Comprehensive Regularization in a Bi-directional Predictive Network for Video Anomaly Detection


  • Chengwei Chen East China Normal University
  • Yuan Xie East China Normal University
  • Shaohui Lin East China Normal University
  • Angela Yao National University of Singapore
  • Guannan Jiang Contemporary Amperex Technology Co., Limited (CATL)
  • Wei Zhang Contemporary Amperex Technology Co., Limited (CATL)
  • Yanyun Qu Xiamen University (XMU)
  • Ruizhi Qiao Tencent Youtu Lab
  • Bo Ren Tencent Youtu Lab
  • Lizhuang Ma East China Normal University



Computer Vision (CV)


Video anomaly detection aims to automatically identify unusual objects or behaviours by learning from normal videos. Previous methods tend to use simplistic reconstruction or prediction constraints, which leads to the insufficiency of learned representations for normal data. As such, we propose a novel bi-directional architecture with three consistency constraints to comprehensively regularize the prediction task from pixel-wise, cross-modal, and temporal-sequence levels. First, predictive consistency is proposed to consider the symmetry property of motion and appearance in forwards and backwards time, which ensures the highly realistic appearance and motion predictions at the pixel-wise level. Second, association consistency considers the relevance between different modalities and uses one modality to regularize the prediction of another one. Finally, temporal consistency utilizes the relationship of the video sequence and ensures that the predictive network generates temporally consistent frames. During inference, the pattern of abnormal frames is unpredictable and will therefore cause higher prediction errors. Experiments show that our method outperforms advanced anomaly detectors and achieves state-of-the-art results on UCSD Ped2, CUHK Avenue, and ShanghaiTech datasets.




How to Cite

Chen, C., Xie, Y., Lin, S., Yao, A., Jiang, G., Zhang, W., Qu, Y., Qiao, R., Ren, B., & Ma, L. (2022). Comprehensive Regularization in a Bi-directional Predictive Network for Video Anomaly Detection. Proceedings of the AAAI Conference on Artificial Intelligence, 36(1), 230-238.



AAAI Technical Track on Computer Vision I