摘要
In this paper, we propose HF2-VAD, a Hybrid framework that integrates Flow reconstruction and Frame prediction seamlessly to handle Video Anomaly Detection. Firstly, we design the network of ML-MemAE-SC (Multi-Level Memory modules in an Autoencoder with Skip Connections) to memorize normal patterns for optical flow reconstruction so that abnormal events can be sensitively identified with larger flow reconstruction errors. More importantly, conditioned on the reconstructed flows, we then employ a Conditional Variational Autoencoder (CVAE), which captures the high correlation between video frame and optical flow, to predict the next frame given several previous frames. By CVAE, the quality of flow reconstruction essentially influences that of frame prediction. Therefore, poorly reconstructed optical flows of abnormal events further deteriorate the quality of the final predicted future frame, making the anomalies more detectable. Experimental results demonstrate the effectiveness of the proposed method. Code is available at https://github.com/LiUzHiAn/hf2vad.
- Video anomaly detection with spatio-temporal dissociationChang, Yunpeng; Tu, Zhigang*; Xie, Wei; Luo, Bin; Zhang, Shifu; Sui, Haigang; Yuan, JunsongPattern Recognition, 2022, 122: 108213.被引 64
- Comprehensive Regularization in a Bi-directional Predictive Network for Video Anomaly DetectionChen, Chengwei; Xie, Yuan*; Lin, Shaohui; Yao, Angela; Jiang, Guannan; Zhang, Wei; Qu, Yanyun; Qiao, Ruizhi; Ren, Bo; Ma, Lizhuang*36th AAAI Conference on Artificial Intelligence / 34th Conference on Innovative Applications of Artificial Intelligence / 12th Symposium on Educational Advances in Artificial Intelligence, ELECTR NETWORK, 2022-02-22 To 2022.被引 6
- Anomaly Detection With Bidirectional Consistency in VideosFang, Zhiwen; Liang, Jiafei; Zhou, Joey Tianyi*; Xiao, Yang; Yang, FengIEEE Transactions on Neural Networks and Learning Systems, 2022, 33(3): 1079-1092.被引 17
