ACSNet: Action-Context Separation Network for Weakly Supervised Temporal Action Localization
About
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.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Temporal Action Localization | THUMOS14 (test) | AP @ IoU=0.532.4 | 319 | |
| Temporal Action Localization | ActivityNet 1.3 (val) | AP@0.536.3 | 257 | |
| Temporal Action Localization | ActivityNet 1.2 (val) | mAP@IoU 0.540.1 | 110 | |
| Temporal Action Localization | THUMOS 2014 | mAP@0.3051.4 | 93 | |
| Temporal Action Localization | ActivityNet v1.3 (test) | mAP @ IoU=0.536.3 | 47 | |
| Temporal Action Localization | ActivityNet 1.3 | Average mAP23.9 | 32 |