mlsanityData to 7 Oct 2026

Contracting Skeletal Kinematics for Human-Related Video Anomaly Detection

arXiv 2301.09489 ↗First posted 23 Jan 2023cs.CVcited by 13

Not on the map. Why?

Abstract (arXiv)

Detecting the anomaly of human behavior is paramount to timely recognizing endangering situations, such as street fights or elderly falls. However, anomaly detection is complex since anomalous events are rare and because it is an open set recognition task, i.e., what is anomalous at inference has not been observed at training. We propose COSKAD, a novel model that encodes skeletal human motion by a graph convolutional network and learns to COntract SKeletal kinematic embeddings onto a latent hypersphere of minimum volume for Video Anomaly Detection. We propose three latent spaces: the commonly-adopted Euclidean and the novel spherical and hyperbolic. All variants outperform the state-of-the-art on the most recent UBnormal dataset, for which we contribute a human-related version with annotated skeletons. COSKAD sets a new state-of-the-art on the human-related versions of ShanghaiTech Campus and CUHK Avenue, with performance comparable to video-based methods. Source code and dataset will be released upon acceptance.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 28 of its 61 references that are in the map. First posted on arXiv 23 Jan 2023.

Builds on

28 of 61 references.

References · 28

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  4. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  5. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  6. 2021Is Space-Time Attention All You Need for Video Understanding?cited by 1,609
  7. 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,199
  8. 2018Real-world Anomaly Detection in Surveillance Videoscited by 570
  9. 2019Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detectioncited by 560
  10. 2017Future Frame Prediction for Anomaly Detection -- A New Baselinecited by 391
  11. 2016RMPE: Regional Multi-person Pose Estimationcited by 340
  12. 2020Learning Memory-guided Normality for Anomaly Detectioncited by 278
16 more
  1. 2016Learning Temporal Regularity in Video Sequencescited by 254
  2. 2018Hyperspherical Variational Auto-Encoderscited by 188
  3. 2020Anomaly Detection in Video via Self-Supervised and Multi-Task Learningcited by 147
  4. 2019Learning Regularity in Skeleton Trajectories for Anomaly Detection in Videoscited by 103
  5. 2019Graph Embedded Pose Clustering for Anomaly Detectioncited by 95
  6. 2021UBnormal: New Benchmark for Supervised Open-Set Video Anomaly Detectioncited by 91
  7. 2021Constructing Stronger and Faster Baselines for Skeleton-based Action Recognitioncited by 87
  8. 2022Anomaly Detection in Autonomous Driving: A Surveycited by 87
  9. 2020A Background-Agnostic Framework with Adversarial Training for Abnormal Event Detection in Videocited by 85
  10. 2021Space-Time-Separable Graph Convolutional Network for Pose Forecastingcited by 84
  11. 2018Pose Flow: Efficient Online Pose Trackingcited by 80
  12. 2022Spatio-Temporal Gating-Adjacency GCN for Human Motion Predictioncited by 48
  13. 2022SSMTL++: Revisiting Self-Supervised Multi-Task Learning for Video Anomaly Detectioncited by 45
  14. 2022Pose Forecasting in Industrial Human-Robot Collaborationcited by 24
  15. 2020Multi-Scale One-Class Recurrent Neural Networks for Discrete Event Sequence Anomaly Detectioncited by 19
  16. 2022Are we certain it's anomalous?cited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 2; 2025: 5; 2026: 5.

13 papers.

Sort:

By area:

  1. 2024Compositional Entailment Learning for Hyperbolic Vision-Language Modelscited by 72
  2. 2023Multimodal Motion Conditioned Diffusion Model for Skeleton-based Video Anomaly Detectioncited by 42
  3. 2025Sequential keypoint density estimator: an overlooked baseline of skeleton-based video anomaly detectioncited by 7
  4. 2024Frequency-Guided Diffusion Model with Perturbation Training for Skeleton-Based Video Anomaly Detectioncited by 6
  5. 2026Bounding-Box Trajectories Matter for Video Anomaly Detectioncited by 3
  6. 2025Emotion Recognition from Skeleton Data: A Comprehensive Surveycited by 2
  7. 2025H2em: Learning Hierarchical Hyperbolic Embeddings for Compositional Zero-Shot Learningcited by 1
  8. 2026ARGENT: Adaptive Hierarchical Image-Text Representationscited by 1
  9. 2025Video Anomaly Detection with Contours -- A Studycited by 0
  10. 20253D Human-Human Interaction Anomaly Detectioncited by 0
  11. 2026Motion Semantics Guided Normalizing Flow for Privacy-Preserving Video Anomaly Detectioncited by 0
  12. 2026Reliability-Aware Prototype Calibration for Frozen Pose-Flow Video Anomaly Detectioncited by 0
1 more
  1. 2026STEP: Score-Based Temporal Energy for Human Pose Video Anomaly Detectioncited by 0