Human-Scene Network: A novel baseline with self-rectifying loss for weakly supervised video anomaly detection
-
Published:2024-04
Issue:
Volume:241
Page:103955
-
ISSN:1077-3142
-
Container-title:Computer Vision and Image Understanding
-
language:en
-
Short-container-title:Computer Vision and Image Understanding
Author:
Majhi SnehashisORCID, Dai Rui, Kong Quan, Garattoni Lorenzo, Francesca Gianpiero, Brémond François
Funder
Toyota Motor Europe
Reference50 articles.
1. Robust real-time unusual event detection using multiple fixed-location monitors;Adam;IEEE Trans. Pattern Anal. Mach. Intell.,2008 2. Carreira, J., Zisserman, A., 2017. Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset. In: The IEEE Conference on Computer Vision and Pattern Recognition. CVPR. 3. Chen, Y., Liu, Z., Zhang, B., Fok, W., Qi, X., Wu, Y.-C., 2023a. Mgfn: Magnitude-contrastive glance-and-focus network for weakly-supervised video anomaly detection. In: Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 37, (1), pp. 387–395. 4. Chen, W., Ma, K.T., Yew, Z.J., Hur, M., Khoo, D.A.-A., 2023b. TEVAD: Improved video anomaly detection with captions. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 5548–5558. 5. Learning a similarity metric discriminatively, with application to face verification;Chopra,2005
Cited by
3 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
|
|