Update README.md
Browse files
README.md
CHANGED
|
@@ -122,7 +122,7 @@ In all of the following evaluations, ViPE consistently demonstrates its robustne
|
|
| 122 |
- Image-text Retrieval on the [HAIVMet dataset](https://aclanthology.org/2023.findings-acl.465.pdf)
|
| 123 |
- Emotion visualizations: How well does ViPE transfer emotionally charged tweets into a depictable description of a scene in comparison with
|
| 124 |
ChatGPT. The [Emotion dataset](https://huggingface.co/datasets/dair-ai/emotion) is utilized.
|
| 125 |
-
- ***Human evaluations
|
| 126 |
- We conducted a user study involving 30 native English-speaking participants aged between 20 and 40. Participants were
|
| 127 |
presented with 3 images and a metaphor from the HAIVMet dataset. They were asked to select the images that matches the metaphor the best.
|
| 128 |
The images were generated using prompts from ViPE, ChatGPT, and human experts (HAIVMet).
|
|
|
|
| 122 |
- Image-text Retrieval on the [HAIVMet dataset](https://aclanthology.org/2023.findings-acl.465.pdf)
|
| 123 |
- Emotion visualizations: How well does ViPE transfer emotionally charged tweets into a depictable description of a scene in comparison with
|
| 124 |
ChatGPT. The [Emotion dataset](https://huggingface.co/datasets/dair-ai/emotion) is utilized.
|
| 125 |
+
- ***Human evaluations***
|
| 126 |
- We conducted a user study involving 30 native English-speaking participants aged between 20 and 40. Participants were
|
| 127 |
presented with 3 images and a metaphor from the HAIVMet dataset. They were asked to select the images that matches the metaphor the best.
|
| 128 |
The images were generated using prompts from ViPE, ChatGPT, and human experts (HAIVMet).
|