English

ACSNet: Action-Context Separation Network for Weakly Supervised Temporal Action Localization

Computer Vision and Pattern Recognition 2021-03-30 v1

Abstract

The object of Weakly-supervised Temporal Action Localization (WS-TAL) is to localize all action instances in an untrimmed video with only video-level supervision. Due to the lack of frame-level annotations during training, current WS-TAL methods rely on attention mechanisms to localize the foreground snippets or frames that contribute to the video-level classification task. This strategy frequently confuse context with the actual action, in the localization result. Separating action and context is a core problem for precise WS-TAL, but it is very challenging and has been largely ignored in the literature. In this paper, we introduce an Action-Context Separation Network (ACSNet) that explicitly takes into account context for accurate action localization. It consists of two branches (i.e., the Foreground-Background branch and the Action-Context branch). The Foreground- Background branch first distinguishes foreground from background within the entire video while the Action-Context branch further separates the foreground as action and context. We associate video snippets with two latent components (i.e., a positive component and a negative component), and their different combinations can effectively characterize foreground, action and context. Furthermore, we introduce extended labels with auxiliary context categories to facilitate the learning of action-context separation. Experiments on THUMOS14 and ActivityNet v1.2/v1.3 datasets demonstrate the ACSNet outperforms existing state-of-the-art WS-TAL methods by a large margin.

Keywords

Cite

@article{arxiv.2103.15088,
  title  = {ACSNet: Action-Context Separation Network for Weakly Supervised Temporal Action Localization},
  author = {Ziyi Liu and Le Wang and Qilin Zhang and Wei Tang and Junsong Yuan and Nanning Zheng and Gang Hua},
  journal= {arXiv preprint arXiv:2103.15088},
  year   = {2021}
}

Comments

Accepted by the 35th AAAI Conference on Artificial Intelligence (AAAI 2021)

R2 v1 2026-06-24T00:37:17.843Z