Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.18094 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915211332550656 |
|---|---|
| author | Li, Fei Liu, Wenxuan Chen, Jingjing Zhang, Ruixu Wang, Yuran Zhong, Xian Wang, Zheng |
| author_facet | Li, Fei Liu, Wenxuan Chen, Jingjing Zhang, Ruixu Wang, Yuran Zhong, Xian Wang, Zheng |
| contents | Open Vocabulary Video Anomaly Detection (OVVAD) seeks to detect and classify both base and novel anomalies. However, existing methods face two specific challenges related to novel anomalies. The first challenge is detection ambiguity, where the model struggles to assign accurate anomaly scores to unfamiliar anomalies. The second challenge is categorization confusion, where novel anomalies are often misclassified as visually similar base instances. To address these challenges, we explore supplementary information from multiple sources to mitigate detection ambiguity by leveraging multiple levels of visual data alongside matching textual information. Furthermore, we propose incorporating label relations to guide the encoding of new labels, thereby improving alignment between novel videos and their corresponding labels, which helps reduce categorization confusion. The resulting Anomize framework effectively tackles these issues, achieving superior performance on UCF-Crime and XD-Violence datasets, demonstrating its effectiveness in OVVAD. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_18094 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Anomize: Better Open Vocabulary Video Anomaly Detection Li, Fei Liu, Wenxuan Chen, Jingjing Zhang, Ruixu Wang, Yuran Zhong, Xian Wang, Zheng Computer Vision and Pattern Recognition Open Vocabulary Video Anomaly Detection (OVVAD) seeks to detect and classify both base and novel anomalies. However, existing methods face two specific challenges related to novel anomalies. The first challenge is detection ambiguity, where the model struggles to assign accurate anomaly scores to unfamiliar anomalies. The second challenge is categorization confusion, where novel anomalies are often misclassified as visually similar base instances. To address these challenges, we explore supplementary information from multiple sources to mitigate detection ambiguity by leveraging multiple levels of visual data alongside matching textual information. Furthermore, we propose incorporating label relations to guide the encoding of new labels, thereby improving alignment between novel videos and their corresponding labels, which helps reduce categorization confusion. The resulting Anomize framework effectively tackles these issues, achieving superior performance on UCF-Crime and XD-Violence datasets, demonstrating its effectiveness in OVVAD. |
| title | Anomize: Better Open Vocabulary Video Anomaly Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.18094 |