Weakly Supervised Gaussian Networks for Action Detection
This addresses the challenge of expensive manual supervision in action detection for computer vision applications, though it is incremental as it builds on existing weakly supervised approaches.
The paper tackles the problem of detecting temporal extents of human actions in videos by proposing WSGN, a weakly supervised method that uses only video-level labels instead of expensive frame-level annotations, achieving results close to supervised methods on THUMOS14 and Charades benchmarks.
Detecting temporal extents of human actions in videos is a challenging computer vision problem that requires detailed manual supervision including frame-level labels. This expensive annotation process limits deploying action detectors to a limited number of categories. We propose a novel method, called WSGN, that learns to detect actions from \emph{weak supervision}, using only video-level labels. WSGN learns to exploit both video-specific and dataset-wide statistics to predict relevance of each frame to an action category. This strategy leads to significant gains in action detection for two standard benchmarks THUMOS14 and Charades. Our method obtains excellent results compared to state-of-the-art methods that uses similar features and loss functions on THUMOS14 dataset. Similarly, our weakly supervised method is only 0.3% mAP behind a state-of-the-art supervised method on challenging Charades dataset for action localization.