Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.04504 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914180792057856 |
|---|---|
| author | Ahn, Sunghyun Jo, Youngwan Lee, Kijung Kwon, Sein Hong, Inpyo Park, Sanghyun |
| author_facet | Ahn, Sunghyun Jo, Youngwan Lee, Kijung Kwon, Sein Hong, Inpyo Park, Sanghyun |
| contents | Video anomaly detection (VAD) is crucial for video analysis and surveillance in computer vision. However, existing VAD models rely on learned normal patterns, which makes them difficult to apply to diverse environments. Consequently, users should retrain models or develop separate AI models for new environments, which requires expertise in machine learning, high-performance hardware, and extensive data collection, limiting the practical usability of VAD. To address these challenges, this study proposes customizable video anomaly detection (C-VAD) technique and the AnyAnomaly model. C-VAD considers user-defined text as an abnormal event and detects frames containing a specified event in a video. We effectively implemented AnyAnomaly using a context-aware visual question answering without fine-tuning the large vision language model. To validate the effectiveness of the proposed model, we constructed C-VAD datasets and demonstrated the superiority of AnyAnomaly. Furthermore, our approach showed competitive results on VAD benchmarks, achieving state-of-the-art performance on UBnormal and UCF-Crime and surpassing other methods in generalization across all datasets. Our code is available online at github.com/SkiddieAhn/Paper-AnyAnomaly. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_04504 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AnyAnomaly: Zero-Shot Customizable Video Anomaly Detection with LVLM Ahn, Sunghyun Jo, Youngwan Lee, Kijung Kwon, Sein Hong, Inpyo Park, Sanghyun Computer Vision and Pattern Recognition Video anomaly detection (VAD) is crucial for video analysis and surveillance in computer vision. However, existing VAD models rely on learned normal patterns, which makes them difficult to apply to diverse environments. Consequently, users should retrain models or develop separate AI models for new environments, which requires expertise in machine learning, high-performance hardware, and extensive data collection, limiting the practical usability of VAD. To address these challenges, this study proposes customizable video anomaly detection (C-VAD) technique and the AnyAnomaly model. C-VAD considers user-defined text as an abnormal event and detects frames containing a specified event in a video. We effectively implemented AnyAnomaly using a context-aware visual question answering without fine-tuning the large vision language model. To validate the effectiveness of the proposed model, we constructed C-VAD datasets and demonstrated the superiority of AnyAnomaly. Furthermore, our approach showed competitive results on VAD benchmarks, achieving state-of-the-art performance on UBnormal and UCF-Crime and surpassing other methods in generalization across all datasets. Our code is available online at github.com/SkiddieAhn/Paper-AnyAnomaly. |
| title | AnyAnomaly: Zero-Shot Customizable Video Anomaly Detection with LVLM |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.04504 |