Unbiased multiple instance learning for weakly supervised video anomaly detection

• Main Authors: Lv, Hui, Yue, Zhongqi, Sun, Qianru, Luo, Bin, Cui, Zhen, Zhang, Hanwang
• Other Authors: School of Computer Science and Engineering
• Format: Conference or Workshop Item
• Language: English
• Published: 2023
• Subjects: Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence; Multiple Instance Learning; Weakly Supervised Video Anomaly Detection
• Online Access: https://hdl.handle.net/10356/169509; https://cvpr2023.thecvf.com/Conferences/2023
• Institution: Nanyang Technological University

Weakly Supervised Video Anomaly Detection (WSVAD) is challenging because the binary anomaly label is only given on the video level, but the output requires snippetlevel predictions. So, Multiple Instance Learning (MIL) is prevailing in WSVAD. However, MIL is notoriously known to suffer from man...