Weakly-Supervised Temporal Action Localization (WS-TAL) task aims to recognize and localize temporal starts and ends of action instances in an untrimmed video with only video-level label supervision. Due to lack of negative samples of background category, it is difficult for the network to separate foreground and background, resulting in poor detection performance. In this report, we present our 2021 HACS Challenge - Weakly-supervised Learning Track solution that based on BaSNet to address above problem. Specifically, we first adopt pre-trained CSN, Slowfast, TDN, and ViViT as feature extractors to get feature sequences. Then our proposed Local-Global Background Modeling Network (LGBM-Net) is trained to localize instances by using only video-level labels based on Multi-Instance Learning (MIL). Finally, we ensemble multiple models to get the final detection results and reach 22.45% mAP on the test set
@article{arxiv.2106.11811,
title = {Weakly-Supervised Temporal Action Localization Through Local-Global Background Modeling},
author = {Xiang Wang and Zhiwu Qing and Ziyuan Huang and Yutong Feng and Shiwei Zhang and Jianwen Jiang and Mingqian Tang and Yuanjie Shao and Nong Sang},
journal= {arXiv preprint arXiv:2106.11811},
year = {2021}
}