18.222.163.231
18.222.163.231
close menu
Multi-stage Transformer for Video Anomaly Detection
( Viet-tuan Le ) , ( Khuong G. T. Diep ) , ( Tae-seok Kim ) , ( Yong-guk Kim )
UCI I410-ECN-151-24-02-089051976
이 자료는 4페이지 이하의 자료입니다.

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.

[자료제공 : 네이버학술정보]
×