mlsanityData to 7 Oct 2026

ComplexVAD: Detecting Interaction Anomalies in Video

arXiv 2501.09733 ↗First posted 16 Jan 2025cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

Existing video anomaly detection datasets are inadequate for representing complex anomalies that occur due to the interactions between objects. The absence of complex anomalies in previous video anomaly detection datasets affects research by shifting the focus onto simple anomalies. To address this problem, we introduce a new large-scale dataset: ComplexVAD. In addition, we propose a novel method to detect complex anomalies via modeling the interactions between objects using a scene graph with spatio-temporal attributes. With our proposed method and two other state-of-the-art video anomaly detection methods, we obtain baseline scores on ComplexVAD and demonstrate that our new method outperforms existing works.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 26 of its 39 references that are in the map. First posted on arXiv 16 Jan 2025.

Builds on

26 of 39 references.

References · 26

  1. 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,646
  2. 2021ByteTrack: Multi-Object Tracking by Associating Every Detection Boxcited by 812
  3. 2018Real-world Anomaly Detection in Surveillance Videoscited by 570
  4. 2019Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detectioncited by 560
  5. 2017Future Frame Prediction for Anomaly Detection -- A New Baselinecited by 391
  6. 2016Learning Temporal Regularity in Video Sequencescited by 254
  7. 2020Anomaly Detection in Video via Self-Supervised and Multi-Task Learningcited by 147
  8. 2021A Hybrid Video Anomaly Detection Framework via Memory-Augmented Flow Reconstruction and Flow-Guided Frame Predictioncited by 129
  9. 2019Anomaly Detection in Video Sequence with Appearance-Motion Correspondencecited by 118
  10. 2018Object-centric Auto-encoders and Dummy Anomalies for Abnormal Event Detection in Videocited by 110
  11. 2021UBnormal: New Benchmark for Supervised Open-Set Video Anomaly Detectioncited by 91
  12. 2019Street Scene: A new dataset and evaluation protocol for video anomaly detectioncited by 89
14 more
  1. 2020A Background-Agnostic Framework with Adversarial Training for Abnormal Event Detection in Videocited by 85
  2. 2020Cloze Test Helps: Effective Video Anomaly Detection via Learning to Complete Video Eventscited by 70
  3. 2020Few-shot Scene-adaptive Anomaly Detectioncited by 62
  4. 2022Video Anomaly Detection by Solving Decoupled Spatio-Temporal Jigsaw Puzzlescited by 62
  5. 2019Multi-timescale Trajectory Prediction for Abnormal Human Activity Detectioncited by 59
  6. 2023Video Event Restoration Based on Keyframes for Video Anomaly Detectioncited by 54
  7. 2022SSMTL++: Revisiting Self-Supervised Multi-Task Learning for Video Anomaly Detectioncited by 45
  8. 2023Hierarchical Semantic Contrast for Scene-aware Video Anomaly Detectioncited by 39
  9. 2020Any-Shot Sequential Anomaly Detection in Surveillance Videoscited by 34
  10. 2022EVAL: Explainable Video Anomaly Localizationcited by 19
  11. 2021X-MAN: Explaining multiple sources of anomalies in videocited by 10
  12. 2022Adversarial Machine Learning Attacks Against Video Anomaly Detection Systemscited by 9
  13. 2021A Modular and Unified Framework for Detecting and Localizing Video Anomaliescited by 6
  14. 2021An Efficient Approach for Anomaly Detection in Traffic Videoscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 4.

7 papers.

  1. 2025LLM-Guided Agentic Object Detection for Open-World Understandingcited by 7
  2. 2025Leveraging Multimodal LLM Descriptions of Activity for Explainable Semi-Supervised Video Anomaly Detectioncited by 4
  3. 2026QVAD: A Question-Centric Agentic Framework for Efficient and Training-Free Video Anomaly Detectioncited by 1
  4. 2026Is Video Anomaly Detection Misframed? Evidence from LLM-Based and Multi-Scene Modelscited by 1
  5. 2025HyCoVAD: A Hybrid SSL-LLM Model for Complex Video Anomaly Detectioncited by 0
  6. 2026BUSSARD: Normalizing Flows for Bijective Universal Scene-Specific Anomalous Relationship Detectioncited by 0
  7. 2026SENSE-VAD: Sentient and Semantic Video Anomaly Detection for Autonomous Drivingcited by 0