Saved in:
Bibliographic Details
Main Authors: Lin, Dongheng, Qu, Mengxue, Han, Kunyang, Jiao, Jianbo, Jin, Xiaojie, Wei, Yunchao
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.00962
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908624714989568
author Lin, Dongheng
Qu, Mengxue
Han, Kunyang
Jiao, Jianbo
Jin, Xiaojie
Wei, Yunchao
author_facet Lin, Dongheng
Qu, Mengxue
Han, Kunyang
Jiao, Jianbo
Jin, Xiaojie
Wei, Yunchao
contents Most video-anomaly research stops at frame-wise detection, offering little insight into why an event is abnormal, typically outputting only frame-wise anomaly scores without spatial or semantic context. Recent video anomaly localization and video anomaly understanding methods improve explainability but remain data-dependent and task-specific. We propose a unified reasoning framework that bridges the gap between temporal detection, spatial localization, and textual explanation. Our approach is built upon a chained test-time reasoning process that sequentially connects these tasks, enabling holistic zero-shot anomaly analysis without any additional training. Specifically, our approach leverages intra-task reasoning to refine temporal detections and inter-task chaining for spatial and semantic understanding, yielding improved interpretability and generalization in a fully zero-shot manner. Without any additional data or gradients, our method achieves state-of-the-art zero-shot performance across multiple video anomaly detection, localization, and explanation benchmarks. The results demonstrate that careful prompt design with task-wise chaining can unlock the reasoning power of foundation models, enabling practical, interpretable video anomaly analysis in a fully zero-shot manner. Project Page: https://rathgrith.github.io/Unified_Frame_VAA/.
format Preprint
id arxiv_https___arxiv_org_abs_2511_00962
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Unified Reasoning Framework for Holistic Zero-Shot Video Anomaly Analysis
Lin, Dongheng
Qu, Mengxue
Han, Kunyang
Jiao, Jianbo
Jin, Xiaojie
Wei, Yunchao
Computer Vision and Pattern Recognition
Most video-anomaly research stops at frame-wise detection, offering little insight into why an event is abnormal, typically outputting only frame-wise anomaly scores without spatial or semantic context. Recent video anomaly localization and video anomaly understanding methods improve explainability but remain data-dependent and task-specific. We propose a unified reasoning framework that bridges the gap between temporal detection, spatial localization, and textual explanation. Our approach is built upon a chained test-time reasoning process that sequentially connects these tasks, enabling holistic zero-shot anomaly analysis without any additional training. Specifically, our approach leverages intra-task reasoning to refine temporal detections and inter-task chaining for spatial and semantic understanding, yielding improved interpretability and generalization in a fully zero-shot manner. Without any additional data or gradients, our method achieves state-of-the-art zero-shot performance across multiple video anomaly detection, localization, and explanation benchmarks. The results demonstrate that careful prompt design with task-wise chaining can unlock the reasoning power of foundation models, enabling practical, interpretable video anomaly analysis in a fully zero-shot manner. Project Page: https://rathgrith.github.io/Unified_Frame_VAA/.
title A Unified Reasoning Framework for Holistic Zero-Shot Video Anomaly Analysis
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.00962