Weakly Supervised Anomaly Detection in Videos Considering the Openness of Events

doi:10.1109/TITS.2022.3174088

	Weakly Supervised Anomaly Detection in Videos Considering the Openness of Events
	Zhang, Chen 1,2; Li, Guorong 3; Xu, Qianqian 4; Zhang, Xinfeng 3; Su, Li 3; Huang, Qingming 3
	2022-05-13
发表期刊	IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
ISSN	1524-9050
页码	13
摘要	Although various weakly supervised anomaly detection methods have been proposed in recent years, generalization of anomaly detection is still not well-explored. Existing weakly supervised methods usually use normal and abnormal events to pose anomaly detection as a regression problem. However, defining concepts that encompass all possible normal and abnormal event patterns is nearly unrealistic, so the anomaly detection model is likely to face both open normal and abnormal events in practical applications. We find some weakly supervised anomaly detection methods suffer from performance degradation when faced with open events due to their poor generalization. To tackle this issue, we propose a two-branch weakly supervised approach, which can improve the anomaly detection performance of open events without affecting the performance of the seen events. Specifically, considering that the pattern of open events is different from that of seen events, we design a Test Data Analyzer (TDA) that determines whether the test video features belong to seen or open data and argue for separate treatment for them. For the seen data, a classifier trained by multiple instance learning is used to predict anomaly scores. For the open data, we design an anomaly detection model via meta-learning named Meta-Learning Anomaly Detection (MLAD), which can directly determine whether open data is abnormal without updating model parameters. In detail, MLAD synthesizes pseudo-seen data and pseudo-open data so that the model can learn to detect anomalies in open data by transferring the knowledge of seen data. Experimental results validate the effectiveness of our proposed method.
关键词	Anomaly detection Videos Open data Data models Training Feature extraction Predictive models Anomaly detection surveillance videos openness meta-learning
DOI	10.1109/TITS.2022.3174088
收录类别	SCI
语种	英语
资助项目	Italy-China Collaboration Project Talent[2018YFE0118400] ; National Natural Science Foundation of China[61836002] ; National Natural Science Foundation of China[61976069] ; National Natural Science Foundation of China[61872333] ; National Natural Science Foundation of China[61931008] ; Youth Innovation Promotion Association CAS ; Fundamental Research Funds for Central Universities
WOS研究方向	Engineering ; Transportation
WOS类目	Engineering, Civil ; Engineering, Electrical & Electronic ; Transportation Science & Technology
WOS记录号	WOS:000799606400001
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：13[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/19569
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Li, Guorong
作者单位	1.Chinese Acad Sci, State Key Lab Informat Security, Inst Informat Engn, Beijing 100093, Peoples R China 2.Univ Chinese Acad Sci, Sch Cyber Secur, Beijing 100049, Peoples R China 3.Univ Chinese Acad Sci, Sch Comp Sci & Technol, Beijing 100049, Peoples R China 4.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Zhang, Chen,Li, Guorong,Xu, Qianqian,et al. Weakly Supervised Anomaly Detection in Videos Considering the Openness of Events[J]. IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS,2022:13.
APA	Zhang, Chen,Li, Guorong,Xu, Qianqian,Zhang, Xinfeng,Su, Li,&Huang, Qingming.(2022).Weakly Supervised Anomaly Detection in Videos Considering the Openness of Events.IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS,13.
MLA	Zhang, Chen,et al."Weakly Supervised Anomaly Detection in Videos Considering the Openness of Events".IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2022):13.