ContextRefine-CLIP for EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge 2025
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_ | 1866916791935041536 |
|---|---|
| author | He, Jing Wang, Yiqing Li, Lingling Zhang, Kexin Chen, Puhua |
| author_facet | He, Jing Wang, Yiqing Li, Lingling Zhang, Kexin Chen, Puhua |
| contents | This report presents ContextRefine-CLIP (CR-CLIP), an efficient model for visual-textual multi-instance retrieval tasks. The approach is based on the dual-encoder AVION, on which we introduce a cross-modal attention flow module to achieve bidirectional dynamic interaction and refinement between visual and textual features to generate more context-aware joint representations. For soft-label relevance matrices provided in tasks such as EPIC-KITCHENS-100, CR-CLIP can work with Symmetric Multi-Similarity Loss to achieve more accurate semantic alignment and optimization using the refined features. Without using ensemble learning, the CR-CLIP model achieves 66.78mAP and 82.08nDCG on the EPIC-KITCHENS-100 public leaderboard, which significantly outperforms the baseline model and fully validates its effectiveness in cross-modal retrieval. The code will be released open-source on https://github.com/delCayr/ContextRefine-Clip |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_10550 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ContextRefine-CLIP for EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge 2025 He, Jing Wang, Yiqing Li, Lingling Zhang, Kexin Chen, Puhua Computer Vision and Pattern Recognition This report presents ContextRefine-CLIP (CR-CLIP), an efficient model for visual-textual multi-instance retrieval tasks. The approach is based on the dual-encoder AVION, on which we introduce a cross-modal attention flow module to achieve bidirectional dynamic interaction and refinement between visual and textual features to generate more context-aware joint representations. For soft-label relevance matrices provided in tasks such as EPIC-KITCHENS-100, CR-CLIP can work with Symmetric Multi-Similarity Loss to achieve more accurate semantic alignment and optimization using the refined features. Without using ensemble learning, the CR-CLIP model achieves 66.78mAP and 82.08nDCG on the EPIC-KITCHENS-100 public leaderboard, which significantly outperforms the baseline model and fully validates its effectiveness in cross-modal retrieval. The code will be released open-source on https://github.com/delCayr/ContextRefine-Clip |
| title | ContextRefine-CLIP for EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge 2025 |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.10550 |