DIR-TIR: Dialog-Iterative Refinement for Text-to-Image Retrieval
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918208218333184 |
|---|---|
| author | Zhen, Zongwei Zeng, Biqing |
| author_facet | Zhen, Zongwei Zeng, Biqing |
| contents | This paper addresses the task of interactive, conversational text-to-image retrieval.
Our DIR-TIR framework progressively refines the target image search through two specialized modules: the Dialog Refiner Module and the Image Refiner Module.
The Dialog Refiner actively queries users to extract essential information and generate increasingly precise descriptions of the target image.
Complementarily, the Image Refiner identifies perceptual gaps between generated images and user intentions, strategically reducing the visual-semantic discrepancy. By leveraging multi-turn dialogues, DIR-TIR provides superior controllability and fault tolerance compared to conventional single-query methods, significantly improving target image hit accuracy.
Comprehensive experiments across diverse image datasets demonstrate our dialogue-based approach substantially outperforms initial-description-only baselines, while the synergistic module integration achieves both higher retrieval precision and enhanced interactive experience. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_14449 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DIR-TIR: Dialog-Iterative Refinement for Text-to-Image Retrieval Zhen, Zongwei Zeng, Biqing Computer Vision and Pattern Recognition This paper addresses the task of interactive, conversational text-to-image retrieval. Our DIR-TIR framework progressively refines the target image search through two specialized modules: the Dialog Refiner Module and the Image Refiner Module. The Dialog Refiner actively queries users to extract essential information and generate increasingly precise descriptions of the target image. Complementarily, the Image Refiner identifies perceptual gaps between generated images and user intentions, strategically reducing the visual-semantic discrepancy. By leveraging multi-turn dialogues, DIR-TIR provides superior controllability and fault tolerance compared to conventional single-query methods, significantly improving target image hit accuracy. Comprehensive experiments across diverse image datasets demonstrate our dialogue-based approach substantially outperforms initial-description-only baselines, while the synergistic module integration achieves both higher retrieval precision and enhanced interactive experience. |
| title | DIR-TIR: Dialog-Iterative Refinement for Text-to-Image Retrieval |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.14449 |