mlsanityData to 7 Oct 2026

Pose Flow: Efficient Online Pose Tracking

arXiv 1802.00977 ↗First posted 3 Feb 2018cs.CV cs.AIcited by 80

Not on the map. Why?

Abstract (arXiv)

Multi-person articulated pose tracking in unconstrained videos is an important while challenging problem. In this paper, going along the road of top-down approaches, we propose a decent and efficient pose tracker based on pose flows. First, we design an online optimization framework to build the association of cross-frame poses and form pose flows (PF-Builder). Second, a novel pose flow non-maximum suppression (PF-NMS) is designed to robustly reduce redundant pose flows and re-link temporal disjoint ones. Extensive experiments show that our method significantly outperforms best-reported results on two standard Pose Tracking datasets by 13 mAP 25 MOTA and 6 mAP 3 MOTA respectively. Moreover, in the case of working on detected poses in individual frames, the extra computation of pose tracker is very minor, guaranteeing online 10FPS tracking. Our source codes are made publicly available(https://github.com/YuliangXiu/PoseFlow).

Key facts. Cited by 80 papers in the map (data through 7 Oct 2026). First posted on arXiv 3 Feb 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 25; 2022: 21; 2023: 14; 2024: 13; 2025: 4; 2026: 3.

80 papers.

Sort:

By area:

  1. 2022Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Trackingcited by 345
  2. 2023Humans in 4D: Reconstructing and Tracking Humans with Transformerscited by 344
  3. 2022AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Timecited by 199
  4. 2022Capturing and Inferring Dense Full-Body Human-Scene Contactcited by 176
  5. 2023TRACE: 5D Temporal Regression of Avatars with Dynamic Cameras in 3D Environmentscited by 89
  6. 2022Normalizing Flows for Human Pose Anomaly Detectioncited by 59
  7. 2021Deep Dual Consecutive Network for Human Pose Estimationcited by 51
  8. 2021Recent Advances in Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspectivecited by 49
  9. 2021VoxelTrack: Multi-Person 3D Human Pose Estimation and Tracking in the Wildcited by 39
  10. 2021Learning Dynamics via Graph Neural Networks for Human Pose Estimation and Trackingcited by 37
  11. 2023DiffPose: SpatioTemporal Diffusion Model for Video-Based Human Pose Estimationcited by 36
  12. 2023On the Benefits of 3D Pose and Tracking for Human Action Recognitioncited by 32
38 more
  1. 2023FGAHOI: Fine-Grained Anchors for Human-Object Interaction Detectioncited by 30
  2. 2021ViPNAS: Efficient Video Pose Estimation via Neural Architecture Searchcited by 26
  3. 2022Temporal Feature Alignment and Mutual Information Maximization for Video-Based Human Pose Estimationcited by 24
  4. 2021Tracking People with 3D Representationscited by 22
  5. 2021Regularity Learning via Explicit Distribution Modeling for Skeletal Video Anomaly Detectioncited by 22
  6. 20222D Human Pose Estimation: A Surveycited by 21
  7. 2021Online Multi-Agent Forecasting with Interpretable Collaborative Graph Neural Networkcited by 20
  8. 2021Simple Baseline for Single Human Motion Forecastingcited by 18
  9. 2021Egocentric Human Trajectory Forecasting with a Wearable Camera and Multi-Modal Fusioncited by 17
  10. 2022Geometric Features Informed Multi-person Human-object Interaction Recognition in Videoscited by 17
  11. 2023Mutual Information-Based Temporal Difference Learning for Human Pose Estimation in Videocited by 17
  12. 2021Tracking People by Predicting 3D Appearance, Location & Posecited by 15
  13. 2021Behavior-Driven Synthesis of Human Dynamicscited by 14
  14. 2022Jointly Harnessing Prior Structures and Temporal Consistency for Sign Language Video Generationcited by 14
  15. 2023Human MotionFormer: Transferring Human Motions with Vision Transformerscited by 14
  16. 2021TrouSPI-Net: Spatio-temporal attention on parallel atrous convolutions and U-GRUs for skeletal pedestrian crossing predictioncited by 13
  17. 2022Delving Deep into One-Shot Skeleton-based Action Recognition with Diverse Occlusionscited by 13
  18. 2022Spatial-then-Temporal Self-Supervised Learning for Video Correspondencecited by 13
  19. 2023Contracting Skeletal Kinematics for Human-Related Video Anomaly Detectioncited by 13
  20. 2022Freeform Body Motion Generation from Speechcited by 11
  21. 2024Privacy-Preserving Video Anomaly Detection: A Surveycited by 11
  22. 2022OTPose: Occlusion-Aware Transformer for Pose Estimation in Sparsely-Labeled Videoscited by 10
  23. 2024Video-Based Human Pose Regression via Decoupled Space-Time Aggregationcited by 10
  24. 2022Spatial-Temporal Parallel Transformer for Arm-Hand Dynamic Estimationcited by 8
  25. 2021PGT: A Progressive Method for Training Models on Long Videoscited by 7
  26. 2022BiPOCO: Bi-Directional Trajectory Prediction with Pose Constraints for Pedestrian Anomaly Detectioncited by 7
  27. 2024DA-Flow: Dual Attention Normalizing Flow for Skeleton-based Video Anomaly Detectioncited by 7
  28. 2024Joint-Motion Mutual Learning for Pose Estimation in Videoscited by 7
  29. 2025Sequential keypoint density estimator: an overlooked baseline of skeleton-based video anomaly detectioncited by 7
  30. 2023Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Surveycited by 6
  31. 2024Deep Learning for Computer Vision based Activity Recognition and Fall Detection of the Elderly: a Systematic Reviewcited by 6
  32. 2021SIMPLE: SIngle-network with Mimicking and Point Learning for Bottom-up Human Pose Estimationcited by 5
  33. 2021HR-Crime: Human-Related Anomaly Detection in Surveillance Videoscited by 5
  34. 2023WASD: A Wilder Active Speaker Detection Datasetcited by 5
  35. 2024A Medical Low-Back Pain Physical Rehabilitation Dataset for Human Body Movement Analysiscited by 5
  36. 20213D Human Reconstruction in the Wild with Collaborative Aerial Camerascited by 4
  37. 2021View Birdification in the Crowd: Ground-Plane Localization from Perceived Movementscited by 4
  38. 2022ModSelect: Automatic Modality Selection for Synthetic-to-Real Domain Generalizationcited by 4

50 most cited of 80 All 80 (JSON)