Unbiased multiple instance learning for weakly supervised video anomaly detection
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...
Saved in:
Main Authors: | Lv, Hui, Yue, Zhongqi, Sun, Qianru, Luo, Bin, Cui, Zhen, Zhang, Hanwang |
---|---|
其他作者: | School of Computer Science and Engineering |
格式: | Conference or Workshop Item |
語言: | English |
出版: |
2023
|
主題: | |
在線閱讀: | https://hdl.handle.net/10356/169509 https://cvpr2023.thecvf.com/Conferences/2023 |
標簽: |
添加標簽
沒有標簽, 成為第一個標記此記錄!
|
相似書籍
-
Weakly supervised segmentation via instance-aware propagation
由: XIN, Huang, et al.
出版: (2021) -
Unbiased multiple instance learning for weakly supervised video anomaly detection
由: LYU, Hui, et al.
出版: (2023) -
Contrastive transformer-based multiple instance learning for weakly supervised polyp frame detection
由: YU, Tian, et al.
出版: (2022) -
Deep weakly-supervised anomaly detection
由: PANG, Guansong, et al.
出版: (2023) -
Semi-supervised tooth instance segmentation
由: Ling, Zijie
出版: (2024)