Revisiting Uncertainty: On Evidential Learning for Partially Relevant Video Retrieval
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917467838742528 |
|---|---|
| author | Li, Jun Lai, Peifeng Lou, Xuhang Wang, Jinpeng Wang, Yuting Chen, Ke Wang, Yaowei Xia, Shu-Tao |
| author_facet | Li, Jun Lai, Peifeng Lou, Xuhang Wang, Jinpeng Wang, Yuting Chen, Ke Wang, Yaowei Xia, Shu-Tao |
| contents | Partially relevant video retrieval aims to retrieve untrimmed videos using text queries that describe only partial content. However, the inherent asymmetry between brief queries and rich video content inevitably introduces uncertainty into the retrieval process. In this setting, vague queries often induce semantic ambiguity across videos, a challenge that is further exacerbated by the sparse temporal supervision within videos, which fails to provide sufficient matching evidence. To address this, we propose Holmes, a hierarchical evidential learning framework that aggregates multi-granular cross-modal evidence to quantify and model uncertainty explicitly. At the inter-video level, similarity scores are interpreted as evidential support and modeled via a Dirichlet distribution. Based on the proposed three-fold principle, we perform fine-grained query identification, which then guides query-adaptive calibrated learning. At the intra-video level, to accumulate denser evidence, we formulate a soft query-clip alignment via flexible optimal transport with an adaptive dustbin, which alleviates sparse temporal supervision while suppressing spurious local responses. Extensive experiments demonstrate that Holmes outperforms state-of-the-art methods. Code is released at https://github.com/lijun2005/ICML26-Holmes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_06083 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Revisiting Uncertainty: On Evidential Learning for Partially Relevant Video Retrieval Li, Jun Lai, Peifeng Lou, Xuhang Wang, Jinpeng Wang, Yuting Chen, Ke Wang, Yaowei Xia, Shu-Tao Computer Vision and Pattern Recognition Information Retrieval Machine Learning Multimedia Partially relevant video retrieval aims to retrieve untrimmed videos using text queries that describe only partial content. However, the inherent asymmetry between brief queries and rich video content inevitably introduces uncertainty into the retrieval process. In this setting, vague queries often induce semantic ambiguity across videos, a challenge that is further exacerbated by the sparse temporal supervision within videos, which fails to provide sufficient matching evidence. To address this, we propose Holmes, a hierarchical evidential learning framework that aggregates multi-granular cross-modal evidence to quantify and model uncertainty explicitly. At the inter-video level, similarity scores are interpreted as evidential support and modeled via a Dirichlet distribution. Based on the proposed three-fold principle, we perform fine-grained query identification, which then guides query-adaptive calibrated learning. At the intra-video level, to accumulate denser evidence, we formulate a soft query-clip alignment via flexible optimal transport with an adaptive dustbin, which alleviates sparse temporal supervision while suppressing spurious local responses. Extensive experiments demonstrate that Holmes outperforms state-of-the-art methods. Code is released at https://github.com/lijun2005/ICML26-Holmes. |
| title | Revisiting Uncertainty: On Evidential Learning for Partially Relevant Video Retrieval |
| topic | Computer Vision and Pattern Recognition Information Retrieval Machine Learning Multimedia |
| url | https://arxiv.org/abs/2605.06083 |