Deep feature enhancing and selecting network for weakly supervised temporal action localization

Abstract Weakly supervised temporal action localization is a challenging computer vision problem which uses only video-level labels and lacks of the supervision of temporal annotations. In this task, the majority of existing methods usually identify the most discriminative snippets and ignore other relevant snippets. To address this problem, we propose a deep feature enhancing and selecting network. It generates multiple masks for both capturing the more complete temporal interval of actions and keeping its high classification accuracy. After that, we further propose a novel selection strategy to balance the influence of multiple masks and improve the model performance. In the experiments, we evaluate the proposed method on the THUMOS’14 and ActivityNet datasets, and the results show the effectiveness of our approach for weakly supervised action localization.