Abstract | ||
---|---|---|
Video anomaly detection is a challenging task in the computer vision community. Most single task-based methods do not consider the independence of unique spatial and temporal patterns, while two-stream structures lack the exploration of the correlations. In this paper, we propose spatial-temporal memories augmented two-stream auto-encoder framework, which learns the appearance normality and motion normality independently and explores the correlations via adversarial learning. Specifically, we first design two proxy tasks to train the two-stream structure to extract appearance and motion features in isolation. Then, the prototypical features are recorded in the corresponding spatial and temporal memory pools. Finally, the encoding-decoding network performs adversarial learning with the discriminator to explore the correlations between spatial and temporal patterns. Experimental results show that our framework outperforms the state-of-the-art methods, achieving AUCs of 98.1% and 89.8% on UCSD Ped2 and CUHK Avenue datasets. |
Year | DOI | Venue |
---|---|---|
2022 | 10.1109/ICME52920.2022.9859727 | IEEE International Conference on Multimedia and Expo (ICME) |
DocType | Citations | PageRank |
Conference | 0 | 0.34 |
References | Authors | |
0 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yang Liu | 1 | 491 | 116.11 |
Jing Liu | 2 | 1781 | 88.09 |
Mengyang Zhao | 3 | 1 | 1.03 |
Dingkang Yang | 4 | 0 | 0.68 |
Xiaoguang Zhu | 5 | 0 | 1.35 |
Liang Song | 6 | 7 | 3.14 |