Glance, Scrutinize, and Think: Advancing Video Anomaly Detection from Training-Free to Agentic Reasoning

• URL: http://arxiv.org/abs/2608.11260v1
• Date: Fri, 07 Aug 2026 17:07:49 GMT
• Title: Glance, Scrutinize, and Think: Advancing Video Anomaly Detection from Training-Free to Agentic Reasoning
• Abstract summary: Video Anomaly Detection (VAD) aims to identify anomalous events and localize their temporal intervals.<n>Existing approaches exhibit a "when-what" dissociation: traditional methods localize when anomalies occur but lack semantic understanding.<n>We propose Glance then Scrutinize (GtS), a training-free framework using static and dynamic textual guidance.<n>Experiments show that GtS substantially surpasses training-free baselines, while the agentic model delivers both higher accuracy and faster inference.
• Score: 27.676141768874732
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Video Anomaly Detection (VAD) aims to identify anomalous events and localize their temporal intervals. Existing approaches exhibit a "when-what" dissociation: traditional DNN-based methods localize when anomalies occur but lack semantic understanding, whereas LLM-based methods explain what happens but neglect precise temporal grounding. We attribute this to the absence of a unified reasoning paradigm. Inspired by how humans inspect surveillance videos - glancing globally to form temporal hypotheses, scrutinizing suspicious segments, and thinking iteratively to correct errors - we study this global-to-local paradigm from two perspectives. We first propose Glance then Scrutinize (GtS), a training-free framework using static and dynamic textual guidance for coarse-to-fine anomaly grounding and understanding, balancing accuracy and speed. To break the ceiling imposed by frozen external modules, we further propose a tool-augmented agentic VAD method, where a multimodal large language model learns to invoke a video cropping tool, inspect densely resampled frames, and self-correct mislocalized hypotheses, via cold-start supervised fine-tuning followed by reinforcement learning with a joint answer-grounding reward. For training and evaluation, we extend our prior VAGU benchmark into VAGU-T (Video Anomaly Grounding, Understanding, and Thinking), comprising 7,567 real-world videos over 21 anomaly categories with human-validated grounding, explanations, QA pairs, and chain-of-thought tool-calling traces. We further introduce JeAUG, a metric jointly evaluating semantic interpretability and temporal precision. Experiments show that GtS substantially surpasses training-free baselines, while the agentic model delivers both higher accuracy and faster inference.

Related papers

• CoReVAD: A Contextual Reasoning Framework for Training-Free Video Anomaly Detection [0.14323566945483493]
  CoReVAD is a contextual reasoning framework for training-free video anomaly detection.<n>To mitigate noise in generative outputs, we introduce a Local Response Cleaning (LRC) module.<n>Experiments on UCF-Crime and XD-Violence demonstrate that CoReVAD achieves competitive performance among training-free methods.
  arXiv  Detail & Related papers  (2026-05-22T00:32:46Z)
• Foresee-to-Ground: From Predictive Temporal Perception to Evidence-Driven Reasoning for Video Temporal Grounding [86.37002814396674]
  We propose Foresee-to-Ground (F2G) for Video Temporal Grounding.<n>F2G integrates Predictive Temporal Perception with Evidence-Driven Reasoning.<n>It consistently improves grounding accuracy across diverse benchmarks.
  arXiv  Detail & Related papers  (2026-05-21T04:03:25Z)
• SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere [90.85001795656633]
  Video anomaly detection (VAD) aims to automatically identify events that deviate from normal patterns in untrimmed surveillance videos.<n>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.
  arXiv  Detail & Related papers  (2026-05-08T16:57:38Z)
• Spatiotemporal Sycophancy: Negation-Based Gaslighting in Video Large Language Models [54.76242207842981]
  We identify video syphancy, a failure mode in which Vid-LLMs retract correct, visually grounded judgments under negation-based gaslighting.<n>Rather than merely changing their answers, the models often fabricate unsupported temporal or spatial explanations to justify incorrect revisions.<n>We introduce GasVideo-1000, a curated benchmark designed to probe videotemporal sycophancy with clear visual grounding and temporal reasoning requirements.
  arXiv  Detail & Related papers  (2026-04-20T06:35:26Z)
• Reasoning-Guided Grounding: Elevating Video Anomaly Detection through Multimodal Large Language Models [2.8529525624646492]
  Video Anomaly Detection (VAD) has traditionally been framed as binary classification or outlier detection.<n>We propose VANGUARD, a framework that unifies anomaly classification, spatial grounding, and chain-of-thought reasoning.<n>On UCF-Crime, VANGUARD achieves 94% ROC-AUC with 84% F1 while simultaneously producing interpretable chain-of-thought explanations and spatial grounding of anomalous objects.
  arXiv  Detail & Related papers  (2026-04-07T20:15:15Z)
• Agentic Spatio-Temporal Grounding via Collaborative Reasoning [80.83158605034465]
  Temporal Video Grounding aims to retrieve thetemporal tube of a target object or person in a video given a text query.<n>We propose the Agentic Spatio-Temporal Grounder (ASTG) framework for the task of STVG towards an open-world and training-free scenario.<n>Specifically, two specialized agents SRA (Spatial Reasoning Agent) and TRA (Temporal Reasoning Agent) constructed leveraging on modern Multimoal Large Language Models (MLLMs)<n>Experiments on popular benchmarks demonstrate the superiority of the proposed approach where it outperforms existing weakly-supervised and zero-shot approaches by a margin
  arXiv  Detail & Related papers  (2026-02-10T10:16:27Z)
• Video-R2: Reinforcing Consistent and Grounded Reasoning in Multimodal Language Models [56.851611990473174]
  Reasoning over dynamic visual content remains a central challenge for large language models.<n>We propose a reinforcement learning approach that enhances both temporal precision and reasoning consistency.<n>The resulting model, Video R2, achieves consistently higher TAC, VAS, and accuracy across multiple benchmarks.
  arXiv  Detail & Related papers  (2025-11-28T18:59:58Z)
• A Unified Reasoning Framework for Holistic Zero-Shot Video Anomaly Analysis [64.42659342276117]
  Most video-anomaly research stops at frame-wise detection, offering little insight into why an event is abnormal.<n>Recent video anomaly localization and video anomaly understanding methods improve explainability but remain data-dependent and task-specific.<n>We propose a unified reasoning framework that bridges the gap between temporal detection, spatial localization, and textual explanation.
  arXiv  Detail & Related papers  (2025-11-02T14:49:08Z)
• Unlocking Vision-Language Models for Video Anomaly Detection via Fine-Grained Prompting [17.850029260662648]
  We propose ASK-Hint, a structured prompting framework for video anomaly detection.<n>Our approach organizes prompts into semantically coherent groups and formulates fine-grained guiding questions.<n>Experiments on UCF-Crime and XD-Violence show that ASK-Hint consistently improves AUC over prior baselines.
  arXiv  Detail & Related papers  (2025-10-02T16:06:31Z)
• VAGU & GtS: LLM-Based Benchmark and Framework for Joint Video Anomaly Grounding and Understanding [22.43740206690383]
  Video Anomaly Detection (VAD) aims to identify anomalous events in videos and accurately determine their time intervals.<n>VAGU is the first benchmark to integrate anomaly understanding and grounding.<n>We propose Glance then Scrutinize (GtS), a training-free framework guided by textual prompts.<n>We also propose the JeAUG metric, which jointly evaluates semantic interpretability and temporal precision.
  arXiv  Detail & Related papers  (2025-07-29T05:17:48Z)

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.