mlsanityData to 14 Oct 2026

Sherlock: Towards Multi-scene Video Abnormal Event Extraction and Localization via a Global-local Spatial-sensitive LLM

arXiv 2502.18863 ↗First posted 26 Feb 2025cs.CV cs.AIcited by 11

Not on the map. Why?

Abstract (arXiv)

Prior studies on Video Anomaly Detection (VAD) mainly focus on detecting whether each video frame is abnormal or not in the video, which largely ignore the structured video semantic information (i.e., what, when, and where does the abnormal event happen). With this in mind, we propose a new chat-paradigm Multi-scene Video Abnormal Event Extraction and Localization (M-VAE) task, aiming to extract the abnormal event quadruples (i.e., subject, event type, object, scene) and localize such event. Further, this paper believes that this new task faces two key challenges, i.e., global-local spatial modeling and global-local spatial balancing. To this end, this paper proposes a Global-local Spatial-sensitive Large Language Model (LLM) named Sherlock, i.e., acting like Sherlock Holmes to track down the criminal events, for this M-VAE task. Specifically, this model designs a Global-local Spatial-enhanced MoE (GSM) module and a Spatial Imbalance Regulator (SIR) to address the two challenges respectively. Extensive experiments on our M-VAE instruction dataset show the significant advantages of Sherlock over several advanced Video-LLMs. This justifies the importance of global-local spatial information for the M-VAE task and the effectiveness of Sherlock in capturing such information.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 27 of its 78 references that are in the map. First posted on arXiv 26 Feb 2025.

Builds on

27 of 78 references.

References · 27

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  2. 2016Layer Normalizationcited by 5,669
  3. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,565
  4. 2023Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understandingcited by 1,471
  5. 2023ImageBind: One Embedding Space To Bind Them Allcited by 1,175
  6. 2018Real-world Anomaly Detection in Surveillance Videoscited by 577
  7. 2019Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detectioncited by 564
  8. 2023Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understandingcited by 371
  9. 2016Visual Relationship Detection with Language Priorscited by 334
  10. 2023PandaGPT: One Model To Instruction-Follow Them Allcited by 334
  11. 2018Video Action Transformer Networkcited by 316
  12. 2016Learning Temporal Regularity in Video Sequencescited by 254
15 more
  1. 2023From Sparse to Soft Mixtures of Expertscited by 248
  2. 2020Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervisioncited by 238
  3. 2023Valley: Video Assistant with Large Language model Enhanced abilitYcited by 234
  4. 2021Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learningcited by 230
  5. 2023OneLLM: One Framework to Align All Modalities with Languagecited by 187
  6. 2019Graph Convolutional Label Noise Cleaner: Train a Plug-and-play Action Classifier for Anomaly Detectioncited by 171
  7. 2023VadCLIP: Adapting Vision-Language Models for Weakly Supervised Video Anomaly Detectioncited by 123
  8. 2017Visual Translation Embedding Network for Visual Relation Detectioncited by 112
  9. 2024Holmes-VAD: Towards Unbiased and Explainable Video Anomaly Detection via Multi-modal LLMcited by 64
  10. 2019RWF-2000: An Open Large Scale Video Database for Violence Detectioncited by 39
  11. 2023Video-GroundingDINO: Towards Open-Vocabulary Spatio-Temporal Video Groundingcited by 32
  12. 2022DiaASQ : A Benchmark of Conversational Aspect-based Sentiment Quadruple Analysiscited by 27
  13. 2017PPR-FCN: Weakly Supervised Visual Relation Detection via Parallel Pairwise R-FCNcited by 25
  14. 2019Anomaly Locality in Video Surveillancecited by 18
  15. 2024ManiFoundation Model for General-Purpose Robotic Manipulation of Contact Synthesis with Arbitrary Objects and Robotscited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 8.

11 papers.

  1. 2025Event Extraction in Large Language Modelcited by 5
  2. 2025CueBench: Advancing Unified Understanding of Context-Aware Video Anomalies in Real-Worldcited by 4
  3. 2026SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hyperspherecited by 2
  4. 2025Cerberus: Real-Time Video Anomaly Detection via Cascaded Vision-Language Modelscited by 1
  5. 2026Designing Multi-Robot Ground Video Sensemaking with Public Safety Professionalscited by 1
  6. 2026DeepSVU: Towards In-depth Security-oriented Video Understanding via Unified Physical-world Regularized MoEcited by 1
  7. 2026SRVAU-R1: Enhancing Video Anomaly Understanding via Reflection-Aware Learningcited by 0
  8. 2026From Structure to Synergy: A Survey of Vision-Language Perception Paradigm Evolution in Multimodal Large Language Modelscited by 0
  9. 2026EvoSherlock: Towards Agentic Lifelong Evolution for Unseen Long-Tailed Security-Critical Events in Videoscited by 0
  10. 2026Cog-VADU: A Training-Free Cognitive Reasoning Framework for Video Anomaly Detection and Understandingcited by 0
  11. 2026Learning Temporal Evidence Selection for Video Anomaly Understandingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Is Video Anomaly Detection Misframed? Evidence from LLM-Based and Multi-Scene Models
  2. 2025EventVAD: Training-Free Event-Aware Video Anomaly Detection
  3. 2025Aligning Effective Tokens with Video Anomaly in Large Language Models
  4. 2024VANE-Bench: Video Anomaly Evaluation Benchmark for Conversational LMMs
  5. 2024Harnessing Large Language Models for Training-free Video Anomaly Detection
  6. 2026Context-structured Video Anomaly Detection with Large Vision-Language Models
  7. 2025Text-guided Fine-Grained Video Anomaly Understanding
  8. 2024Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any Granularity