mlsanityData to 14 Oct 2026

Hierarchical Semantic Contrast for Scene-aware Video Anomaly Detection

arXiv 2303.13051 ↗First posted 23 Mar 2023cs.CVcited by 39

Not on the map. Why?

Abstract (arXiv)

Increasing scene-awareness is a key challenge in video anomaly detection (VAD). In this work, we propose a hierarchical semantic contrast (HSC) method to learn a scene-aware VAD model from normal videos. We first incorporate foreground object and background scene features with high-level semantics by taking advantage of pre-trained video parsing models. Then, building upon the autoencoder-based reconstruction framework, we introduce both scene-level and object-level contrastive learning to enforce the encoded latent features to be compact within the same semantic classes while being separable across different classes. This hierarchical semantic contrast strategy helps to deal with the diversity of normal patterns and also increases their discrimination ability. Moreover, for the sake of tackling rare normal activities, we design a skeleton-based motion augmentation to increase samples and refine the model further. Extensive experiments on three public datasets and scene-dependent mixture datasets validate the effectiveness of our proposed method.

Key facts. Cited by 39 papers in the map (data through 14 Oct 2026). Builds on 48 of its 77 references that are in the map. First posted on arXiv 23 Mar 2023.

Builds on

48 of 77 references.

References · 48

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  3. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  4. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,223
  5. 2018YOLOv3: An Incremental Improvementcited by 2,659
  6. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,845
  7. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  8. 2020Prototypical Contrastive Learning of Unsupervised Representationscited by 640
  9. 2018Real-world Anomaly Detection in Surveillance Videoscited by 577
  10. 2019Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detectioncited by 564
  11. 2020FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Trackingcited by 490
  12. 2017Future Frame Prediction for Anomaly Detection -- A New Baselinecited by 391
36 more
  1. 2020Learning Memory-guided Normality for Anomaly Detectioncited by 278
  2. 2021Revisiting Skeleton-based Action Recognitioncited by 257
  3. 2016Learning Temporal Regularity in Video Sequencescited by 254
  4. 2021Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learningcited by 230
  5. 2020Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-IDcited by 212
  6. 2019Graph Convolutional Label Noise Cleaner: Train a Plug-and-play Action Classifier for Anomaly Detectioncited by 171
  7. 2020Anomaly Detection in Video via Self-Supervised and Multi-Task Learningcited by 148
  8. 2021MIST: Multiple Instance Self-Training Framework for Video Anomaly Detectioncited by 138
  9. 2021A Hybrid Video Anomaly Detection Framework via Memory-Augmented Flow Reconstruction and Flow-Guided Frame Predictioncited by 129
  10. 2019Anomaly Detection in Video Sequence with Appearance-Motion Correspondencecited by 118
  11. 2018Object-centric Auto-encoders and Dummy Anomalies for Abnormal Event Detection in Videocited by 111
  12. 2019Learning Regularity in Skeleton Trajectories for Anomaly Detection in Videoscited by 104
  13. 2022Generative Cooperative Learning for Unsupervised Video Anomaly Detectioncited by 102
  14. 2019Graph Embedded Pose Clustering for Anomaly Detectioncited by 95
  15. 2021Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-supervised Action Recognitioncited by 90
  16. 2020A Survey of Single-Scene Video Anomaly Detectioncited by 88
  17. 2020A Background-Agnostic Framework with Adversarial Training for Abnormal Event Detection in Videocited by 86
  18. 2021Weakly Supervised Semantic Segmentation by Pixel-to-Prototype Contrastcited by 85
  19. 2021Skeleton-Contrastive 3D Action Representation Learningcited by 76
  20. 2021Learning Normal Dynamics in Videos with Meta Prototype Networkcited by 71
  21. 2020Cloze Test Helps: Effective Video Anomaly Detection via Learning to Complete Video Eventscited by 70
  22. 2022Regional Semantic Contrast and Aggregation for Weakly Supervised Semantic Segmentationcited by 64
  23. 2020Few-shot Scene-adaptive Anomaly Detectioncited by 62
  24. 2020Robust Unsupervised Video Anomaly Detection by Multi-Path Frame Predictioncited by 42
  25. 2020Driver Anomaly Detection: A Dataset and Contrastive Learning Approachcited by 41
  26. 2018DOPING: Generative Data Augmentation for Unsupervised Anomaly Detection with GANcited by 34
  27. 2021Weakly-Supervised Spatio-Temporal Anomaly Detection in Surveillance Videocited by 32
  28. 2020Learning a distance function with a Siamese network to localize anomalies in videoscited by 31
  29. 2021Convolutional Transformer based Dual Discriminator Generative Adversarial Networks for Video Anomaly Detectioncited by 31
  30. 2018Detecting abnormal events in video using Narrowed Normality Clusterscited by 30
  31. 2017Training Adversarial Discriminators for Cross-channel Abnormal Event Detection in Crowdscited by 28
  32. 2021Deep Anomaly Discovery From Unlabeled Videos via Normality Advantage and Self-Paced Refinementcited by 21
  33. 2022Context Recovery and Knowledge Retrieval: A Novel Two-Stream Framework for Video Anomaly Detectioncited by 18
  34. 2021Learnable Locality-Sensitive Hashing for Video Anomaly Detectioncited by 17
  35. 2022Offline-Online Associated Camera-Aware Proxies for Unsupervised Person Re-identificationcited by 9
  36. 2022Hierarchical Semi-Supervised Contrastive Learning for Contamination-Resistant Anomaly Detectioncited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 6; 2024: 19; 2025: 7; 2026: 7.

39 papers.

Sort:

By area:

  1. 2024Harnessing Large Language Models for Training-free Video Anomaly Detectioncited by 87
  2. 2023Open-Vocabulary Video Anomaly Detectioncited by 57
  3. 2024Follow the Rules: Reasoning for Video Anomaly Detection with Large Language Modelscited by 57
  4. 2024Advancing Video Anomaly Detection: A Concise Review and a New Datasetcited by 49
  5. 2023Foundation Model Assisted Weakly Supervised Semantic Segmentationcited by 33
  6. 2024Deep Learning for Video Anomaly Detection: A Reviewcited by 27
  7. 2024Open-World Semantic Segmentation Including Class Similaritycited by 24
  8. 2024Video Anomaly Detection in 10 Years: A Survey and Outlookcited by 18
  9. 2024Context-aware Video Anomaly Detection in Long-Term Datasetscited by 11
  10. 2024Privacy-Preserving Video Anomaly Detection: A Surveycited by 11
  11. 2023Long-Short Temporal Co-Teaching for Weakly Supervised Video Anomaly Detectioncited by 10
  12. 2024VideoPatchCore: An Effective Method to Memorize Normality for Video Anomaly Detectioncited by 8
27 more
  1. 2025ComplexVAD: Detecting Interaction Anomalies in Videocited by 8
  2. 2024Dynamic Distinction Learning: Adaptive Pseudo Anomalies for Video Anomaly Detectioncited by 6
  3. 2024Vision-Language Models Assisted Unsupervised Video Anomaly Detectioncited by 6
  4. 2024Frequency-Guided Diffusion Model with Perturbation Training for Skeleton-Based Video Anomaly Detectioncited by 6
  5. 2024Interleaving One-Class and Weakly-Supervised Models with Adaptive Thresholding for Unsupervised Video Anomaly Detectioncited by 5
  6. 2024Exploiting Autoencoder's Weakness to Generate Pseudo Anomaliescited by 4
  7. 2025Autoregressive Denoising Score Matching is a Good Video Anomaly Detectorcited by 4
  8. 2025The Evolution of Video Anomaly Detection: A Unified Framework from DNN to MLLMcited by 4
  9. 2024IPAD: Industrial Process Anomaly Detection Datasetcited by 3
  10. 2024Multi-scale Bottleneck Transformer for Weakly Supervised Multimodal Violence Detectioncited by 3
  11. 2024Unveiling Context-Related Anomalies: Knowledge Graph Empowered Decoupling of Scene and Action for Human-Related Video Anomaly Detectioncited by 3
  12. 2025Detecting Contextual Anomalies by Discovering Consistent Spatial Regionscited by 3
  13. 2023Beyond the Benchmark: Detecting Diverse Anomalies in Videoscited by 1
  14. 2023A Lightweight Video Anomaly Detection Model with Weak Supervision and Adaptive Instance Selectioncited by 1
  15. 2024Towards Completeness: A Generalizable Action Proposal Generator for Zero-Shot Temporal Action Localizationcited by 1
  16. 2025Context-Aware Zero-Shot Anomaly Detection in Surveillance Using Contrastive and Predictive Spatiotemporal Modelingcited by 1
  17. 2025Action Hints: Semantic Typicality and Context Uniqueness for Generalizable Skeleton-based Video Anomaly Detectioncited by 1
  18. 2026PrismVAU: Prompt-Refined Inference System for Multimodal Video Anomaly Understandingcited by 1
  19. 2026Enhancing Weakly Supervised Multimodal Video Anomaly Detection through Text Guidancecited by 1
  20. 2026Benchmarking Compact VLMs for Clip-Level Surveillance Anomaly Detection Under Weak Supervisioncited by 1
  21. 2023A brief introduction to a framework named Multilevel Guidance-Exploration Networkcited by 0
  22. 2024Camera clustering for scalable stream-based active distillationcited by 0
  23. 2025PA-VAD: Diffusion-Based Pseudo-Only Video Anomaly Detection via Domain-Aligned Memory Updatescited by 0
  24. 2026Forward Consistency Learning with Gated Context Aggregation for Video Anomaly Detectioncited by 0
  25. 2026GridVAD: Open-Set Video Anomaly Detection via Spatial Reasoning over Stratified Frame Gridscited by 0
  26. 2026Privacy-Aware Video Anomaly Detection through Orthogonal Subspace Projectioncited by 0
  27. 2026Beyond Isolated Entities: Relation-Aware Multi-Entity Modeling for Unsupervised Video Anomaly Detectioncited by 0