mlsanityData to 7 Oct 2026

Distilling Aggregated Knowledge for Weakly-Supervised Video Anomaly Detection

arXiv 2406.02831 ↗First posted 5 Jun 2024cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

Video anomaly detection aims to develop automated models capable of identifying abnormal events in surveillance videos. The benchmark setup for this task is extremely challenging due to: i) the limited size of the training sets, ii) weak supervision provided in terms of video-level labels, and iii) intrinsic class imbalance induced by the scarcity of abnormal events. In this work, we show that distilling knowledge from aggregated representations of multiple backbones into a single-backbone Student model achieves state-of-the-art performance. In particular, we develop a bi-level distillation approach along with a novel disentangled cross-attention-based feature aggregation network. Our proposed approach, DAKD (Distilling Aggregated Knowledge with Disentangled Attention), demonstrates superior performance compared to existing methods across multiple benchmark datasets. Notably, we achieve significant improvements of 1.36%, 0.78%, and 7.02% on the UCF-Crime, ShanghaiTech, and XD-Violence datasets, respectively.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 30 of its 42 references that are in the map. First posted on arXiv 5 Jun 2024.

Builds on

30 of 42 references.

References · 30

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  4. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  5. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,259
  6. 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,157
  7. 2014FitNets: Hints for Thin Deep Netscited by 1,619
  8. 2016Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfercited by 1,059
  9. 2019Contrastive Representation Distillationcited by 734
  10. 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 675
  11. 2018Real-world Anomaly Detection in Surveillance Videoscited by 570
  12. 2017Future Frame Prediction for Anomaly Detection -- A New Baselinecited by 391
18 more
  1. 2020Learning Memory-guided Normality for Anomaly Detectioncited by 278
  2. 2016Learning Temporal Regularity in Video Sequencescited by 254
  3. 2018Knowledge Transfer via Distillation of Activation Boundaries Formed by Hidden Neuronscited by 235
  4. 2020Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervisioncited by 235
  5. 2021Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learningcited by 226
  6. 2022Frozen CLIP Models are Efficient Video Learnerscited by 181
  7. 2019Graph Convolutional Label Noise Cleaner: Train a Plug-and-play Action Classifier for Anomaly Detectioncited by 171
  8. 2020Anomaly Detection in Video via Self-Supervised and Multi-Task Learningcited by 147
  9. 2021MIST: Multiple Instance Self-Training Framework for Video Anomaly Detectioncited by 137
  10. 2021A Hybrid Video Anomaly Detection Framework via Memory-Augmented Flow Reconstruction and Flow-Guided Frame Predictioncited by 129
  11. 2022MGFN: Magnitude-Contrastive Glance-and-Focus Network for Weakly-Supervised Video Anomaly Detectioncited by 87
  12. 2020CLAWS: Clustering Assisted Weakly Supervised Learning with Normalcy Suppression for Anomalous Event Detectioncited by 79
  13. 2015Learning Deep Representations of Appearance and Motion for Anomalous Event Detectioncited by 75
  14. 2020Self-Distillation as Instance-Specific Label Smoothingcited by 71
  15. 2020Cloze Test Helps: Effective Video Anomaly Detection via Learning to Complete Video Eventscited by 70
  16. 2019GODS: Generalized One-class Discriminative Subspaces for Anomaly Detectioncited by 64
  17. 2019Future Frame Prediction Using Convolutional VRNN for Anomaly Detectioncited by 27
  18. 2018S3D: Single Shot multi-Span Detector via Fully 3D Convolutional Networkscited by 16

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Benchmarking Compact VLMs for Clip-Level Surveillance Anomaly Detection Under Weak Supervisioncited by 1
  2. 2026Is Video Anomaly Detection Misframed? Evidence from LLM-Based and Multi-Scene Modelscited by 1
  3. 2026Look Inside Each Video: Rethinking How Video Anomaly Detection Is Evaluatedcited by 0