mlsanityData to 14 Oct 2026

Improving Multi-Person Pose Tracking with A Confidence Network

arXiv 2310.18920 ↗First posted 29 Oct 2023cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

Human pose estimation and tracking are fundamental tasks for understanding human behaviors in videos. Existing top-down framework-based methods usually perform three-stage tasks: human detection, pose estimation and tracking. Although promising results have been achieved, these methods rely heavily on high-performance detectors and may fail to track persons who are occluded or miss-detected. To overcome these problems, in this paper, we develop a novel keypoint confidence network and a tracking pipeline to improve human detection and pose estimation in top-down approaches. Specifically, the keypoint confidence network is designed to determine whether each keypoint is occluded, and it is incorporated into the pose estimation module. In the tracking pipeline, we propose the Bbox-revision module to reduce missing detection and the ID-retrieve module to correct lost trajectories, improving the performance of the detection stage. Experimental results show that our approach is universal in human detection and pose estimation, achieving state-of-the-art performance on both PoseTrack 2017 and 2018 datasets.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 52 of its 72 references that are in the map. First posted on arXiv 29 Oct 2023.

Builds on

52 of 72 references.

References · 52

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020End-to-End Object Detection with Transformerscited by 7,414
  3. 2017Mask R-CNNcited by 7,277
  4. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,852
  5. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,415
  6. 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,385
  7. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  8. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,064
  9. 2019EfficientDet: Scalable and Efficient Object Detectioncited by 1,020
  10. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 915
  11. 2019Object Detection in 20 Years: A Surveycited by 531
  12. 2018Object Detection with Deep Learning: A Reviewcited by 528
38 more
  1. 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
  2. 2019Hybrid Task Cascade for Instance Segmentationcited by 481
  3. 2022ViTPose: Simple Vision Transformer Baselines for Human Pose Estimationcited by 456
  4. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
  5. 2016RMPE: Regional Multi-person Pose Estimationcited by 340
  6. 2016Convolutional Pose Machinescited by 325
  7. 2013DeepPose: Human Pose Estimation via Deep Neural Networkscited by 305
  8. 2014Efficient Object Localization Using Convolutional Networkscited by 227
  9. 2016Speed/accuracy trade-offs for modern convolutional object detectorscited by 198
  10. 2017Towards Accurate Multi-person Pose Estimation in the Wildcited by 131
  11. 2014Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimationcited by 129
  12. 2015Human Pose Estimation with Iterative Error Feedbackcited by 121
  13. 2019PifPaf: Composite Fields for Human Pose Estimationcited by 120
  14. 2015DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimationcited by 117
  15. 2016DeeperCut: A Deeper, Stronger, and Faster Multi-Person Pose Estimation Modelcited by 96
  16. 2018Pose Flow: Efficient Online Pose Trackingcited by 80
  17. 2021CBNet: A Composite Backbone Network Architecture for Object Detectioncited by 77
  18. 2015Flowing ConvNets for Human Pose Estimation in Videoscited by 55
  19. 2021OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Associationcited by 55
  20. 2016Human pose estimation via Convolutional Part Heatmap Regressioncited by 51
  21. 2017Detect-and-Track: Efficient Pose Estimation in Videoscited by 51
  22. 2020Combining detection and tracking for human pose estimation in videoscited by 49
  23. 2017Thin-Slicing Network: A Deep Structured Model for Pose Estimation in Videoscited by 40
  24. 2019Learning Temporal Pose Estimation from Sparsely-Labeled Videoscited by 39
  25. 2019Multi-person Articulated Tracking with Spatial and Temporal Embeddingscited by 38
  26. 2021Learning Dynamics via Graph Neural Networks for Human Pose Estimation and Trackingcited by 37
  27. 2018Efficient Online Multi-Person 2D Pose Tracking with Recurrent Spatio-Temporal Affinity Fieldscited by 32
  28. 2021Dual-Awareness Attention for Few-Shot Object Detectioncited by 29
  29. 2016ArtTrack: Articulated Multi-person Tracking in the Wildcited by 27
  30. 201915 Keypoints Is All You Needcited by 23
  31. 2020Toward fast and accurate human pose estimation via soft-gated skip connectionscited by 22
  32. 2020Self-supervised Keypoint Correspondences for Multi-Person Pose Estimation and Tracking in Videoscited by 22
  33. 2018Multi-Domain Pose Network for Multi-Person Pose Estimation and Trackingcited by 21
  34. 2016Multi-Person Pose Estimation with Local Joint-to-Person Associationscited by 18
  35. 2017Knowledge-Guided Deep Fractal Neural Networks for Human Pose Estimationcited by 18
  36. 2019LightTrack: A Generic Framework for Online Top-Down Human Pose Trackingcited by 16
  37. 2015Bottom-Up and Top-Down Reasoning with Hierarchical Rectified Gaussianscited by 14
  38. 2019Pose estimator and tracker using temporal flow maps for limbscited by 13

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 1.

3 papers.

  1. 2024Joint-Motion Mutual Learning for Pose Estimation in Videoscited by 7
  2. 2025Multi-Grained Feature Pruning for Video-Based Human Pose Estimationcited by 0
  3. 2026NCSTR: Node-Centric Decoupled Spatio-Temporal Reasoning for Video-based Human Pose Estimationcited by 0