DDG-Net: Discriminability-Driven Graph Network for Weakly-supervised Temporal Action Localization
This work improves action localization in videos for applications like surveillance and video analysis, but it is incremental as it builds on existing feature enhancement methods.
The paper tackles the problem of weakly-supervised temporal action localization by addressing ambiguous information that reduces discriminability, proposing DDG-Net to model ambiguous and discriminative snippets with connections and a feature consistency loss, achieving new state-of-the-art results on THUMOS14 and ActivityNet1.2 benchmarks.
Weakly-supervised temporal action localization (WTAL) is a practical yet challenging task. Due to large-scale datasets, most existing methods use a network pretrained in other datasets to extract features, which are not suitable enough for WTAL. To address this problem, researchers design several modules for feature enhancement, which improve the performance of the localization module, especially modeling the temporal relationship between snippets. However, all of them neglect the adverse effects of ambiguous information, which would reduce the discriminability of others. Considering this phenomenon, we propose Discriminability-Driven Graph Network (DDG-Net), which explicitly models ambiguous snippets and discriminative snippets with well-designed connections, preventing the transmission of ambiguous information and enhancing the discriminability of snippet-level representations. Additionally, we propose feature consistency loss to prevent the assimilation of features and drive the graph convolution network to generate more discriminative representations. Extensive experiments on THUMOS14 and ActivityNet1.2 benchmarks demonstrate the effectiveness of DDG-Net, establishing new state-of-the-art results on both datasets. Source code is available at \url{https://github.com/XiaojunTang22/ICCV2023-DDGNet}.