Saved in:
Bibliographic Details
Main Authors: Li, Wenlong, Xu, Yifei, Rao, Yuan, Wang, Zhenhua, Deng, Shuiguang
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.22693
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909978488471552
author Li, Wenlong
Xu, Yifei
Rao, Yuan
Wang, Zhenhua
Deng, Shuiguang
author_facet Li, Wenlong
Xu, Yifei
Rao, Yuan
Wang, Zhenhua
Deng, Shuiguang
contents Video anomaly detection (VAD) focuses on identifying anomalies in videos. Supervised methods demand substantial in-domain training data and fail to deliver clear explanations for anomalies. In contrast, training-free methods leverage the knowledge reserves and language interactivity of large pre-trained models to detect anomalies. However, the current fixed-length temporal window sampling approaches struggle to accurately capture anomalies with varying temporal spans. Therefore, we propose VADTree that utilizes a Hierarchical Granularityaware Tree (HGTree) structure for flexible sampling in VAD. VADTree leverages the knowledge embedded in a pre-trained Generic Event Boundary Detection (GEBD) model to characterize potential anomaly event boundaries. Specifically, VADTree decomposes the video into generic event nodes based on boundary confidence, and performs adaptive coarse-fine hierarchical structuring and redundancy removal to construct the HGTree. Then, the multi-dimensional priors are injected into the visual language models (VLMs) to enhance the node-wise anomaly perception, and anomaly reasoning for generic event nodes is achieved via large language models (LLMs). Finally, an inter-cluster node correlation method is used to integrate the multi-granularity anomaly scores. Extensive experiments on three challenging datasets demonstrate that VADTree achieves state-of-the-art performance in training-free settings while drastically reducing the number of sampled video segments. The code will be available at https://github.com/wenlongli10/VADTree.
format Preprint
id arxiv_https___arxiv_org_abs_2510_22693
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle VADTree: Explainable Training-Free Video Anomaly Detection via Hierarchical Granularity-Aware Tree
Li, Wenlong
Xu, Yifei
Rao, Yuan
Wang, Zhenhua
Deng, Shuiguang
Computer Vision and Pattern Recognition
Video anomaly detection (VAD) focuses on identifying anomalies in videos. Supervised methods demand substantial in-domain training data and fail to deliver clear explanations for anomalies. In contrast, training-free methods leverage the knowledge reserves and language interactivity of large pre-trained models to detect anomalies. However, the current fixed-length temporal window sampling approaches struggle to accurately capture anomalies with varying temporal spans. Therefore, we propose VADTree that utilizes a Hierarchical Granularityaware Tree (HGTree) structure for flexible sampling in VAD. VADTree leverages the knowledge embedded in a pre-trained Generic Event Boundary Detection (GEBD) model to characterize potential anomaly event boundaries. Specifically, VADTree decomposes the video into generic event nodes based on boundary confidence, and performs adaptive coarse-fine hierarchical structuring and redundancy removal to construct the HGTree. Then, the multi-dimensional priors are injected into the visual language models (VLMs) to enhance the node-wise anomaly perception, and anomaly reasoning for generic event nodes is achieved via large language models (LLMs). Finally, an inter-cluster node correlation method is used to integrate the multi-granularity anomaly scores. Extensive experiments on three challenging datasets demonstrate that VADTree achieves state-of-the-art performance in training-free settings while drastically reducing the number of sampled video segments. The code will be available at https://github.com/wenlongli10/VADTree.
title VADTree: Explainable Training-Free Video Anomaly Detection via Hierarchical Granularity-Aware Tree
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.22693