Cross Pseudo Labeling For Weakly Supervised Video Anomaly Detection
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915858448646144 |
|---|---|
| author | Lee, Dayeon Kim, Donghyeong Park, Chaewon Woo, Sungmin Lee, Sangyoun |
| author_facet | Lee, Dayeon Kim, Donghyeong Park, Chaewon Woo, Sungmin Lee, Sangyoun |
| contents | Weakly supervised video anomaly detection aims to detect anomalies and identify abnormal categories with only video-level labels. We propose CPL-VAD, a dual-branch framework with cross pseudo labeling. The binary anomaly detection branch focuses on snippet-level anomaly localization, while the category classification branch leverages vision-language alignment to recognize abnormal event categories. By exchanging pseudo labels, the two branches transfer complementary strengths, combining temporal precision with semantic discrimination. Experiments on XD-Violence and UCF-Crime demonstrate that CPL-VAD achieves state-of-the-art performance in both anomaly detection and abnormal category classification. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_17077 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Cross Pseudo Labeling For Weakly Supervised Video Anomaly Detection Lee, Dayeon Kim, Donghyeong Park, Chaewon Woo, Sungmin Lee, Sangyoun Computer Vision and Pattern Recognition Weakly supervised video anomaly detection aims to detect anomalies and identify abnormal categories with only video-level labels. We propose CPL-VAD, a dual-branch framework with cross pseudo labeling. The binary anomaly detection branch focuses on snippet-level anomaly localization, while the category classification branch leverages vision-language alignment to recognize abnormal event categories. By exchanging pseudo labels, the two branches transfer complementary strengths, combining temporal precision with semantic discrimination. Experiments on XD-Violence and UCF-Crime demonstrate that CPL-VAD achieves state-of-the-art performance in both anomaly detection and abnormal category classification. |
| title | Cross Pseudo Labeling For Weakly Supervised Video Anomaly Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.17077 |