摘要
The automatic detection of abnormal events in surveillance videos with weak supervision has been formulated as a multiple instance learning task, which aims to localize the clips containing abnormal events temporally with the video-level labels. However, most existing methods rely on the features extracted by the pre-trained action recognition models, which are not discriminative enough for video anomaly detection. In this work, we propose a spatial-temporal attention mechanism to learn inter- and intra-correlations of video clips, and the boosted features are encouraged to be task-specific via the mutual cosine embedding loss. Experimental results on standard benchmarks demonstrate the effectiveness of the spatial-temporal attention, and our method achieves superior performance to the state-of-the-art methods.
学科与关键词
- 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
- A Video Anomaly Detection Method Based on Sequence RecognitionYang, Lei; Zhang, Xiaolong*18th International Conference on Intelligent Computing (ICIC), Xian, PEOPLES R CHINA, 2022-08-07 To 2022-08-11.
- Weakly Supervised Violence Detection in Surveillance VideoChoqueluque-Roman, David*; Camara-Chavez, GuillermoSENSORS, 2022, 22(12): 4502.被引 9
