal oct disease classification,575
77,image retrieval,555
78,optical flow estimation,550
79,unsupervised domain adaptation,546
80,cross lingual natural language inference,541
81,type prediction,538
82,adversarial attack,537
83,relation extraction,536
84,metric learning,534
85,linear probe classification,533
86,keypoint detection,532
87,multimodal machine translation,530
88,federated learning,522
89,ner,522
90,scene understanding,516
91,feature engineering,513
92,object tracking,512
93,active learning,497
94,graph classification,494
95,pedestrian attribute recognition,493
96,image clustering,487
97,stochastic optimization,486
98,vqa,483
99,semi supervised image classification,480
100,domain generalization,476
101,retinal vessel segmentation,472
102,gaussian processes,471
103,temporal action localization,470
104,cell segmentation,469
105,graph embedding,466
106,disentanglement,465
107,video polyp segmentation,454
108,pancreas segmentation,449
109,face verification,447
110,feature selection,444
111,semantic parsing,442
112,skin cancer segmentation,441
113,pedestrian detection,438
114,continual learning,436
115,3d object detection,428
116,collaborative filtering,426
117,adversarial robustness,419
118,autonomous vehicles,416
119,pedestrian trajectory prediction,409
120,fine grained image classification,407
121,image reconstruction,405
122,density estimation,402
123,speech enhancement,395
124,image denoising,394
125,imitation learning,393
126,one stage anchor free oriented object detection,393
127,nuclear segmentation,390
128,zero shot learning,387
129,skeleton based action recognition,380
130,model selection,380
131,automatic speech recognition,378
132,3d reconstruction,376
133,action classification,370
134,interpretable machine learning,359
135,multi person pose estimation,357
136,object localization,356
137,document classification,352
138,speech synthesis,352
139,time series forecasting,351
140,lesion segmentation,351
141,real time semantic segmentation,349
142,panoptic segmentation,349
143,semantic similarity,346
144,image restoration,343
145,image inpainting,343
146,self supervised image classification,334
147,optical character recognition,334
148,colorization,333
149,model compression,330
150,unsupervised image to image translation,329
151,multi agent reinforcement learning,327
152,dialogue generation,317
153,crowd counting,316
154,few shot image classification,313
155,online learning,312
156,dependency parsing,309
157,face detection,308
158,emotion recognition,305
159,scene segmentation,303
160,face identification,300
161,pretrained language models,295
162,automl,292
163,monocular depth estimation,288
164,multi label classification,284
165,3d human pose estimation,283
166,eeg,278
167,video semantic segmentation,278
168,self driving cars,277
169,graph attention,276
170,3d point cloud classification,275
171,hyperparameter optimization,273
172,causal inference,272
173,drug discovery,272
174,3d semantic segmentation,270
175,network pruning,268
176,pos,267
177,policy gradient methods,263
178,long tail learning,261
179,tag,261
180,sentence embeddings,259
181,graph representation learning,255
182,video super resolution,254
183,video classification,253
184,ssim,249
185,coreference resolution,249
186,structured prediction,247
187,part of speech tagging,244
188,dense object detection,239
189,graph learning,235
190,document summarization,233
191,deblurring,231
192,synthetic data generation,230
193,computed tomography (ct),229
194,openai gym,229
195,3d part segmentation,229
196,word similarity,229
197,one shot learning,226
198,salient object detection,225
199,imputation,224
200,multimodal unsupervised image to image translation,220
201,face generation,220
202,multiple object tracking,218
203,video understanding,218
204,adversarial defense,217
205,face alignment,216
206,combinatorial optimization,216
207,lane detection,216
208,out of distribution detection,215
209,3d instance segmentation,212
210,fundus to angiography generation,212
211,graph regression,208
212,activity recognition,206
213,time series classification,205
214,response generation,203
215,cross lingual transfer,200
216,time series few shot learning with heterogeneous channels,200
217,text to image generation,200
218,speech emotion recognition,200
219,community detection,199
220,relational reasoning,199
221,open domain question answering,196
222,image enhancement,196
223,feature importance,194
224,click through rate prediction,194
225,action detection,193
226,topic models,191
227,video prediction,190
228,video object segmentation,189
229,speaker verification,189
230,incremental learning,188
231,document image classification,186
232,scene text recognition,186
233,question generation,185
234,motion estimation,183
235,scene text detection,182
236,image manipulation,182
237,tumor segmentation,179
238,linguistic acceptability,178
239,outlier detection,175
240,machine reading comprehension,175
241,video generation,173
242,multi human parsing,172
243,multivariate time series forecasting,172
244,object counting,170
245,entity linking,170
246,human part segmentation,169
247,disguised face verification,168
248,2d human pose estimation,168
249,multi object tracking,167
250,multi class classification,167
251,semantic role labeling,167
252,video recognition,166
253,sentence embedding,165
254,cross view image to image translation,164
255,image augmentation,163
256,re ranking,163
257,image quality assessment,161
258,dota 2,161
259,image compression,160
260,visual tracking,159
261,knowledge graph embedding,157
262,ensemble learning,155
263,multiple instance learning,155
264,masked language modeling,155
265,scene parsing,154
266,model based reinforcement learning,154
267,autonomous navigation,154
268,event detection,153
269,misinformation,153
270,graph generation,153
271,unsupervised anomaly detection,153
272,text to speech synthesis,152
273,traffic prediction,150
274,rgb salient object detection,150
275,trajectory prediction,149
276,network embedding,149
277,breast tumour classification,148
278,motion planning,147
279,efficient exploration,147
280,brain tumor segmentation,147
281,fact checking,146
282,saliency detection,146
283,point cloud registration,146
284,image registration,145
285,node property prediction,144
286,knowledge graph completion,144
287,aspect based sentiment analysis,143
288,starcraft,140
289,voice conversion,139
290,word sense disambiguation,138
291,dictionary learning,137
292,paraphrase identification,136
293,novel view synthesis,136
294,hate speech detection,135
295,explainable artificial intelligence,135
296,multi armed bandits,135
297,cross modal retrieval,134
298,learning to rank,133
299,relation classification,133
300,matrix completion,133
301,change detection,133
302,simultaneous localization and mapping,133
303,video retrieval,133
304,3d pose estimation,132
305,face swapping,132
306,robust classification,131
307,ood detection,131
308,speaker specific lip to speech synthesis,130
309,fake news detection,128
310,visual reasoning,126
311,visual object tracking,125
312,audio generation,124
313,time series prediction,123
314,speaker recognition,123
315,robot navigation,122
316,binarization,122
317,stereo matching,120
318,multiple choice,120
319,unity,119
320,multi task language understanding,119
321,chatbot,118
322,3d classification,118
323,video captioning,116
324,unsupervised pre training,114
325,video instance segmentation,114
326,point processes,114
327,keyword spotting,113
328,class incremental learning,112
329,graph clustering,112
330,slot filling,111
331,covid 19 diagnosis,111
332,action recognition in videos,111
333,code generation,111
334,facial expression recognition,110
335,variable selection,109
336,audio classification,108
337,experimental design,107
338,general reinforcement learning,107
339,informativeness,107
340,edge detection,107
341,text matching,107
342,whole slide images,106
343,motion prediction,106
344,visual localization,104
345,unsupervised machine translation,104
346,graph construction,103
347,extractive summarization,103
348,data to text generation,103
349,self supervised person re identification,103
350,action localization,103
351,extractive text summarization,102
352,unsupervised image classification,101
353,offline rl,101
354,dynamic time warping,100
355,time series analysis,100
356,knowledge graph embeddings,100
357,facial landmark detection,100
358,generalization bounds,100
359,visual odometry,99
360,intent detection,98
361,saliency prediction,98
362,image retrieval with multi modal query,98
363,boundary detection,98
364,out of distribution generalization,97
365,graph matching,97
366,weakly supervised object localization,97
367,dialogue state tracking,96
368,text to sql,96
369,real time instance segmentation,95
370,tensor decomposition,95
371,emotion classification,95
372,hierarchical reinforcement learning,95
373,starcraft ii,95
374,visual grounding,94
375,news recommendation,94
376,music generation,93
377,speech separation,93
378,neural rendering,93
379,medical diagnosis,93
380,texture synthesis,93
381,sound event detection,92
382,intent classification,92
383,program synthesis,92
384,visual place recognition,91
385,weakly supervised semantic segmentation,90
386,data visualization,90
387,surface reconstruction,90
388,6d pose estimation using rgb,89
389,text style transfer,89
390,compressive sensing,89
391,semi supervised video object segmentation,89
392,speaker identification,89
393,task oriented dialogue systems,89
394,deep clustering,88
395,6d pose estimation,87
396,meta reinforcement learning,87
397,image deblurring,87
398,two sample testing,86
399,learning with noisy labels,86
400,knowledge base completion,86
401,music modeling,86
402,multivariate time series imputation,85
403,causal discovery,85
404,gesture recognition,85
405,sequential recommendation,85
406,monocular 3d human pose estimation,84
407,language identification,84
408,pose tracking,83
409,passage retrieval,83
410,multi document summarization,82
411,unsupervised mnist,82
412,learning theory,82
413,video quality assessment,82
414,spoken language understanding,82
415,mri reconstruction,82
416,superpixels,81
417,human object interaction detection,81
418,visual navigation,81
419,malware detection,81
420,word alignment,81
421,rain removal,81
422,answer selection,81
423,topological data analysis,80
424,event extraction,80
425,fraud detection,80
426,probabilistic programming,80
427,hand pose estimation,80
428,edge computing,79
429,chunking,79
430,molecular property prediction,79
431,game of go,79
432,music information retrieval,79
433,document ranking,79
434,image dehazing,78
435,grammatical error correction,78
436,survival analysis,78
437,scene classification,78
438,human detection,77
439,synthetic to real translation,76
440,large scale person re identification,76
441,session based recommendations,76
442,neural network compression,76
443,video object detection,75
444,3d face reconstruction,75
445,3d object reconstruction,75
446,small data image classification,75
447,sequential image classification,75
448,data compression,74
449,video frame interpolation,74
450,stance detection,74
451,scene recognition,74
452,referring expression,74
453,entity typing,73
454,selection bias,73
455,gaze estimation,72
456,image matting,72
457,point cloud classification,72
458,brain segmentation,71
459,game of chess,71
460,montezuma's revenge,70
461,camera calibration,70
462,3d shape reconstruction,70
463,deepfake detection,69
464,weather forecasting,69
465,2d object detection,69
466,video question answering,69
467,object reconstruction,68
468,adversarial text,67
469,pose prediction,67
470,handwriting recognition,66
471,sentence similarity,66
472,homography estimation,66
473,text simplification,66
474,distributed computing,66
475,subjectivity analysis,65
476,video segmentation,65
477,inference attack,65
478,game of shogi,65
479,visual dialog,65
480,entity embeddings,65
481,scene graph generation,65
482,low light image enhancement,65
483,human action generation,64
484,distributed optimization,64
485,face hallucination,64
486,face reconstruction,63
487,multi label text classification,63
488,robotic grasping,62
489,bayesian optimisation,62
490,music source separation,62
491,bilevel optimization,62
492,intrusion detection,62
493,lexical simplification,61
494,video compression,61
495,data poisoning,61
496,motion compensation,61
497,face model,61
498,humor detection,60
499,cloze test,60
500,referring expression comprehension,60
501,self learning,60
502,hyperspectral image classification,59
503,semi supervised semantic segmentation,59
504,change point detection,58
505,multi label learning,58
506,birds eye view object detection,57
507,pneumonia detection,57
508,multimodal sentiment analysis,57
509,document layout analysis,57
510,code summarization,57
511,stochastic block model,56
512,entity alignment,56
513,stereo depth estimation,56
514,chinese named entity recognition,55
515,trajectory forecasting,55
516,argument mining,55
517,morphological analysis,55
518,malware classification,55
519,ms ssim,55
520,audio source separation,55
521,demosaicking,55
522,image stylization,55
523,video summarization,54
524,multimodal activity recognition,54
525,point cloud completion,54
526,depth completion,54
527,template matching,54
528,3d hand pose estimation,54
529,sarcasm detection,54
530,real time strategy games,53
531,motion segmentation,53
532,car pose estimation,53
533,prediction intervals,53
534,electrocardiography (ecg),53
535,activity detection,52
536,citation intent classification,52
537,point cloud segmentation,52
538,monocular 3d object detection,52
539,weakly supervised segmentation,52
540,rgb d salient object detection,52
541,multi label image classification,52
542,speaker diarization,52
543,systematic generalization,52
544,zero shot cross lingual transfer,52
545,univariate time series forecasting,51
546,entity extraction using gan,51
547,lemmatization,51
548,3d medical imaging segmentation,51
549,object detection in aerial images,51
550,backdoor attack,51
551,opinion mining,51
552,scene generation,51
553,traveling salesman problem,50
554,action segmentation,50
555,unsupervised person re identification,50
556,chinese word segmentation,50
557,epidemiology,50
558,portfolio optimization,50
559,age estimation,50
560,language acquisition,50
561,semantic correspondence,50
562,generalized zero shot learning,49
563,fact verification,49
564,multi goal reinforcement learning,49
565,virtual try on,49
566,mortality prediction,49
567,tensor networks,48
568,vision and language navigation,48
569,temporal localization,48
570,knowledge tracing,48
571,source code summarization,47
572,vehicle re identification,47
573,open set learning,47
574,accented speech recognition,47
575,word translation,47
576,thoracic disease classification,47
577,head pose estimation,47
578,sparse learning,47
579,story generation,47
580,dialogue evaluation,46
581,object discovery,46
582,few shot semantic segmentation,46
583,point cloud generation,46
584,hard attention,46
585,curved text detection,46
586,stereo matching hand,46
587,few shot object detection,45
588,distributional reinforcement learning,45
589,keyphrase extraction,45
590,3d shape representation,45
591,jpeg artifact correction,45
592,paraphrase generation,45
593,car racing,45
594,additive models,45
595,medical image registration,44
596,open information extraction,44
597,human motion prediction,44
598,ad hoc information retrieval,44
599,joint entity and relation extraction,44
600,defect detection,44
601,amr parsing,44
602,automated theorem proving,44
603,stock market prediction,44
604,disparity estimation,43
605,lesion detection,43
606,deep attention,43
607,text spotting,43
608,arrhythmia detection,43
609,conversational question answering,43
610,graph mining,43
611,entity disambiguation,43
612,membership inference attack,43
613,community question answering,43
614,interactive segmentation,43
615,sign language recognition,43
616,color image denoising,42
617,cross lingual word embeddings,42
618,single image dehazing,42
619,multimodal deep learning,42
620,image matching,42
621,code search,42
622,face anti spoofing,42
623,motion forecasting,41
624,small object detection,41
625,human parsing,41
626,molecular graph generation,41
627,text categorization,41
628,one shot visual object segmentation,41
629,smac,41
630,3d action recognition,40
631,visual commonsense reasoning,40
632,genre classification,40
633,multi hop question answering,40
634,skin lesion segmentation,40
635,abusive language,40
636,unsupervised reinforcement learning,40
637,multi view learning,40
638,nested named entity recognition,40
639,imbalanced classification,40
640,motion synthesis,39
641,numerical integration,39
642,fine grained visual categorization,39
643,multimodal emotion recognition,39
644,board games,39
645,gender prediction,39
646,survival prediction,39
647,handwritten text recognition,38
648,emotion recognition in conversation,38
649,noisy speech recognition,38
650,sentence completion,38
651,network intrusion detection,38
652,video enhancement,38
653,text similarity,38
654,unsupervised video object segmentation,38
655,single image deraining,38
656,cardiac segmentation,38
657,medical object detection,37
658,inductive logic programming,37
659,topic classification,37
660,hippocampus,37
661,discourse parsing,37
662,fault detection,37
663,music transcription,36
664,zero shot cross modal retrieval,36
665,disease prediction,36
666,term extraction,36
667,audio tagging,36
668,riemannian optimization,36
669,image cropping,36
670,probabilistic time series forecasting,36
671,fine grained image recognition,36
672,aspect extraction,36
673,dense pixel correspondence estimation,35
674,future prediction,35
675,spatio temporal forecasting,35
676,hand gesture recognition,35
677,fine grained visual recognition,35
678,object proposal generation,34
679,video denoising,34
680,formation energy,34
681,conversational response generation,34
682,line detection,34
683,time series clustering,34
684,node clustering,34
685,semi supervised anomaly detection,34
686,few shot text classification,34
687,weakly supervised 3d human pose estimation,34
688,gpr,34
689,cross lingual document classification,34
690,lip reading,33
691,graph sampling,33
692,table to text generation,33
693,temporal action proposal generation,33
694,mri segmentation,33
695,medical named entity recognition,33
696,shadow removal,33
697,transliteration,33
698,lung disease classification,33
699,weakly supervised classification,33
700,scene flow estimation,33
701,unsupervised semantic segmentation,33
702,knowledge base question answering,33
703,interest point detection,33
704,lipreading,33
705,breast cancer detection,32
706,goal oriented dialog,32
707,self supervised action recognition,32
708,visual relationship detection,32
709,safe reinforcement learning,32
710,weakly supervised action localization,32
711,weakly supervised object detection,32
712,protein folding,32
713,liver segmentation,32
714,3d object classification,32
715,abuse detection,31
716,6d pose estimation using rgbd,31
717,lung nodule segmentation,31
718,patch matching,31
719,volumetric medical image segmentation,31
720,answer generation,31
721,probabilistic deep learning,31
722,single view 3d reconstruction,31
723,multi domain dialogue state tracking,31
724,sentence summarization,31
725,mutual information estimation,31
726,speech to text translation,31
727,camera localization,31
728,traffic sign recognition,30
729,video description,30
730,knowledge base population,30
731,image forensics,30
732,spelling correction,30
733,de identification,30
734,video based person re identification,30
735,entity resolution,30
736,texture classification,30
737,sleep staging,30
738,person retrieval,29
739,pose transfer,29
740,no reference image quality assessment,29
741,blind super resolution,29
742,object categorization,29
743,text independent speaker verification,29
744,medical image generation,29
745,referring expression segmentation,29
746,music tagging,29
747,product recommendation,29
748,graph partitioning,29
749,depth and camera motion,29
750,color constancy,29
751,meme classification,29
752,chinese reading comprehension,28
753,viewpoint estimation,28
754,speaker separation,28
755,cross domain few shot,28
756,graph similarity,28
757,permuted mnist,28
758,counterfactual explanation,28
759,graph to sequence,28
760,bias detection,28
761,document embedding,28
762,anomaly detection in surveillance videos,28
763,mixed reality,27
764,noise estimation,27
765,3d face modeling,27
766,medical relation extraction,27
767,3d object recognition,27
768,counterfactual inference,27
769,card games,27
770,person search,27
771,multiobjective optimization,27
772,3d shape classification,27
773,spam detection,27
774,morphological inflection,27
775,multi target domain adaptation,27
776,dialogue understanding,27
777,second order methods,27
778,material recognition,27
779,safe exploration,26
780,text segmentation,26
781,zero shot transfer image classification,26
782,sketch based image retrieval,26
783,code completion,26
784,robust object detection,26
785,handwritten digit recognition,26
786,open domain dialog,26
787,bilingual lexicon induction,26
788,pico,26
789,pointgoal navigation,26
790,point cloud reconstruction,26
791,foveation,26
792,unsupervised text style transfer,26
793,text augmentation,26
794,music classification,26
795,geometric matching,26
796,video inpainting,26
797,physical simulations,26
798,content based image retrieval,26
799,data summarization,26
800,3d multi object tracking,25
801,grounded language learning,25
802,weakly supervised temporal action localization,25
803,stock prediction,25
804,lidar semantic segmentation,25
805,prompt engineering,25
806,text to video retrieval,25
807,fps games,25
808,unconditional image generation,25
809,headline generation,25
810,one class classifier,25
811,semi supervised text classification,25
812,fake image detection,25
813,3d multi person pose estimation,25
814,automatic post editing,25
815,multi source unsupervised domain adaptation,25
816,3d shape generation,25
817,video restoration,25
818,environmental sound classification,25
819,sleep stage detection,25
820,table detection,24
821,3d human reconstruction,24
822,stance classification,24
823,decision making under uncertainty,24
824,online multi object tracking,24
825,multi frame super resolution,24
826,graph property prediction,24
827,extreme multi label classification,24
828,decipherment,24
829,news classification,24
830,robust face recognition,24
831,reflection removal,24
832,acoustic scene classification,24
833,graph reconstruction,24
834,text image retrieval,24
835,normalising flows,24
836,conversational search,24
837,program repair,24
838,copy detection,24
839,vehicle pose estimation,24
840,audio question answering,24
841,face clustering,23
842,dialogue management,23
843,time series regression,23
844,talking head generation,23
845,sentence fusion,23
846,indoor localization,23
847,privacy preserving deep learning,23
848,surface normals estimation,23
849,speech denoising,23
850,edge classification,23
851,length of stay prediction,23
852,3d object tracking,23
853,sentence compression,22
854,infrared and visible image fusion,22
855,lesion classification,22
856,image deblocking,22
857,shadow detection,22
858,video to video synthesis,22
859,keyword extraction,22
860,trajectory planning,22
861,ecg classification,22
862,program induction,22
863,image morphing,22
864,vulnerability detection,22
865,action anticipation,22
866,talking face generation,22
867,,22
868,explanation generation,21
869,multi future trajectory prediction,21
870,text clustering,21
871,activity prediction,21
872,information plane,21
873,aspect sentiment triplet extraction,21
874,line segment detection,21
875,text based games,21
876,seizure detection,21
877,mathematical reasoning,21
878,semantic slam,21
879,l2 regularization,21
880,camouflaged object segmentation,21
881,learning word embeddings,21
882,passage ranking,21
883,multilingual nlp,21
884,vision language navigation,21
885,single object discovery,21
886,math word problem solving,21
887,action triplet recognition,21
888,salt and pepper noise removal,21
889,protein structure prediction,21
890,keyphrase generation,21
891,graph structure learning,21
892,natural language visual grounding,20
893,semantic composition,20
894,remote sensing image classification,20
895,zero shot action recognition,20
896,personalized federated learning,20
897,generative question answering,20
898,unsupervised image segmentation,20
899,visual speech recognition,20
900,video text retrieval,20
901,2d semantic segmentation,20
902,table recognition,20
903,learning to execute,20
904,game of doom,20
905,extractive document summarization,20
906,multilingual word embeddings,20
907,total energy,20
908,long range modeling,20
909,key information extraction,20
910,citation recommendation,20
911,video style transfer,20
912,stock price prediction,20
913,code translation,20
914,heartbeat classification,20
915,load forecasting,19
916,extreme summarization,19
917,gait recognition,19
918,iris recognition,19
919,abnormal event detection in video,19
920,histopathological image classification,19
921,legged robots,19
922,cross lingual ner,19
923,few shot relation classification,19
924,intent classification and slot filling,19
925,morphological tagging,19
926,automated feature engineering,19
927,word sense induction,19
928,density ratio estimation,19
929,rotated mnist,19
930,conditional text generation,19
931,brain image segmentation,19
932,loop closure detection,19
933,3d face alignment,19
934,humanitarian,18
935,unsupervised object segmentation,18
936,classification with binary neural network,18
937,3d human pose and shape estimation,18
938,twitter sentiment analysis,18
939,mathematical proofs,18
940,parallel corpus mining,18
941,aerial scene classification,18
942,triple classification,18
943,zero shot text to image generation,18
944,blind image quality assessment,18
945,cross domain few shot learning,18
946,audio captioning,18
947,age and gender classification,18
948,passage re ranking,18
949,video reconstruction,18
950,moment retrieval,18
951,dqn replay dataset,18
952,cloud detection,18
953,bsds500,18
954,tone mapping,18
955,face parsing,17
956,stereo disparity estimation,17
957,semantic dependency parsing,17
958,malware analysis,17
959,question similarity,17
960,lexical entailment,17
961,3d semantic scene completion,17
962,video salient object detection,17
963,spoken dialogue systems,17
964,event based vision,17
965,nested mention recognition,17
966,artificial life,17
967,license plate recognition,17
968,visual storytelling,17
969,superpixel image classification,17
970,change detection for remote sensing images,17
971,dense video captioning,17
972,semantic text matching,17
973,multiple choice question answering (mcqa),17
974,real time visual tracking,17
975,action generation,17
976,few shot anomaly detection,17
977,operator learning,17
978,poker hand classification,17
979,transition based dependency parsing,17
980,phrase grounding,17
981,cross lingual bitext mining,17
982,model extraction,17
983,partial domain adaptation,17
984,dialect identification,17
985,image relighting,17
986,transparent objects,16
987,robust face alignment,16
988,constituency grammar induction,16
989,toxic spans detection,16
990,low rank matrix completion,16
991,real time multi object tracking,16
992,skull stripping,16
993,token classification,16
994,vector graphics,16
995,action quality assessment,16
996,distant speech recognition,16
997,transfer reinforcement learning,16
998,unsupervised video summarization,16
999,spike sorting,16
1000,dialogue act classification,16
1001,predictive process monitoring,16
1002,disaster response,16
1003,3d depth estimation,16
1004,low resource neural machine translation,16
1005,game of poker,16
1006,rumour detection,16
1007,entity retrieval,16
1008,event coreference resolution,16
1009,explainable models,16
1010,image defocus deblurring,16
1011,document ai,16
1012,physics informed machine learning,16
1013,egocentric activity recognition,16
1014,head detection,16
1015,3d shape recognition,16
1016,amr to text generation,16
1017,3d scene reconstruction,16
1018,hyperspectral unmixing,16
1019,visual entailment,16
1020,resynthesis,16
1021,action understanding,15
1022,supervised video summarization,15
1023,fine grained action recognition,15
1024,video object tracking,15
1025,kg to text generation,15
1026,model poisoning,15
1027,3d point cloud reconstruction,15
1028,semi supervised object detection,15
1029,text infilling,15
1030,facial inpainting,15
1031,image based localization,15
1032,perceptual distance,15
1033,music genre classification,15
1034,connectivity estimation,15
1035,auxiliary learning,15
1036,small footprint keyword spotting,15
1037,ccg supertagging,15
1038,emotion cause extraction,15
1039,skin lesion classification,15
1040,seismic imaging,15
1041,monocular visual odometry,15
1042,caricature,15
1043,image quality estimation,15
1044,video stabilization,15
1045,jpeg compression artifact reduction,15
1046,computational phenotyping,15
1047,facial action unit detection,15
1048,discourse segmentation,15
1049,point clouds,15
1050,zero shot object detection,15
1051,blind face restoration,15
1052,meeting summarization,14
1053,person identification,14
1054,goal oriented dialogue systems,14
1055,group activity recognition,14
1056,3d point cloud linear classification,14
1057,deformable medical image registration,14
1058,image smoothing,14
1059,intrinsic image decomposition,14
1060,image similarity search,14
1061,landmark recognition,14
1062,dynamic link prediction,14
1063,underwater image restoration,14
1064,industrial robots,14
1065,video alignment,14
1066,image deconvolution,14
1067,myocardial infarction detection,14
1068,sql to text,14
1069,text attribute transfer,14
1070,image stitching,14
1071,short text clustering,14
1072,human mesh recovery,14
1073,sar image despeckling,14
1074,skin cancer classification,14
1075,cross lingual question answering,14
1076,handwriting generation,14
1077,emotion cause pair extraction,14
1078,action unit detection,14
1079,deception detection,14
1080,protein function prediction,14
1081,instrument recognition,14
1082,human dynamics,14
1083,multi task audio source seperation,14
1084,diachronic word embeddings,14
1085,sentence segmentation,13
1086,automatic machine learning model selection,13
1087,news summarization,13
1088,point cloud retrieval,13
1089,interactive video object segmentation,13
1090,inductive knowledge graph completion,13
1091,grayscale image denoising,13
1092,self knowledge distillation,13
1093,few shot ner,13
1094,sound event localization and detection,13
1095,model discovery,13
1096,lexical normalization,13
1097,supervised dimensionality reduction,13
1098,irregular text recognition,13
1099,image manipulation detection,13
1100,medical image retrieval,13
1101,robust speech recognition,13
1102,music genre recognition,13
1103,sentence ordering,13
1104,art analysis,13
1105,multi label zero shot learning,13
1106,unsupervised 3d point cloud linear evaluation,13
1107,brain decoding,13
1108,audio signal processing,13
1109,audio super resolution,13
1110,image steganography,13
1111,layout to image generation,13
1112,motion detection,13
1113,video saliency prediction,13
1114,one shot segmentation,13
1115,unsupervised extractive summarization,13
1116,text based person retrieval,13
1117,co salient object detection,13
1118,stereo lidar fusion,13
1119,iris segmentation,13
1120,3d face animation,13
1121,diabetic retinopathy detection,13
1122,medical code prediction,13
1123,domain adaptive person re identification,13
1124,relationship extraction (distant supervised),12
1125,electromyography (emg),12
1126,license plate detection,12
1127,weakly supervised instance segmentation,12
1128,short text conversation,12
1129,metaheuristic optimization,12
1130,image outpainting,12
1131,online clustering,12
1132,atari games 100k,12
1133,3d absolute human pose estimation,12
1134,colorectal polyps characterization,12
1135,image animation,12
1136,joint multilingual sentence representations,12
1137,multi agent path finding,12
1138,hyperspectral image super resolution,12
1139,disjoint 10 1,12
1140,temporal information extraction,12
1141,portrait segmentation,12
1142,depression detection,12
1143,3d aware image synthesis,12
1144,3d object reconstruction from a single image,12
1145,clone detection,12
1146,room layout estimation,12
1147,disjoint 15 1,12
1148,skills assessment,12
1149,contour detection,12
1150,medical report generation,12
1151,overlapped 10 1,12
1152,stock trend prediction,12
1153,abstractive dialogue summarization,12
1154,generalizable person re identification,12
1155,animal pose estimation,12
1156,disjoint 15 5,12
1157,voice anti spoofing,11
1158,cross domain named entity recognition,11
1159,domain 11 1,11
1160,zero shot image classification,11
1161,overlapped 15 5,11
1162,spatio temporal action localization,11
1163,domain 11 5,11
1164,acrobot,11
1165,multiple sequence alignment,11
1166,multiple people tracking,11
1167,automated essay scoring,11
1168,non intrusive load monitoring,11
1169,domain 1 1,11
1170,traffic sign detection,11
1171,face presentation attack detection,11
1172,overlapped 15 1,11
1173,compositional zero shot learning,11
1174,link property prediction,11
1175,font generation,11
1176,data free quantization,11
1177,3d shape retrieval,11
1178,3d shape modeling,11
1179,drone navigation,11
1180,gesture generation,11
1181,extract aspect,11
1182,music auto tagging,11
1183,authorship verification,11
1184,audio visual speech recognition,11
1185,blind image deblurring,11
1186,code documentation generation,11
1187,dialog relation extraction,11
1188,photo retouching,11
1189,temporal knowledge graph completion,11
1190,band gap,11
1191,occlusion handling,11
1192,question rewriting,11
1193,review generation,11
1194,multi view subspace clustering,11
1195,end to end dialogue modelling,11
1196,semantic image matting,11
1197,empathetic response generation,11
1198,single image haze removal,11
1199,chinese sentence pair classification,11
1200,image level supervised instance segmentation,11
1201,human pose forecasting,11
1202,cyber attack detection,10
1203,camera shot boundary detection,10
1204,zero shot text search,10
1205,symmetry detection,10
1206,set matching,10
1207,sign language translation,10
1208,highlight detection,10
1209,unbiased scene graph generation,10
1210,electron microscopy image segmentation,10
1211,3d point cloud matching,10
1212,semi supervised medical image segmentation,10
1213,multi hop reading comprehension,10
1214,sentence pair modeling,10
1215,affordance detection,10
1216,recipe generation,10
1217,multi target regression,10
1218,breast cancer histology image classification,10
1219,crop yield prediction,10
1220,aesthetics quality assessment,10
1221,heart rate estimation,10
1222,person recognition,10
1223,object slam,10
1224,variational monte carlo,10
1225,automatic sleep stage classification,10
1226,acoustic unit discovery,10
1227,activity recognition in videos,10
1228,camera relocalization,10
1229,inductive relation prediction,10
1230,chinese sentiment analysis,10
1231,value prediction,10
1232,cloud removal,10
1233,learning semantic representations,10
1234,deformable object manipulation,10
1235,grammatical error detection,10
1236,unsupervised facial landmark detection,10
1237,algorithmic trading,10
1238,long tail learning with class descriptors,10
1239,document level event extraction,10
1240,one shot object detection,10
1241,snes games,10
1242,road damage detection,10