Uncertainty-Aware Dual-Evidential Learning for Weakly-Supervised Temporal Action Localization

doi:10.1109/TPAMI.2023.3308571

	Uncertainty-Aware Dual-Evidential Learning for Weakly-Supervised Temporal Action Localization
	Chen, Mengyuan 1,2; Gao, Junyu1,2 ; Xu, Changsheng1,2,3
发表期刊	IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
ISSN	0162-8828
	2023-12-01
卷号	45 期号:12 页码:15896-15911
通讯作者	Xu, Changsheng(csxu@nlpr.ia.ac.cn)
摘要	Weakly-supervised temporal action localization (WTAL) aims to localize the action instances and recognize their categories with only video-level labels. Despite great progress, existing methods suffer from severe action-background ambiguity, which mainly arises from background noise and neglect of non-salient action snippets. To address this issue, we propose a generalized evidential deep learning (EDL) framework forWTAL, called Uncertainty-aware Dual-Evidential Learning (UDEL), which extends the traditional paradigm of EDL to adapt to the weakly-supervised multi-label classification goal with the guidance of epistemic and aleatoric uncertainties, of which the former comes from models lacking knowledge, while the latter comes from the inherent properties of samples themselves. Specifically, targeting excluding the undesirable background snippets, we fuse the video-level epistemic and aleatoric uncertainties to measure the interference of background noise to video-level prediction. Then, the snippet-level aleatoric uncertainty is further deduced for progressive mutual learning, which gradually focuses on the entire action instances in an "easy-to-hard" manner and encourages the snippet-level epistemic uncertainty to be complementary with the foreground attention scores. Extensive experiments show that UDEL achieves state-of-the-art performance on four public benchmarks. Our code is available in github/mengyuanchen2021/ UDEL.
关键词	Uncertainty Background noise Task analysis Location awareness Measurement uncertainty Interference Predictive models Weakly-supervised temporal action localization evidential deep learning uncertainty estimation
DOI	10.1109/TPAMI.2023.3308571
关键词[WOS]	ATTENTION
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Plan of China[2020AAA0106200] ; National Natural Science Foundation of China[62036012] ; National Natural Science Foundation of China[U21B2044] ; National Natural Science Foundation of China[62236008] ; National Natural Science Foundation of China[61721004] ; National Natural Science Foundation of China[62102415] ; National Natural Science Foundation of China[62072286] ; National Natural Science Foundation of China[62106262] ; National Natural Science Foundation of China[62002355] ; Beijing Natural Science Foundation[L201001] ; Open Research Projects of Zhejiang Lab[2022RC0AB02]
项目资助者	National Key Research and Development Plan of China ; National Natural Science Foundation of China ; Beijing Natural Science Foundation ; Open Research Projects of Zhejiang Lab
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:001130146400114
出版者	IEEE COMPUTER SOC
引用统计
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/55494
专题	多模态人工智能系统全国重点实验室
通讯作者	Xu, Changsheng
作者单位	1.Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 101408, Peoples R China 3.Peng Cheng Lab, Shenzhen 518055, Peoples R China
第一作者单位	中国科学院自动化研究所
通讯作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Chen, Mengyuan,Gao, Junyu,Xu, Changsheng. Uncertainty-Aware Dual-Evidential Learning for Weakly-Supervised Temporal Action Localization[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2023,45(12):15896-15911.
APA	Chen, Mengyuan,Gao, Junyu,&Xu, Changsheng.(2023).Uncertainty-Aware Dual-Evidential Learning for Weakly-Supervised Temporal Action Localization.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,45(12),15896-15911.
MLA	Chen, Mengyuan,et al."Uncertainty-Aware Dual-Evidential Learning for Weakly-Supervised Temporal Action Localization".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 45.12(2023):15896-15911.