Ex-VAD: Explainable Fine-grained Video Anomaly Detection Based on Visual-Language Models

Chao Huang, Yushu Shi, Jie Wen, Wei Wang, Yong Xu, Xiaochun Cao
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:25750-25761, 2025.

Abstract

With advancements in visual language models (VLMs) and large language models (LLMs), video anomaly detection (VAD) has progressed beyond binary classification to fine-grained categorization and multidimensional analysis. However, existing methods focus mainly on coarse-grained detection, lacking anomaly explanations. To address these challenges, we propose Ex-VAD, an Explainable Fine-grained Video Anomaly Detection approach that combines fine-grained classification with detailed explanations of anomalies. First, we use a VLM to extract frame-level captions, and an LLM converts them to video-level explanations, enhancing the model’s explainability. Second, integrating textual explanations of anomalies with visual information greatly enhances the model’s anomaly detection capability. Finally, we apply label-enhanced alignment to optimize feature fusion, enabling precise fine-grained detection. Extensive experimental results on the UCF-Crime and XD-Violence datasets demonstrate that Ex-VAD significantly outperforms existing State-of-The-Art methods.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-huang25ad, title = {Ex-{VAD}: Explainable Fine-grained Video Anomaly Detection Based on Visual-Language Models}, author = {Huang, Chao and Shi, Yushu and Wen, Jie and Wang, Wei and Xu, Yong and Cao, Xiaochun}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {25750--25761}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/huang25ad/huang25ad.pdf}, url = {https://proceedings.mlr.press/v267/huang25ad.html}, abstract = {With advancements in visual language models (VLMs) and large language models (LLMs), video anomaly detection (VAD) has progressed beyond binary classification to fine-grained categorization and multidimensional analysis. However, existing methods focus mainly on coarse-grained detection, lacking anomaly explanations. To address these challenges, we propose Ex-VAD, an Explainable Fine-grained Video Anomaly Detection approach that combines fine-grained classification with detailed explanations of anomalies. First, we use a VLM to extract frame-level captions, and an LLM converts them to video-level explanations, enhancing the model’s explainability. Second, integrating textual explanations of anomalies with visual information greatly enhances the model’s anomaly detection capability. Finally, we apply label-enhanced alignment to optimize feature fusion, enabling precise fine-grained detection. Extensive experimental results on the UCF-Crime and XD-Violence datasets demonstrate that Ex-VAD significantly outperforms existing State-of-The-Art methods.} }
Endnote
%0 Conference Paper %T Ex-VAD: Explainable Fine-grained Video Anomaly Detection Based on Visual-Language Models %A Chao Huang %A Yushu Shi %A Jie Wen %A Wei Wang %A Yong Xu %A Xiaochun Cao %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-huang25ad %I PMLR %P 25750--25761 %U https://proceedings.mlr.press/v267/huang25ad.html %V 267 %X With advancements in visual language models (VLMs) and large language models (LLMs), video anomaly detection (VAD) has progressed beyond binary classification to fine-grained categorization and multidimensional analysis. However, existing methods focus mainly on coarse-grained detection, lacking anomaly explanations. To address these challenges, we propose Ex-VAD, an Explainable Fine-grained Video Anomaly Detection approach that combines fine-grained classification with detailed explanations of anomalies. First, we use a VLM to extract frame-level captions, and an LLM converts them to video-level explanations, enhancing the model’s explainability. Second, integrating textual explanations of anomalies with visual information greatly enhances the model’s anomaly detection capability. Finally, we apply label-enhanced alignment to optimize feature fusion, enabling precise fine-grained detection. Extensive experimental results on the UCF-Crime and XD-Violence datasets demonstrate that Ex-VAD significantly outperforms existing State-of-The-Art methods.
APA
Huang, C., Shi, Y., Wen, J., Wang, W., Xu, Y. & Cao, X.. (2025). Ex-VAD: Explainable Fine-grained Video Anomaly Detection Based on Visual-Language Models. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:25750-25761 Available from https://proceedings.mlr.press/v267/huang25ad.html.

Related Material