ChatSearch: a Dataset and a Generative Retrieval Model for General Conversational Image Retrieval
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911659357896704 |
|---|---|
| author | Zhao, Zijia Guo, Longteng Yue, Tongtian Hu, Erdong Shao, Shuai Yuan, Zehuan Huang, Hua Liu, Jing |
| author_facet | Zhao, Zijia Guo, Longteng Yue, Tongtian Hu, Erdong Shao, Shuai Yuan, Zehuan Huang, Hua Liu, Jing |
| contents | In this paper, we investigate the task of general conversational image retrieval on open-domain images. The objective is to search for images based on interactive conversations between humans and computers. To advance this task, we curate a dataset called ChatSearch. This dataset includes a multi-round multimodal conversational context query for each target image, thereby requiring the retrieval system to find the accurate image from database. Simultaneously, we propose a generative retrieval model named ChatSearcher, which is trained end-to-end to accept/produce interleaved image-text inputs/outputs. ChatSearcher exhibits strong capability in reasoning with multimodal context and can leverage world knowledge to yield visual retrieval results. It demonstrates superior performance on the ChatSearch dataset and also achieves competitive results on other image retrieval tasks and visual conversation tasks. We anticipate that this work will inspire further research on interactive multimodal retrieval systems. Our dataset will be available at https://github.com/joez17/ChatSearch. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_18715 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ChatSearch: a Dataset and a Generative Retrieval Model for General Conversational Image Retrieval Zhao, Zijia Guo, Longteng Yue, Tongtian Hu, Erdong Shao, Shuai Yuan, Zehuan Huang, Hua Liu, Jing Computer Vision and Pattern Recognition In this paper, we investigate the task of general conversational image retrieval on open-domain images. The objective is to search for images based on interactive conversations between humans and computers. To advance this task, we curate a dataset called ChatSearch. This dataset includes a multi-round multimodal conversational context query for each target image, thereby requiring the retrieval system to find the accurate image from database. Simultaneously, we propose a generative retrieval model named ChatSearcher, which is trained end-to-end to accept/produce interleaved image-text inputs/outputs. ChatSearcher exhibits strong capability in reasoning with multimodal context and can leverage world knowledge to yield visual retrieval results. It demonstrates superior performance on the ChatSearch dataset and also achieves competitive results on other image retrieval tasks and visual conversation tasks. We anticipate that this work will inspire further research on interactive multimodal retrieval systems. Our dataset will be available at https://github.com/joez17/ChatSearch. |
| title | ChatSearch: a Dataset and a Generative Retrieval Model for General Conversational Image Retrieval |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2410.18715 |