Glance, Scrutinize, and Think: Advancing Video Anomaly Detection from Training-Free to Agentic Reasoning
Shibo Gao, Peipei Yang, Xu-Yao Zhang, Linlin Huang
cs.AI, cs.CV
Submitted: 2026-08-07
Updated: 2026-08-13
Comments: 34 pages, 8 figures, 8 tables. Journal extension of our AAAI 2026 paper (arXiv:2507.21507)
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- The Evolution of Video Anomaly Detection: A Unified Framework from DNN to MLLM
- Dual Memory Units with Uncertainty Regulation for Weakly Supervised Video Anomaly Detection
- VadCLIP: Adapting Vision-Language Models for Weakly Supervised Video Anomaly Detection
- VERA: Explainable Video Anomaly Detection via Verbalized Learning of Vision-Language Models
- Holmes-VAD: Towards Unbiased and Explainable Video Anomaly Detection via Multi-modal LLM
- Video Anomaly Detection and Explanation via Large Language Models
- Anomaly Heterogeneity Learning for Open-set Supervised Anomaly Detection
- VANE-Bench: Video Anomaly Evaluation Benchmark for Conversational LMMs
- AnyAnomaly: Zero-Shot Customizable Video Anomaly Detection with LVLM
- Pixel Reasoner: Incentivizing Pixel-Space Reasoning with Curiosity-Driven Reinforcement Learning
- DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning
- Video-Thinker: Sparking "Thinking with Videos" via Reinforcement Learning
- Ego-R1: Chain-of-Tool-Thought for Ultra-Long Egocentric Video Reasoning
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models
- MM-Eureka: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning
- VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model
- Multi-GRPO: Multi-Group Advantage Estimation for Text-to-Image Generation with Tree-Based Trajectories and Multiple Rewards
- Reinforced MLLM: A Survey on RL-Based Reasoning in Multimodal Large Language Models
- VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems