Uncertainty-aware weakly supervised temporal action localization with knowledge selection

Weakly-Supervised Temporal Action Localization (WS-TAL) aims to localize actions in untrimmed videos using only video-level labels. The core challenge is the lack of fine-grained annotations, which leads to high prediction uncertainty and confusion between actions and background. To address this, we propose an Uncertainty-Aware and Knowledge-Selection (UAKS) approach. Specifically, we integrate two uncertainty estimation strategies to cooperatively optimize the model and leverage uncertainty to guide external knowledge selection. First, evidential learning estimates model uncertainty, generating more confident predictions via regularization. Second, probabilistic distribution learning captures data uncertainty. Both uncertainties jointly guide model optimization. Additionally, uncertainty-driven knowledge selection enables the efficient utilization of external knowledge under weak supervision. Experiments show that our method improves accuracy and robustness, with 12.9% and 2% accuracy improvements on THUMOS and ActivityNet v1.3 datasets respectively, demonstrating the potential of uncertainty modeling in WS-TAL.