Papers by Ishan Gaur
ColorSwap: A Color and Word Order Dataset for Multimodal Evaluation (2024.findings-acl)
Copied to clipboard
| Challenge: | Recent work reveals that vision and language models struggle to comprehend fine grained distinctions in images. |
| Approach: | They propose a dataset to assess multimodal models' ability to match objects with their colors. |
| Outcome: | The proposed model performs well in visual questionanswering, text-to-image generation and word-order understanding tasks. |