Enhanced Partially Relevant Video Retrieval through Inter- and Intra-Sample Analysis with Coherence Prediction
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912733401710592 |
|---|---|
| author | Ren, Junlong Zhang, Gangjian Hu, Yu Shu, Jian Xiong, Hui Wang, Hao |
| author_facet | Ren, Junlong Zhang, Gangjian Hu, Yu Shu, Jian Xiong, Hui Wang, Hao |
| contents | Partially Relevant Video Retrieval (PRVR) aims to retrieve the target video that is partially relevant to the text query. The primary challenge in PRVR arises from the semantic asymmetry between textual and visual modalities, as videos often contain substantial content irrelevant to the query. Existing methods coarsely align paired videos and text queries to construct the semantic space, neglecting the critical cross-modal dual nature inherent in this task: inter-sample correlation and intra-sample redundancy. To this end, we propose a novel PRVR framework to systematically exploit these two characteristics. Our framework consists of three core modules. First, the Inter Correlation Enhancement (ICE) module captures inter-sample correlation by identifying semantically similar yet unpaired text queries and video moments, combining them to form pseudo-positive pairs for more robust semantic space construction. Second, the Intra Redundancy Mining (IRM) module mitigates intra-sample redundancy by mining redundant moment features and distinguishing them from query-relevant moments, encouraging the model to learn more discriminative representations. Finally, to reinforce these modules, we introduce the Temporal Coherence Prediction (TCP) module, enhancing discrimination of fine-grained moment-level semantics by training the model to predict the original temporal order of randomly shuffled video sequences. Extensive experiments demonstrate the superiority of our method, achieving state-of-the-art results. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_19637 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Enhanced Partially Relevant Video Retrieval through Inter- and Intra-Sample Analysis with Coherence Prediction Ren, Junlong Zhang, Gangjian Hu, Yu Shu, Jian Xiong, Hui Wang, Hao Computer Vision and Pattern Recognition Partially Relevant Video Retrieval (PRVR) aims to retrieve the target video that is partially relevant to the text query. The primary challenge in PRVR arises from the semantic asymmetry between textual and visual modalities, as videos often contain substantial content irrelevant to the query. Existing methods coarsely align paired videos and text queries to construct the semantic space, neglecting the critical cross-modal dual nature inherent in this task: inter-sample correlation and intra-sample redundancy. To this end, we propose a novel PRVR framework to systematically exploit these two characteristics. Our framework consists of three core modules. First, the Inter Correlation Enhancement (ICE) module captures inter-sample correlation by identifying semantically similar yet unpaired text queries and video moments, combining them to form pseudo-positive pairs for more robust semantic space construction. Second, the Intra Redundancy Mining (IRM) module mitigates intra-sample redundancy by mining redundant moment features and distinguishing them from query-relevant moments, encouraging the model to learn more discriminative representations. Finally, to reinforce these modules, we introduce the Temporal Coherence Prediction (TCP) module, enhancing discrimination of fine-grained moment-level semantics by training the model to predict the original temporal order of randomly shuffled video sequences. Extensive experiments demonstrate the superiority of our method, achieving state-of-the-art results. |
| title | Enhanced Partially Relevant Video Retrieval through Inter- and Intra-Sample Analysis with Coherence Prediction |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.19637 |