Exploring the Temporal Consistency for Point-Level Weakly-Supervised Temporal Action Localization
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_ | 1866914308065067008 |
|---|---|
| author | Ma, Yunchuan Qing, Laiyun Li, Guorong Liu, Yuqing Qi, Yuankai Huang, Qingming |
| author_facet | Ma, Yunchuan Qing, Laiyun Li, Guorong Liu, Yuqing Qi, Yuankai Huang, Qingming |
| contents | Point-supervised Temporal Action Localization (PTAL) adopts a lightly frame-annotated paradigm (\textit{i.e.}, labeling only a single frame per action instance) to train a model to effectively locate action instances within untrimmed videos. Most existing approaches design the task head of models with only a point-supervised snippet-level classification, without explicit modeling of understanding temporal relationships among frames of an action. However, understanding the temporal relationships of frames is crucial because it can help a model understand how an action is defined and therefore benefits localizing the full frames of an action. To this end, in this paper, we design a multi-task learning framework that fully utilizes point supervision to boost the model's temporal understanding capability for action localization. Specifically, we design three self-supervised temporal understanding tasks: (i) Action Completion, (ii) Action Order Understanding, and (iii) Action Regularity Understanding. These tasks help a model understand the temporal consistency of actions across videos. To the best of our knowledge, this is the first attempt to explicitly explore temporal consistency for point supervision action localization. Extensive experimental results on four benchmark datasets demonstrate the effectiveness of the proposed method compared to several state-of-the-art approaches. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_05718 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Exploring the Temporal Consistency for Point-Level Weakly-Supervised Temporal Action Localization Ma, Yunchuan Qing, Laiyun Li, Guorong Liu, Yuqing Qi, Yuankai Huang, Qingming Computer Vision and Pattern Recognition Point-supervised Temporal Action Localization (PTAL) adopts a lightly frame-annotated paradigm (\textit{i.e.}, labeling only a single frame per action instance) to train a model to effectively locate action instances within untrimmed videos. Most existing approaches design the task head of models with only a point-supervised snippet-level classification, without explicit modeling of understanding temporal relationships among frames of an action. However, understanding the temporal relationships of frames is crucial because it can help a model understand how an action is defined and therefore benefits localizing the full frames of an action. To this end, in this paper, we design a multi-task learning framework that fully utilizes point supervision to boost the model's temporal understanding capability for action localization. Specifically, we design three self-supervised temporal understanding tasks: (i) Action Completion, (ii) Action Order Understanding, and (iii) Action Regularity Understanding. These tasks help a model understand the temporal consistency of actions across videos. To the best of our knowledge, this is the first attempt to explicitly explore temporal consistency for point supervision action localization. Extensive experimental results on four benchmark datasets demonstrate the effectiveness of the proposed method compared to several state-of-the-art approaches. |
| title | Exploring the Temporal Consistency for Point-Level Weakly-Supervised Temporal Action Localization |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.05718 |