mlsanityData to 14 Oct 2026

A Gated Attention Transformer for Multi-Person Pose Tracking

arXiv 2306.05807 ↗First posted 9 Jun 2023cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

Multi-person pose tracking is an important element for many applications and requires to estimate the human poses of all persons in a video and to track them over time. The association of poses across frames remains an open research problem, in particular for online tracking methods, due to motion blur, crowded scenes and occlusions. To tackle the association challenge, we propose a Gated Attention Transformer. The core aspect of our model is the gating mechanism that automatically adapts the impact of appearance embeddings and embeddings based on temporal pose similarity in the attention layers. In order to re-identify persons that have been occluded, we incorporate a pose-conditioned re-identification network that provides initial embeddings and allows to match persons even if the number of visible joints differ between frames. We further propose a matching layer based on gated attention for pose-to-track association and duplicate removal. We evaluate our approach on PoseTrack 2018 and PoseTrack21.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 44 of its 54 references that are in the map. First posted on arXiv 9 Jun 2023.

Builds on

44 of 54 references.

References · 44

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  5. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  6. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  7. 2016Layer Normalizationcited by 5,669
  8. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  9. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  10. 2016Gaussian Error Linear Units (GELUs)cited by 3,502
  11. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,299
  12. 2017In Defense of the Triplet Loss for Person Re-Identificationcited by 786
32 more
  1. 2018Deformable ConvNets v2: More Deformable, Better Resultscited by 670
  2. 2020HOTA: A Higher Order Metric for Evaluating Multi-Object Trackingcited by 552
  3. 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
  4. 2020FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Trackingcited by 490
  5. 2019Hybrid Task Cascade for Instance Segmentationcited by 481
  6. 2017Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)cited by 473
  7. 2019Bag of Tricks and A Strong Baseline for Deep Person Re-identificationcited by 430
  8. 2019Cascade R-CNN: High Quality Object Detection and Instance Segmentationcited by 429
  9. 2019Tracking without bells and whistlescited by 382
  10. 2019Towards Real-Time Multi-Object Trackingcited by 311
  11. 2017PoseTrack: A Benchmark for Human Pose Estimation and Trackingcited by 173
  12. 2023Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Taskscited by 96
  13. 2018SNIPER: Efficient Multi-Scale Trainingcited by 88
  14. 2017A Pose-Sensitive Embedding for Person Re-Identification with Expanded Cross Neighborhood Re-Rankingcited by 74
  15. 2020Pose-guided Visible Part Matching for Occluded Person ReIDcited by 70
  16. 2019Perceive Where to Focus: Learning Visibility-aware Part-level Features for Partial Person Re-identificationcited by 56
  17. 2017Detect-and-Track: Efficient Pose Estimation in Videoscited by 51
  18. 2020Combining detection and tracking for human pose estimation in videoscited by 49
  19. 2017Pose Invariant Embedding for Deep Person Re-identificationcited by 47
  20. 2021On the Unreasonable Effectiveness of Centroids in Image Retrievalcited by 45
  21. 2018Multi-scale 3D Convolution Network for Video Based Person Re-Identificationcited by 41
  22. 2019Multi-person Articulated Tracking with Spatial and Temporal Embeddingscited by 38
  23. 2021Learning Dynamics via Graph Neural Networks for Human Pose Estimation and Trackingcited by 37
  24. 2018Efficient Online Multi-Person 2D Pose Tracking with Recurrent Spatio-Temporal Affinity Fieldscited by 32
  25. 2017GLAD: Global-Local-Alignment Descriptor for Pedestrian Retrievalcited by 25
  26. 201915 Keypoints Is All You Needcited by 23
  27. 2020Self-supervised Keypoint Correspondences for Multi-Person Pose Estimation and Tracking in Videoscited by 22
  28. 2021Learning to Track Instances without Video Annotationscited by 18
  29. 2019Pose estimator and tracker using temporal flow maps for limbscited by 13
  30. 2021Keypoint Message Passing for Video-based Person Re-Identificationcited by 8
  31. 2019Exploiting Offset-guided Network for Pose Estimation and Trackingcited by 3
  32. 2022DiP: Learning Discriminative Implicit Parts for Person Re-Identificationcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 0; 2025: 1; 2026: 1.

3 papers.

  1. 2023Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Surveycited by 6
  2. 2025Grounding Foundational Vision Models with 3D Human Poses for Robust Action Recognitioncited by 0
  3. 2026IMPose: Interactive Multi-person Pose Estimation with Dynamic Correction Propagationcited by 0