Weakly Supervised Gaussian Networks for Action Detection

Basura Fernando, Cheston Tan, Hakan Bilen; Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2020, pp. 537-546

Abstract


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 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.

Related Material


[pdf] [video]
[bibtex]
@InProceedings{Fernando_2020_WACV,
author = {Fernando, Basura and Tan, Cheston and Bilen, Hakan},
title = {Weakly Supervised Gaussian Networks for Action Detection},
booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
month = {March},
year = {2020}
}