Is Video Anomaly Detection Misframed? Evidence from LLM-Based and Multi-Scene Models

• URL: http://arxiv.org/abs/2605.12725v1
• Date: Tue, 12 May 2026 20:29:49 GMT
• Title: Is Video Anomaly Detection Misframed? Evidence from LLM-Based and Multi-Scene Models
• Abstract summary: Video anomaly detection research has expanded rapidly with an emphasis on general models of normality intended to work across many different scenes.<n>This focus has shifted the field away from modeling the scene-specific and context-dependent nature of normal behavior.<n>We show that meaningful progress in VAD requires renewed focus on single-scene, spatially-aware, and explainable formulations.
• Score: 33.77002721234086
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Recent video anomaly detection research has expanded rapidly with an emphasis on general models of normality intended to work across many different scenes. While this focus has led to improvements in scalability and multi-scene generalization, it has also shifted the field away from modeling the scene-specific and context-dependent nature of normal behavior. Contemporary approaches frequently rely on video-level weak supervision and opaque pretrained representations from multi-modal large language models (MLLMs), which encourage models to respond to familiar semantic anomaly categories rather than to deviations from the normal patterns of a particular environment. This trend suppresses spatial localization, introduces semantic bias, and reduces anomaly detection to a form of action recognition. In this paper, we examine whether these prevailing formulations align with the core requirements of real-world VAD, which is typically performed within a single scene where normality is determined by local geometry, semantics, and activity patterns. Through targeted visual analyses and empirical evaluations, we demonstrate the practical consequences of these limitations and show that meaningful progress in VAD requires renewed focus on single-scene, spatially-aware, and explainable formulations that capture the nuanced structure of normality within individual environments.

Related papers

• Steering and Rectifying Latent Representation Manifolds in Frozen Multi-modal LLMs for Video Anomaly Detection [52.5174167737992]
  Video anomaly detection (VAD) aims to identify abnormal events in videos.<n>We propose SteerVAD, which advances MLLM-based VAD by shifting from passively reading to actively steering and rectifying internal representations.<n>Our method achieves state-of-the-art performance among tuning-free approaches requiring only 1% of training data.
  arXiv  Detail & Related papers  (2026-02-27T13:48:50Z)
• RefineVAD: Semantic-Guided Feature Recalibration for Weakly Supervised Video Anomaly Detection [2.770730728142587]
  Weakly-Supervised Video Anomaly Detection aims to identify anomalous events using only video-level labels.<n>Existing methods often oversimplify the anomaly space by treating all abnormal events as a single category.<n>We propose RefineVAD, a novel framework that mimics this dual-process reasoning.
  arXiv  Detail & Related papers  (2025-11-17T10:15:34Z)
• Learning to Tell Apart: Weakly Supervised Video Anomaly Detection via Disentangled Semantic Alignment [47.507511439028754]
  We propose a novel Disentangled Semantic Alignment Network (DSANet) to explicitly separate abnormal and normal features from coarse-grained and fine-grained aspects.<n>At the coarse-grained level, we introduce a self-guided normality modeling branch that reconstructs input video features under the guidance of learned normal prototypes.<n>At the fine-grained level, we present a decoupled contrastive semantic alignment mechanism, which first temporally decomposes each video into event-centric and background-centric components.
  arXiv  Detail & Related papers  (2025-11-13T14:06:48Z)
• Action Hints: Semantic Typicality and Context Uniqueness for Generalizable Skeleton-based Video Anomaly Detection [39.65895515365808]
  We propose a novel zero-shot video anomaly detection framework, unlocking the potential of skeleton data via action typicality and uniqueness learning.<n>Our method achieves state-of-the-art results against skeleton-based methods on four large-scale VAD datasets.
  arXiv  Detail & Related papers  (2025-09-14T02:51:32Z)
• CRCL: Causal Representation Consistency Learning for Anomaly Detection in Surveillance Videos [40.63347505454772]
  Video Anomaly Detection (VAD) remains a fundamental yet formidable task in the video understanding community.<n>Previous methods only use easily collected regular events to model the inherent normality of normal spatial-temporal patterns in an unsupervised manner.<n>We propose Causal Consistency Representation Learning (CRCL) to implicitly mine potential scene-robust causal variable in unsupervised video normality learning.
  arXiv  Detail & Related papers  (2025-03-24T15:50:19Z)
• Video Anomaly Detection with Motion and Appearance Guided Patch Diffusion Model [15.67669626517481]
  We propose a novel patch-based diffusion model for video anomaly detection.<n>We introduce innovative motion and appearance conditions that are seamlessly integrated into our model.<n> Experimental results in four challenging video anomaly detection datasets substantiate the efficacy of our proposed approach.
  arXiv  Detail & Related papers  (2024-12-12T07:42:50Z)
• Video Anomaly Detection via Spatio-Temporal Pseudo-Anomaly Generation : A Unified Approach [49.995833831087175]
  This work proposes a novel method for generating generic Video-temporal PAs by inpainting a masked out region of an image. In addition, we present a simple unified framework to detect real-world anomalies under the OCC setting. Our method performs on par with other existing state-of-the-art PAs generation and reconstruction based methods under the OCC setting.
  arXiv  Detail & Related papers  (2023-11-27T13:14:06Z)
• Open-Vocabulary Video Anomaly Detection [57.552523669351636]
  Video anomaly detection (VAD) with weak supervision has achieved remarkable performance in utilizing video-level labels to discriminate whether a video frame is normal or abnormal. Recent studies attempt to tackle a more realistic setting, open-set VAD, which aims to detect unseen anomalies given seen anomalies and normal videos. This paper takes a step further and explores open-vocabulary video anomaly detection (OVVAD), in which we aim to leverage pre-trained large models to detect and categorize seen and unseen anomalies.
  arXiv  Detail & Related papers  (2023-11-13T02:54:17Z)
• Spatio-temporal predictive tasks for abnormal event detection in videos [60.02503434201552]
  We propose new constrained pretext tasks to learn object level normality patterns. Our approach consists in learning a mapping between down-scaled visual queries and their corresponding normal appearance and motion characteristics. Experiments on several benchmark datasets demonstrate the effectiveness of our approach to localize and track anomalies.
  arXiv  Detail & Related papers  (2022-10-27T19:45:12Z)
• Object-centric and memory-guided normality reconstruction for video anomaly detection [56.64792194894702]
  This paper addresses anomaly detection problem for videosurveillance. Due to the inherent rarity and heterogeneity of abnormal events, the problem is viewed as a normality modeling strategy. Our model learns object-centric normal patterns without seeing anomalous samples during training.
  arXiv  Detail & Related papers  (2022-03-07T19:28:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.