Rethinking Weakly-supervised Video Temporal Grounding From a Game Perspective
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911717934497792 |
|---|---|
| author | Fang, Xiang Xiong, Zeyu Fang, Wanlong Qu, Xiaoye Chen, Chen Dong, Jianfeng Tang, Keke Zhou, Pan Cheng, Yu Liu, Daizong |
| author_facet | Fang, Xiang Xiong, Zeyu Fang, Wanlong Qu, Xiaoye Chen, Chen Dong, Jianfeng Tang, Keke Zhou, Pan Cheng, Yu Liu, Daizong |
| contents | This paper addresses the challenging task of weakly-supervised video temporal grounding. Existing approaches are generally based on the moment proposal selection framework that utilizes contrastive learning and reconstruction paradigm for scoring the pre-defined moment proposals. Although they have achieved significant progress, we argue that their current frameworks have overlooked two indispensable issues: 1) Coarse-grained cross-modal learning: previous methods solely capture the global video-level alignment with the query, failing to model the detailed consistency between video frames and query words for accurately grounding the moment boundaries. 2) Complex moment proposals: their performance severely relies on the quality of proposals, which are also time-consuming and complicated for selection. To this end, in this paper, we make the first attempt to tackle this task from a novel game perspective, which effectively learns the uncertain relationship between each vision-language pair with diverse granularity and flexible combination for multi-level cross-modal interaction.Specifically, we creatively model each video frame and query word as game players with multivariate cooperative game theory to learn their contribution to the cross-modal similarity score. By quantifying the trend of frame-word cooperation within a coalition via the game-theoretic interaction, we are able to value all uncertain but possible correspondence between frames and words. Finally, instead of using moment proposals, we utilize the learned query-guided frame-wise scores for better moment localization.Experiments show that our method achieves superior performance on both Charades-STA and ActivityNet Caption datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_26441 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Rethinking Weakly-supervised Video Temporal Grounding From a Game Perspective Fang, Xiang Xiong, Zeyu Fang, Wanlong Qu, Xiaoye Chen, Chen Dong, Jianfeng Tang, Keke Zhou, Pan Cheng, Yu Liu, Daizong Computer Vision and Pattern Recognition Artificial Intelligence This paper addresses the challenging task of weakly-supervised video temporal grounding. Existing approaches are generally based on the moment proposal selection framework that utilizes contrastive learning and reconstruction paradigm for scoring the pre-defined moment proposals. Although they have achieved significant progress, we argue that their current frameworks have overlooked two indispensable issues: 1) Coarse-grained cross-modal learning: previous methods solely capture the global video-level alignment with the query, failing to model the detailed consistency between video frames and query words for accurately grounding the moment boundaries. 2) Complex moment proposals: their performance severely relies on the quality of proposals, which are also time-consuming and complicated for selection. To this end, in this paper, we make the first attempt to tackle this task from a novel game perspective, which effectively learns the uncertain relationship between each vision-language pair with diverse granularity and flexible combination for multi-level cross-modal interaction.Specifically, we creatively model each video frame and query word as game players with multivariate cooperative game theory to learn their contribution to the cross-modal similarity score. By quantifying the trend of frame-word cooperation within a coalition via the game-theoretic interaction, we are able to value all uncertain but possible correspondence between frames and words. Finally, instead of using moment proposals, we utilize the learned query-guided frame-wise scores for better moment localization.Experiments show that our method achieves superior performance on both Charades-STA and ActivityNet Caption datasets. |
| title | Rethinking Weakly-supervised Video Temporal Grounding From a Game Perspective |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2605.26441 |