ABSTRACT
Abnormal behavior detection in surveillance video is a fundamental task in modern public security. Different from typical pixel-based solutions, pose-based approaches leverage low-dimensional and strongly-structured skeleton feature, which enables the anomaly detector to be immune to complex background noise and obtain higher efficiency. However, existing pose-based methods only utilize the pose of each individual independently while ignore the important interactions between individuals. In this paper, we present a hierarchical graph embedded pose regularity learning framework via spatio-temporal transformer, which leverages the strength of graph representation in encoding strongly-structured skeleton feature. Specifically, skeleton feature is encoded as the hierarchical graph representation, which jointly models the interactions among multiple individuals and the correlations among body joints within the same individual. Furthermore, a novel task-specific spatial-temporal graph transformer is designed to encode the hierarchical spatio-temporal graph embeddings of human skeletons and learn the regular patterns within normal training videos. Experimental results indicate that our method obtains superior performance over state-of-the-art methods on several challenging datasets.
Supplemental Material
Available for Download
- Gedas Bertasius, Heng Wang, and Lorenzo Torresani. 2021. Is Space-Time Attention All You Need for Video Understanding?. In Proceedings of the International Conference on Machine Learning (ICML).Google Scholar
- Ruichu Cai, Hao Zhang, Wen Liu, Shenghua Gao, and Zhifeng Hao. 2021. Appearance-motion memory consistency network for video anomaly detection. In Proceedings of the 35th AAAI Conference on Artificial Intelligence. 938--946.Google ScholarCross Ref
- Zhi Chen, Jingjing Li, Yadan Luo, Zi Huang, and Yang Yang. 2020a. Canzsl: Cycle-Consistent Adversarial Networks for Zero-Shot Learning from Natural Language. In IEEE/CVF Winter Conference on Applications of Computer Vision (WACV). 874--883.Google ScholarCross Ref
- Zhi Chen, Yadan Luo, Ruihong Qiu, Sen Wang, Zi Huang, Jingjing Li, and Zheng Zhang. 2021a. Semantics Disentangling for Generalized Zero-Shot Learning. In IEEE/CVF International Conference on Computer Vision (ICCV).Google Scholar
- Zhi Chen, Yadan Luo, Sen Wang, Ruihong Qiu, Jingjing Li, and Zi Huang. 2021b. Mitigating Generation Shifts for Generalized Zero-Shot Learning. In Proceedings of the 28th ACM International Conference on Multimedia.Google Scholar
- Zhi Chen, Sen Wang, Jingjing Li, and Zi Huang. 2020b. Rethinking Generative Zero-Shot Learning: An Ensemble Learning Perspective for Recognising Visual Patches. In Proceedings of the 28th ACM International Conference on Multimedia. 3413--3421.Google ScholarDigital Library
- Xinyang Feng, Dongjin Song, Yuncong Chen, Zhengzhang Chen, Jingchao Ni, and Haifeng Chen. 2021. Convolutional Transformer based Dual Discriminator Generative Adversarial Networks for Video Anomaly Detection. In Proceedings of the 29th ACM International Conference on Multimedia. 5546--5554.Google ScholarDigital Library
- Dong Gong, Lingqiao Liu, Vuong Le, Budhaditya Saha, Moussa Reda Mansour, Svetha Venkatesh, and Anton van den Hengel. 2019. Memorizing normality to detect anomaly: Memory-augmented deep autoencoder for unsupervised anomaly detection. In Proceedings of the IEEE International Conference on Computer Vision. 1705--1714.Google Scholar
- Chao Huang, Jie Wen, Yong Xu, Qiuping Jiang, Jian Yang, Yaowei Wang, and David Zhang. 2022. Self-supervised attentive generative adversarial networks for video anomaly detection. IEEE Transactions on Neural Networks and Learning Systems (2022).Google ScholarCross Ref
- Chao Huang, Zhihao Wu, Jie Wen, Yong Xu, Qiuping Jiang, and Yaowei Wang. 2021a. Abnormal event detection using deep contrastive learning for intelligent video surveillance system. IEEE Transactions on Industrial Informatics, Vol. 18, 8 (2021), 5171--5179.Google ScholarCross Ref
- Chao Huang, Zehua Yang, Jie Wen, Yong Xu, Qiuping Jiang, Jian Yang, and Yaowei Wang. 2021b. Self-Supervision-Augmented Deep Autoencoder for Unsupervised Visual Anomaly Detection. IEEE Transactions on Cybernetics (2021).Google ScholarCross Ref
- Yashswi Jain, Ashvini Kumar Sharma, Rajbabu Velmurugan, and Biplab Banerjee. 2021. PoseCVAE: Anomalous Human Activity Detection. In 25th International Conference on Pattern Recognition (ICPR). 2927--2934.Google Scholar
- Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014).Google Scholar
- An-An Liu, Yu-Ting Su, Wei-Zhi Nie, and Mohan Kankanhalli. 2016. Hierarchical clustering multi-task learning for joint human action grouping and recognition. IEEE transactions on pattern analysis and machine intelligence, Vol. 39, 1 (2016), 102--114.Google Scholar
- An-An Liu, Hongshuo Tian, Ning Xu, Weizhi Nie, Yongdong Zhang, and Mohan Kankanhalli. 2021. Toward region-aware attention learning for scene graph generation. IEEE Transactions on Neural Networks and Learning Systems (2021).Google ScholarCross Ref
- Wen Liu, Weixin Luo, Dongze Lian, and Shenghua Gao. 2018. Future frame prediction for anomaly detection--a new baseline. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 6536--6545.Google ScholarCross Ref
- Cewu Lu, Jianping Shi, and Jiaya Jia. [n.d.]. Abnormal event detection at 150 fps in matlab. In Proceedings of the IEEE International Conference on Computer vision.Google Scholar
- Weixin Luo, Wen Liu, and Shenghua Gao. 2017a. Remembering history with convolutional lstm for anomaly detection. In 2017 IEEE International Conference on Multimedia and Expo (ICME). 439--444.Google ScholarCross Ref
- Weixin Luo, Wen Liu, and Shenghua Gao. 2017b. A revisit of sparse coding based anomaly detection in stacked rnn framework. In Proceedings of the IEEE international conference on computer vision. 341--349.Google ScholarCross Ref
- Weixin Luo, Wen Liu, and Shenghua Gao. 2021a. Normal graph: Spatial temporal graph convolutional networks based prediction network for skeleton based video anomaly detection. Neurocomputing, Vol. 444 (2021), 332--337.Google ScholarCross Ref
- Weixin Luo, Wen Liu, Dongze Lian, and Shenghua Gao. 2021b. Future Frame Prediction Network for Video Anomaly Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence (2021).Google Scholar
- Weixin Luo, Wen Liu, Dongze Lian, Jinhui Tang, Lixin Duan, Xi Peng, and Shenghua Gao. 2021c. Video anomaly detection with sparse coding inspired deep neural networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 43, 3 (2021), 1070--1084.Google ScholarCross Ref
- Hui Lv, Chen Chen, Zhen Cui, Chunyan Xu, Yong Li, and Jian Yang. 2021. Learning Normal Dynamics in Videos with Meta Prototype Network. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 15425--15434.Google ScholarCross Ref
- Amir Markovitz, Gilad Sharir, Itamar Friedman, Lihi Zelnik-Manor, and Shai Avidan. 2020. Graph embedded pose clustering for anomaly detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 10539--10547.Google ScholarCross Ref
- Romero Morais, Vuong Le, Truyen Tran, Budhaditya Saha, Moussa Mansour, and Svetha Venkatesh. 2020. Learning regularity in skeleton trajectories for anomaly detection in videos. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 11996--12004.Google Scholar
- Hyunjong Park, Jongyoun Noh, and Bumsub Ham. 2020. Learning memory-guided normality for anomaly detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 14372--14381.Google ScholarCross Ref
- Adam Paszke, Sam Gross, Soumith Chintala, Gregory Chanan, Edward Yang, Zachary DeVito, Zeming Lin, Alban Desmaison, Luca Antiga, and Adam Lerer. 2017. Automatic differentiation in pytorch. (2017).Google Scholar
- Royston Rodrigues, Neha Bhargava, Rajbabu Velmurugan, and Subhasis Chaudhuri. 2020. Multi-timescale trajectory prediction for abnormal human activity detection. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision. 2626--2634.Google ScholarCross Ref
- Che Sun, Yunde Jia, Yao Hu, and Yuwei Wu. 2020. Scene-Aware Context Reasoning for Unsupervised Abnormal Event Detection in Videos. In Proceedings of the 28th ACM International Conference on Multimedia. 184--192.Google ScholarDigital Library
- Ke Sun, Bin Xiao, Dong Liu, and Jingdong Wang. 2019. Deep high-resolution representation learning for human pose estimation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 5693--5703.Google ScholarCross Ref
- ultralytics. 2020. Yolov5. https://github.com/ultralytics/yolov5 (2020).Google Scholar
- Ziming Wang, Yuexian Zou, and Zeming Zhang. 2020. Cluster Attention Contrast for Video Anomaly Detection. In Proceedings of the 28th ACM International Conference on Multimedia. 2463--2471.Google ScholarDigital Library
- Nicolai Wojke, Alex Bewley, and Dietrich Paulus. 2017. Simple online and realtime tracking with a deep association metric. In 2017 IEEE international conference on image processing (ICIP). 3645--3649.Google ScholarDigital Library
- Muchao Ye, Xiaojiang Peng, Weihao Gan, Wei Wu, and Yu Qiao. 2019. Anopcn: Video anomaly detection via deep predictive coding network. In Proceedings of the 27th ACM International Conference on Multimedia. 1805--1813.Google ScholarDigital Library
- Guang Yu, Siqi Wang, Zhiping Cai, En Zhu, Chuanfu Xu, Jianping Yin, and Marius Kloft. 2020. Cloze Test Helps: Effective Video Anomaly Detection via Learning to Complete Video Events. In Proceedings of the 28th ACM International Conference on Multimedia. 583--591.Google ScholarDigital Library
- Qing Yu and Kiyoharu Aizawa. 2019. Unsupervised out-of-distribution detection by maximum classifier discrepancy. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 9518--9526.Google ScholarCross Ref
- Shoubin Yu, Zhongyin Zhao, Haoshu Fang, Andong Deng, Haisheng Su, Dongliang Wang, Weihao Gan, Cewu Lu, and Wei Wu. 2021. Regularity Learning via Explicit Distribution Modeling for Skeletal Video Anomaly Detection. arXiv preprint arXiv:2112.03649 (2021).Google Scholar
- Muhammad Zaigham Zaheer, Jin-ha Lee, Marcella Astrid, and Seung-Ik Lee. 2020. Old is gold: Redefining the adversarially learned one-class classifier training paradigm. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 14183--14193.Google Scholar
- Xianlin Zeng, Yalong Jiang, Wenrui Ding, Hongguang Li, Yafeng Hao, and Zifeng Qiu. 2021. A Hierarchical Spatio-Temporal Graph Convolutional Neural Network for Anomaly Detection in Videos. arXiv preprint arXiv:2112.04294 (2021).Google Scholar
- Dasheng Zhang, Chao Huang, Chengliang Liu, and Yong Xu. 2022a. Weakly Supervised Video Anomaly Detection via Transformer-Enabled Temporal Relation Learning. IEEE Signal Processing Letters, Vol. 29 (2022), 1197--1201.Google ScholarCross Ref
- Zheng Zhang, Luyao Liu, Yadan Luo, Zi Huang, Fumin Shen, Heng Tao Shen, and Guangming Lu. 2020. Inductive structure consistent hashing via flexible semantic calibration. IEEE Transactions on Neural Networks and Learning Systems, Vol. 32, 10 (2020), 4514--4528.Google ScholarCross Ref
- Zheng Zhang, Haoyang Luo, Lei Zhu, Guangming Lu, and Heng Tao Shen. 2022b. Modality-invariant asymmetric networks for cross-modal hashing. IEEE Transactions on Knowledge and Data Engineering (2022).Google ScholarDigital Library
- Ce Zheng, Sijie Zhu, Matias Mendieta, Taojiannan Yang, Chen Chen, and Zhengming Ding. 2021. 3d human pose estimation with spatial and temporal transformers. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 11656--11665.Google ScholarCross Ref
Index Terms
- Hierarchical Graph Embedded Pose Regularity Learning via Spatio-Temporal Transformer for Abnormal Behavior Detection
Recommendations
Pixel-Level Anomaly Detection via Uncertainty-aware Prototypical Transformer
MM '22: Proceedings of the 30th ACM International Conference on MultimediaPixel-level visual anomaly detection, which aims to recognize the abnormal areas from images, plays an important role in industrial fault detection and medical diagnosis. However, it is a challenging task due to the following reasons: i) the large ...
Spatio-Temporal AutoEncoder for Video Anomaly Detection
MM '17: Proceedings of the 25th ACM international conference on MultimediaAnomalous events detection in real-world video scenes is a challenging problem due to the complexity of "anomaly" as well as the cluttered backgrounds, objects and motions in the scenes. Most existing methods use hand-crafted features in local spatial ...
Two-stage anomaly detection algorithm via dynamic community evolution in temporal graph
AbstractDetecting anomalies from a massive amount of user behavioral data is often liken to finding a needle in a haystack. While tremendous efforts have been devoted to anomaly detection from temporal graphs, existing studies rarely consider community ...
Comments