计算机科学
还原(数学)
人工智能
计算机视觉
数学
几何学
作者
Leqi Shen,Guoqiang Gong,Tianxiang Hao,Tao He,Yifeng Zhang,Pengzhang Liu,Sicheng Zhao,Jungong Han,Guiguang Ding
出处
期刊:Proceedings
[Institute of Electrical and Electronics Engineers]
日期:2025-06-10
卷期号:: 19702-19712
被引量:16
标识
DOI:10.1109/cvpr52734.2025.01835
摘要
The parameter-efficient adaptation of the image-text pre-training model CLIP for video-text retrieval is a prominent area of research. While CLIP is focused on image-level vision-language matching, video-text retrieval demands comprehensive understanding at the video level. Three key discrepancies emerge in the transfer from image-level to video-level: vision, language, and alignment. However, existing methods mainly focus on vision while neglecting language and alignment. In this paper, we propose Discrepancy Reduction in Vision, Language, and Alignment (DiscoVLA), which simultaneously mitigates all three discrepancies. Specifically, we introduce Image-Video Features Fusion to integrate image-level and video-level features, effectively tackling both vision and language discrepancies. Additionally, we generate pseudo image captions to learn fine-grained image-level alignment. To mitigate alignment discrepancies, we propose Image-To-Video Alignment Distillation, which leverages image-level alignment knowledge to enhance video-level alignment. Extensive experiments demonstrate the superiority of our DiscoVLA. In particular, on MSRVTT with CLIP (ViT-B/16), DiscoVLA outperforms previous methods by 2.2% R@1 and 7.5% R@sum. The code is available at https://github.com/LunarShen/DsicoVLA.
科研通智能强力驱动
Strongly Powered by AbleSci AI