mlsanityData to 7 Oct 2026

A Coarse-to-Fine Pseudo-Labeling (C2FPL) Framework for Unsupervised Video Anomaly Detection

arXiv 2310.17650 ↗First posted 26 Oct 2023cs.CV cs.LGcited by 13

Not on the map. Why?

Abstract (arXiv)

Detection of anomalous events in videos is an important problem in applications such as surveillance. Video anomaly detection (VAD) is well-studied in the one-class classification (OCC) and weakly supervised (WS) settings. However, fully unsupervised (US) video anomaly detection methods, which learn a complete system without any annotation or human supervision, have not been explored in depth. This is because the lack of any ground truth annotations significantly increases the magnitude of the VAD challenge. To address this challenge, we propose a simple-but-effective two-stage pseudo-label generation framework that produces segment-level (normal/anomaly) pseudo-labels, which can be further used to train a segment-level anomaly detector in a supervised manner. The proposed coarse-to-fine pseudo-label (C2FPL) generator employs carefully-designed hierarchical divisive clustering and statistical hypothesis testing to identify anomalous video segments from a set of completely unlabeled videos. The trained anomaly detector can be directly applied on segments of an unseen test video to obtain segment-level, and subsequently, frame-level anomaly predictions. Extensive studies on two large-scale public-domain datasets, UCF-Crime and XD-Violence, demonstrate that the proposed unsupervised approach achieves superior performance compared to all existing OCC and US methods , while yielding comparable performance to the state-of-the-art WS methods.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 25 of its 39 references that are in the map. First posted on arXiv 26 Oct 2023.

Builds on

25 of 39 references.

References · 25

  1. 2017Squeeze-and-Excitation Networkscited by 4,763
  2. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,259
  3. 2018Real-world Anomaly Detection in Surveillance Videoscited by 570
  4. 2017Residual Attention Network for Image Classificationcited by 385
  5. 2016Learning Temporal Regularity in Video Sequencescited by 254
  6. 2020Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervisioncited by 235
  7. 2021Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learningcited by 226
  8. 2019Graph Convolutional Label Noise Cleaner: Train a Plug-and-play Action Classifier for Anomaly Detectioncited by 171
  9. 2021MIST: Multiple Instance Self-Training Framework for Video Anomaly Detectioncited by 137
  10. 2020Old is Gold: Redefining the Adversarially Learned One-Class Classifier Training Paradigmcited by 115
  11. 2019Learning Regularity in Skeleton Trajectories for Anomaly Detection in Videoscited by 103
  12. 2022Generative Cooperative Learning for Unsupervised Video Anomaly Detectioncited by 102
13 more
  1. 2018Data Augmentation using Random Image Cropping and Patching for Deep CNNscited by 87
  2. 2020CLAWS: Clustering Assisted Weakly Supervised Learning with Normalcy Suppression for Anomalous Event Detectioncited by 79
  3. 2014Toward Supervised Anomaly Detectioncited by 73
  4. 2019GODS: Generalized One-class Discriminative Subspaces for Anomaly Detectioncited by 64
  5. 2022Part-based Pseudo Label Refinement for Unsupervised Person Re-identificationcited by 59
  6. 2021Refining Pseudo Labels with Clustering Consensus over Generations for Unsupervised Object Re-identificationcited by 45
  7. 2021Anomaly Detection in Medical Imaging -- A Mini Reviewcited by 44
  8. 2018Subspace Support Vector Data Descriptioncited by 31
  9. 2021Semi-orthogonal Embedding for Efficient Unsupervised Anomaly Segmentationcited by 26
  10. 2022DyAnNet: A Scene Dynamicity Guided Self-Trained Video Anomaly Detection Networkcited by 26
  11. 2022Stabilizing Adversarially Learned One-Class Novelty Detection Using Pseudo Anomaliescited by 14
  12. 2021Cleaning Label Noise with Clusters for Minimally Supervised Anomaly Detectioncited by 13
  13. 2021Adaptive Pseudo-Label Refinement by Negative Ensemble Learning for Source-Free Unsupervised Domain Adaptationcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 5; 2025: 6; 2026: 2.

13 papers.

Sort:

By area:

  1. 2024Deep Learning for Video Anomaly Detection: A Reviewcited by 27
  2. 2024Collaborative Learning of Anomalies with Privacy (CLAP) for Unsupervised Video Anomaly Detection: A New Baselinecited by 17
  3. 2024FUN-AD: Fully Unsupervised Learning for Anomaly Detection with Noisy Training Datacited by 8
  4. 2024Interleaving One-Class and Weakly-Supervised Models with Adaptive Thresholding for Unsupervised Video Anomaly Detectioncited by 5
  5. 2025Procedural Mistake Detection via Action Effect Modelingcited by 5
  6. 2025Self-supervised Learning of Echocardiographic Video Representations via Online Cluster Distillationcited by 4
  7. 2025The Evolution of Video Anomaly Detection: A Unified Framework from DNN to MLLMcited by 4
  8. 2025A Survey on Video Anomaly Detection via Deep Learning: Human, Vehicle, and Environmentcited by 4
  9. 2026Is Video Anomaly Detection Misframed? Evidence from LLM-Based and Multi-Scene Modelscited by 1
  10. 2024Temporal Divide-and-Conquer Anomaly Actions Localization in Semi-Supervised Videos with Hierarchical Transformercited by 0
  11. 2025Exploring a Hybrid Deep Learning Approach for Anomaly Detection in Mental Healthcare Provider Billing: Addressing Label Scarcity through Semi-Supervised Anomaly Detectioncited by 0
  12. 2025RobustA: Robust Anomaly Detection in Multimodal Datacited by 0
1 more
  1. 2026Geometry-Aware Semantic Reasoning for Training Free Video Anomaly Detectioncited by 0