Weakly-Supervised Temporal Action Localization Through Local-Global Background Modeling
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
Code (0)
등록된 구현이 없습니다.
Tasks
Action LocalizationTemporal Action LocalizationWeakly-supervised LearningWeakly-supervised Temporal Action LocalizationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Transferable Knowledge-Based Multi-Granularity Aggregation Network for Temporal Action Localization: Submission to ActivityNet Challenge 2021
This technical report presents an overview of our solution used in the submission to 2021 HACS Temporal Action Localization Challenge on both Supervised Learning Track and Weakly-Supervised Learning Track. Temporal Actio…
Action LocalizationTemporal Action LocalizationTransfer LearningWeakly-supervised Learning+1Learning Temporal Co-Attention Models for Unsupervised Video Action Localization
Temporal action localization (TAL) in untrimmed videos recently receives tremendous research enthusiasm. To our best knowledge, this is the first attempt in the literature to explore this task under an unsupervised setti…
Action LocalizationClusteringTemporal Action LocalizationTripletWeakly Supervised Action Localization by Sparse Temporal Pooling Network
We propose a weakly supervised temporal action localization algorithm on untrimmed videos using convolutional neural networks. Our algorithm learns from video-level class labels and predicts temporal intervals of human a…
Action ClassificationAction LocalizationTemporal Action LocalizationTemporal Localization+2PivoTAL: Prior-Driven Supervision for Weakly-Supervised Temporal Action Localization
Weakly-supervised Temporal Action Localization (WTAL) attempts to localize the actions in untrimmed videos using only video-level supervision. Most recent works approach WTAL from a localization-by-classification per…
Action LocalizationTemporal Action LocalizationWeakly Supervised Action LocalizationWeakly-supervised Temporal Action LocalizationWeakly-Supervised Temporal Action Localization by Inferring Salient Snippet-Feature
Weakly-supervised temporal action localization aims to locate action regions and identify action categories in untrimmed videos simultaneously by taking only video-level labels as the supervision. Pseudo label generation…
Action LocalizationPseudo LabelTemporal Action LocalizationWeakly-supervised Temporal Action Localization