Geometry-Aware Semantic Reasoning for Training Free Video Anomaly Detection

Ali Zia; Usman Ali; Muhammad Umer Ramzan; Hamza Abid; Abdul Rehman; Wei Xiang

cs.CVMar 10, 2026

Geometry-Aware Semantic Reasoning for Training Free Video Anomaly Detection

Authors: Ali Zia, Usman Ali, Muhammad Umer Ramzan, Hamza Abid, Abdul Rehman, Wei Xiang

Organizations: School of Computing, Engineering & Mathematical Sciences, La Trobe University, Melbourne, Australia · School of Engineering and Applied Sciences, GIFT University, Gujranwala 52250, Pakistan

Abstract

Training-free video anomaly detection (VAD) has recently emerged as a scalable alternative to supervised approaches, yet existing methods largely rely on static prompting and geometry-agnostic feature fusion. As a result, anomaly inference is often reduced to shallow similarity matching over Euclidean embeddings, leading to unstable predictions and limited interpretability, especially in complex or hierarchically structured scenes. We introduce MM-VAD, a geometry-aware semantic reasoning framework for training free VAD that reframes anomaly detection as adaptive test-time inference rather than fixed feature comparison. Our approach projects caption-derived scene representations into hyperbolic space to better preserve hierarchical structure and performs anomaly assessment through an adaptive question answering process over a frozen large language model. A lightweight, learnable prompt is optimised at test time using an unsupervised confidence-sparsity objective, enabling context-specific calibration without updating any backbone parameters. To further ground semantic predictions in visual evidence, we incorporate a covariance-aware Mahalanobis refinement that stabilises cross-modal alignment. Across four benchmarks, MM-VAD consistently improves over prior training-free methods, achieving 90.03% AUC on XD-Violence and 83.24%, 96.95%, and 98.81% on UCF-Crime, ShanghaiTech, and UCSD Ped2, respectively. Our results demonstrate that geometry-aware representation and adaptive semantic calibration provide a principled and effective alternative to static Euclidean matching in training-free VAD.

Figures & tables

Figure 1: Comparison of prior VAD architectures and our modality-agnostic MM-VAD, which introduces adaptive query optimisation and hyperbolic fusion for zero-shot, explainable anomaly detection.

Figure 2: An overview of our MM-VAD framework. Visual captions $C_{\text{vis}}$ and audio captions $C_{\text{aud}}$ are fused in hyperbolic space, and the fused features drive unsupervised refinement of the anomaly query from $Q_{t}$ to $Q_{t+1}$ . A LLaMA-based scorer then evaluates textual video summaries against $Q_{t+1}$ , and a cross-modal refinement step produces the final anomaly scores.

Dataset	LAVAD [ 48 ]	MM-VAD
ShanghaiTech [ 26 ]	94.55	96.95
UCSD Ped2 [ 24 ]	96.11	98.81

Table 2: Comparison of frame-level AUC (%) for training-free methods on ShanghaiTech and UCSD Ped2.

Figure 3: Overview of MM-VAD on XD-Violence. (a) MM-VAD outperforms LAVAD with sharper anomaly localisation and richer action-aware descriptions. (b) Adaptive prompts ( $t_{0}$ – $t_{4}$ ) for frozen-LLM querying. (c) Euclidean embeddings. (d) Hyperbolic embeddings with clearer structure and better separation.

$C^{\text{vis}}$	$C^{\text{aud}}$	$C^{\prime\text{vis}}$	$z_{t}^{(\mathcal{F})}$	$D_{M}$	$Q_{t+1}$	XD-Violence	UCF-Crime
						AUC (%)	AUC (%)
✓	✓	✗	✗	✓	✗	74.56	70.10
✓	✓	✓	✗	✓	✗	80.05	77.80
✓	✓	✗	✓	✓	✗	81.97	78.87
✓	✗	✗	✓	✓	✓	83.24	79.75
✓	✗	✓	✓	✓	✗	85.53	80.41

Table 3: Ablation study of MM-VAD’s components

Table 4: Controlled component and model ablations. (a) Cross-combination study between LAVAD and MM-VAD under different captioning and LLM backbones. (b) LLM ablation with VLRM fixed to isolate the effect of the language model.

Method	Frame	Audio	A-Cap	I-Cap	Idx 1	Clean	Summ	Sco	Idx 2	Refine	Batch	Sec/Frame
LAVAD [ 48 ]	0.2	0.0	0.0	1.3	1.0	4.0	13.0	7.0	1.0	5.0	32.5	2.03
MM-VAD	0.2	0.3	1.0	1.0	1.0	4.0	9.0	4.0	1.0	5.5	27.0	1.69

Table 5: Per-step runtime comparison between MM-VAD and LAVAD . Lower values indicate faster processing and are preferred. The best runtime for each step is highlighted in bold . Shortened headers: A-Cap = Audio-caption, I-Cap = Image caption, Clean = Image caption clean, Summ = LLM-based summary generation, Sco = anomaly score, Refine = Score Refinement, and Batch = Time/Batch (16 frames).

Explore similar work

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere
May 8, 2026Chao Huang, Pengfei Wei, Wei Wang +5Video Anomaly Detection Zero-Shot Anomaly Detection
Shenzhen Campus of Sun Yat-sen University · Harbin Institute of Technology, Shenzhen
Anomaly-Guided Observation and Two-Level Semantic Feedback for Training-Free Video Anomaly Analysis
Oct 12, 2026Hangil Park, Seungheon Kim, Tae-Kyun KimVideo Anomaly Detection
Korea Advanced Institute of Science and Technology (KAIST)
Beyond Hazard Resemblance: Contrastive Event Adjudication for Training-Free Video Anomaly Detection
Aug 10, 2026Wenti Yin, Xiang Wang, Huaxin Zhang +4Interpretable Anomaly Detection Anomaly Localization
Key Laboratory of Image Processing and Intelligent Control, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology · Alibaba Group · The Hong Kong University of Science and Technology (Guangzhou)

May 8, 2026J/K move · Enter open · S save

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere

Chao Huang, Pengfei Wei, Wei Wang, Jie Wen+4

Shenzhen Campus of Sun Yat-sen University · Harbin Institute of Technology, Shenzhen

Video Anomaly Detection Zero-Shot Anomaly Detection

Open paper AskPDF arXiv

Video anomaly detection (VAD) aims to automatically identify events that deviate from normal patterns in untrimmed surveillance videos. Existing methods universally depend on large-scale annotations or task-specific training procedures, severely limiting their rapid deployment to novel scenes. We observe that intermediate-layer features of pre-trained multimodal large language models (MLLMs) already encode rich anomaly semantics, yet existing approaches rely on the language output pathway and fail to exploit the geometric discriminability latent in these representations. Based on this finding, we propose SphereVAD, a fully training-free, zero-shot VAD framework that recasts anomaly discrimination as von Mises-Fisher (vMF) likelihood-ratio geodesic inference on the unit hypersphere, unleashing latent discriminability through principled geometric reasoning rather than learning new representations. Specifically, SphereVAD first applies Frechet mean centering to unfold feature distributions and eliminate domain biases, then employs Holistic Scene Attention (HSA) to reinforce feature consistency using cross-video priors, and finally performs vMF-guided Spherical Geodesic Pulling (SGP) to align ambiguous segments with directional prototypes on the spherical manifold. This training-free pipeline requires only minimal synthetic images for calibration. SphereVAD establishes new state-of-the-art results among training-free approaches on three major benchmarks and remains competitive with fully supervised baselines. Code will be available upon acceptance.

Abstract

Explore similar work

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere

Anomaly-Guided Observation and Two-Level Semantic Feedback for Training-Free Video Anomaly Analysis

Beyond Hazard Resemblance: Contrastive Event Adjudication for Training-Free Video Anomaly Detection