Abnormal event detection by a weakly supervised temporal attention network
Abnormal event detection aims to automatically identify unusual events that do not comply with expectation. Recently, many methods have been proposed to obtain the temporal locations of abnormal events under various determined thresholds. However, the specific categories of abnormal events are mostl...
| Main Authors: | , , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/164312 |
| _version_ | 1811692740395663360 |
|---|---|
| author | Zheng, Xiangtao Zhang, Yichao Zheng, Yunpeng Luo, Fulin Lu, Xiaoqiang |
| author2 | School of Electrical and Electronic Engineering |
| author_facet | School of Electrical and Electronic Engineering Zheng, Xiangtao Zhang, Yichao Zheng, Yunpeng Luo, Fulin Lu, Xiaoqiang |
| author_sort | Zheng, Xiangtao |
| collection | NTU |
| description | Abnormal event detection aims to automatically identify unusual events that do not comply with expectation. Recently, many methods have been proposed to obtain the temporal locations of abnormal events under various determined thresholds. However, the specific categories of abnormal events are mostly neglect, which are important to help in monitoring agents to make decisions. In this study, a Temporal Attention Network (TANet) is proposed to capture both the specific categories and temporal locations of abnormal events in a weakly supervised manner. The TANet learns the anomaly score and specific category for each video segment with only video-level abnormal event labels. An event recognition module is exploited to predict the event scores for each video segment while a temporal attention module is proposed to learn a temporal attention value. Finally, to learn anomaly scores and specific categories, three constraints are considered: event category constraint, event separation constraint and temporal smoothness constraint. Experiments on the University of Central Florida Crime dataset demonstrate the effectiveness of the proposed method. |
| first_indexed | 2024-10-01T06:40:35Z |
| format | Journal Article |
| id | ntu-10356/164312 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T06:40:35Z |
| publishDate | 2023 |
| record_format | dspace |
| spelling | ntu-10356/1643122023-01-16T02:35:40Z Abnormal event detection by a weakly supervised temporal attention network Zheng, Xiangtao Zhang, Yichao Zheng, Yunpeng Luo, Fulin Lu, Xiaoqiang School of Electrical and Electronic Engineering Engineering::Electrical and electronic engineering Human Detection Video Analysis Abnormal event detection aims to automatically identify unusual events that do not comply with expectation. Recently, many methods have been proposed to obtain the temporal locations of abnormal events under various determined thresholds. However, the specific categories of abnormal events are mostly neglect, which are important to help in monitoring agents to make decisions. In this study, a Temporal Attention Network (TANet) is proposed to capture both the specific categories and temporal locations of abnormal events in a weakly supervised manner. The TANet learns the anomaly score and specific category for each video segment with only video-level abnormal event labels. An event recognition module is exploited to predict the event scores for each video segment while a temporal attention module is proposed to learn a temporal attention value. Finally, to learn anomaly scores and specific categories, three constraints are considered: event category constraint, event separation constraint and temporal smoothness constraint. Experiments on the University of Central Florida Crime dataset demonstrate the effectiveness of the proposed method. Published version This work was supported in part by the National Science Fund for Distinguished Young Scholars under grant no. 61925112, in part by the National Natural Science Foundation of China under grant no. 61806193 and grant no. 61772510, in part by the Innovation Capability Support Program of Shaanxi under grant no. 2020KJXX‐091, and in part by the Key Research Program of Frontier Sciences, Chinese Academy of Sciences under grant no. QYZDY‐SSW‐JSC044. 2023-01-16T02:35:40Z 2023-01-16T02:35:40Z 2022 Journal Article Zheng, X., Zhang, Y., Zheng, Y., Luo, F. & Lu, X. (2022). Abnormal event detection by a weakly supervised temporal attention network. CAAI Transactions On Intelligence Technology, 7(3), 419-431. https://dx.doi.org/10.1049/cit2.12068 2468-2322 https://hdl.handle.net/10356/164312 10.1049/cit2.12068 2-s2.0-85120308852 3 7 419 431 en CAAI Transactions on Intelligence Technology © 2021 The Authors. CAAI Transactions on Intelligence Technology published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and Technology and Chongqing University of Technology. This is an open access article under the terms of the Creative Commons Attribution‐NonCommercial‐NoDerivs License, which permits use and distribution in any medium, provided the original work is properly cited, the use is non‐commercial and no modifications or adaptations are made. application/pdf |
| spellingShingle | Engineering::Electrical and electronic engineering Human Detection Video Analysis Zheng, Xiangtao Zhang, Yichao Zheng, Yunpeng Luo, Fulin Lu, Xiaoqiang Abnormal event detection by a weakly supervised temporal attention network |
| title | Abnormal event detection by a weakly supervised temporal attention network |
| title_full | Abnormal event detection by a weakly supervised temporal attention network |
| title_fullStr | Abnormal event detection by a weakly supervised temporal attention network |
| title_full_unstemmed | Abnormal event detection by a weakly supervised temporal attention network |
| title_short | Abnormal event detection by a weakly supervised temporal attention network |
| title_sort | abnormal event detection by a weakly supervised temporal attention network |
| topic | Engineering::Electrical and electronic engineering Human Detection Video Analysis |
| url | https://hdl.handle.net/10356/164312 |
| work_keys_str_mv | AT zhengxiangtao abnormaleventdetectionbyaweaklysupervisedtemporalattentionnetwork AT zhangyichao abnormaleventdetectionbyaweaklysupervisedtemporalattentionnetwork AT zhengyunpeng abnormaleventdetectionbyaweaklysupervisedtemporalattentionnetwork AT luofulin abnormaleventdetectionbyaweaklysupervisedtemporalattentionnetwork AT luxiaoqiang abnormaleventdetectionbyaweaklysupervisedtemporalattentionnetwork |