한국정보처리학회:학술대회논문집 (Proceedings of the Korea Information Processing Society Conference)
- 한국정보처리학회 2023년도 추계학술발표대회
- /
- Pages.648-651
- /
- 2023
- /
- 2005-0011(pISSN)
- /
- 2671-7298(eISSN)
DOI QR Code
Multi-stage Transformer for Video Anomaly Detection
- Viet-Tuan Le (Department of Computer Engineering, Sejong University) ;
- Khuong G. T. Diep (Department of Computer Engineering, Sejong University) ;
- Tae-Seok Kim (Department of Computer Engineering, Sejong University) ;
- Yong-Guk Kim (Department of Computer Engineering, Sejong University)
- 발행 : 2023.11.02
초록
Video anomaly detection aims to detect abnormal events. Motivated by the power of transformers recently shown in vision tasks, we propose a novel transformer-based network for video anomaly detection. To capture long-range information in video, we employ a multi-scale transformer as an encoder. A convolutional decoder is utilized to predict the future frame from the extracted multi-scale feature maps. The proposed method is evaluated on three benchmark datasets: USCD Ped2, CUHK Avenue, and ShanghaiTech. The results show that the proposed method achieves better performance compared to recent methods.
키워드