mlsanityData to 14 Oct 2026

Holistic Representation Learning for Multitask Trajectory Anomaly Detection

arXiv 2311.01851 ↗First posted 3 Nov 2023cs.CVcited by 15

Not on the map. Why?

Abstract (arXiv)

Video anomaly detection deals with the recognition of abnormal events in videos. Apart from the visual signal, video anomaly detection has also been addressed with the use of skeleton sequences. We propose a holistic representation of skeleton trajectories to learn expected motions across segments at different times. Our approach uses multitask learning to reconstruct any continuous unobserved temporal segment of the trajectory allowing the extrapolation of past or future segments and the interpolation of in-between segments. We use an end-to-end attention-based encoder-decoder. We encode temporally occluded trajectories, jointly learn latent representations of the occluded segments, and reconstruct trajectories based on expected motions across different temporal segments. Extensive experiments on three trajectory-based video anomaly detection datasets show the advantages and effectiveness of our approach with state-of-the-art results on anomaly detection in skeleton trajectories.

Key facts. Cited by 15 papers in the map (data through 14 Oct 2026). Builds on 39 of its 62 references that are in the map. First posted on arXiv 3 Nov 2023.

Builds on

39 of 62 references.

References · 39

  1. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  2. 2022VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Trainingcited by 1,322
  3. 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,209
  4. 2018Real-world Anomaly Detection in Surveillance Videoscited by 577
  5. 2017Future Frame Prediction for Anomaly Detection -- A New Baselinecited by 391
  6. 2021Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognitioncited by 322
  7. 2021Revisiting Skeleton-based Action Recognitioncited by 257
  8. 2016Learning Temporal Regularity in Video Sequencescited by 254
  9. 2021Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learningcited by 230
  10. 2022AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Timecited by 200
  11. 2020DLow: Diversifying Latent Flows for Diverse Human Motion Predictioncited by 185
  12. 2021VideoMoCo: Contrastive Video Representation Learning with Temporally Adversarial Examplescited by 154
27 more
  1. 2020Anomaly Detection in Video via Self-Supervised and Multi-Task Learningcited by 148
  2. 2021MIST: Multiple Instance Self-Training Framework for Video Anomaly Detectioncited by 138
  3. 2021TCLR: Temporal Contrastive Learning for Video Representationcited by 136
  4. 2019Learning Regularity in Skeleton Trajectories for Anomaly Detection in Videoscited by 104
  5. 2019Skip-GANomaly: Skip Connected and Adversarially Trained Encoder-Decoder Anomaly Detectioncited by 100
  6. 2020Skeleton-based Action Recognition via Spatial and Temporal Transformer Networkscited by 98
  7. 2019Graph Embedded Pose Clustering for Anomaly Detectioncited by 95
  8. 2017Abnormal Event Detection in Videos using Generative Adversarial Netscited by 82
  9. 2020Social NCE: Contrastive Learning of Socially-aware Motion Representationscited by 58
  10. 2021Learning the Predictability of the Futurecited by 49
  11. 2021On Exposing the Challenging Long Tail in Future Prediction of Traffic Actorscited by 48
  12. 2023Multimodal Motion Conditioned Diffusion Model for Skeleton-based Video Anomaly Detectioncited by 42
  13. 2021Anticipating human actions by correlating past with the future with Jaccard similarity measurescited by 36
  14. 2022Probabilistic Representations for Video Contrastive Learningcited by 34
  15. 2020JOLO-GCN: Mining Joint-Centered Light-Weight Information for Skeleton-Based Action Recognitioncited by 33
  16. 2020Unsupervised Contrastive Learning of Sound Event Representationscited by 32
  17. 2020Quo Vadis, Skeleton Action Recognition ?cited by 22
  18. 2020Multi-Scale One-Class Recurrent Neural Networks for Discrete Event Sequence Anomaly Detectioncited by 19
  19. 2022Spatio-Temporal Tuples Transformer for Skeleton-Based Action Recognitioncited by 17
  20. 2022TempCLR: Reconstructing Hands via Time-Coherent Contrastive Learningcited by 17
  21. 2022Action-based Contrastive Learning for Trajectory Predictioncited by 15
  22. 2023Self-Supervised Video Representation Learning via Latent Time Navigationcited by 11
  23. 2021Enriched Music Representations with Multiple Cross-modal Contrastive Learningcited by 10
  24. 2022Representing Spatial Trajectories as Distributionscited by 5
  25. 2018NHAD: Neuro-Fuzzy Based Horizontal Anomaly Detection In Online Social Networkscited by 4
  26. 2022Image-free Domain Generalization via CLIP for 3D Hand Pose Estimationcited by 4
  27. 2022Learning neural audio features without supervisioncited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 8; 2025: 3; 2026: 4.

15 papers.

Sort:

By area:

  1. 2024Deep Learning for Video Anomaly Detection: A Reviewcited by 27
  2. 2024Gazing Into Missteps: Leveraging Eye-Gaze for Unsupervised Mistake Detection in Egocentric Videos of Skilled Human Activitiescited by 15
  3. 2024Graph-Jigsaw Conditioned Diffusion Model for Skeleton-based Video Anomaly Detectioncited by 9
  4. 2024DA-Flow: Dual Attention Normalizing Flow for Skeleton-based Video Anomaly Detectioncited by 7
  5. 2024Vision-Language Models Assisted Unsupervised Video Anomaly Detectioncited by 6
  6. 2024Frequency-Guided Diffusion Model with Perturbation Training for Skeleton-Based Video Anomaly Detectioncited by 6
  7. 2025The Evolution of Video Anomaly Detection: A Unified Framework from DNN to MLLMcited by 4
  8. 2024Unveiling Context-Related Anomalies: Knowledge Graph Empowered Decoupling of Scene and Action for Human-Related Video Anomaly Detectioncited by 3
  9. 2026Bounding-Box Trajectories Matter for Video Anomaly Detectioncited by 3
  10. 2024Dual Conditioned Motion Diffusion for Pose-Based Video Anomaly Detectioncited by 1
  11. 2026Is Video Anomaly Detection Misframed? Evidence from LLM-Based and Multi-Scene Modelscited by 1
  12. 2025Vision-Based Mistake Analysis in Procedural Activities: A Review of Advances and Challengescited by 0
3 more
  1. 20253D Human-Human Interaction Anomaly Detectioncited by 0
  2. 2026Motion Semantics Guided Normalizing Flow for Privacy-Preserving Video Anomaly Detectioncited by 0
  3. 2026Reliability-Aware Prototype Calibration for Frozen Pose-Flow Video Anomaly Detectioncited by 0