mlsanityData to 7 Oct 2026

3D Human Pose Estimation with Spatial and Temporal Transformers

arXiv 2103.10455 ↗First posted 18 Mar 2021cs.CV cs.AI cs.HCcited by 271

Not on the map. Why?

Abstract (arXiv)

Transformer architectures have become the model of choice in natural language processing and are now being introduced into computer vision tasks such as image classification, object detection, and semantic segmentation. However, in the field of human pose estimation, convolutional architectures still remain dominant. In this work, we present PoseFormer, a purely transformer-based approach for 3D human pose estimation in videos without convolutional architectures involved. Inspired by recent developments in vision transformers, we design a spatial-temporal transformer structure to comprehensively model the human joint relations within each frame as well as the temporal correlations across frames, then output an accurate 3D human pose of the center frame. We quantitatively and qualitatively evaluate our method on two popular and standard benchmark datasets: Human3.6M and MPI-INF-3DHP. Extensive experiments show that PoseFormer achieves state-of-the-art performance on both datasets. Code is available at urlhttps://github.com/zczcwh/PoseFormer

Key facts. Cited by 271 papers in the map (data through 7 Oct 2026). Builds on 34 of its 50 references that are in the map. First posted on arXiv 18 Mar 2021.

Builds on

34 of 50 references.

References · 34

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  5. 2020End-to-End Object Detection with Transformerscited by 7,384
  6. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  7. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  8. 2020Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformerscited by 1,368
  9. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  10. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,061
  11. 2021Transformers in Vision: A Surveycited by 1,009
  12. 2016Deep Networks with Stochastic Depthcited by 973
22 more
  1. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 493
  2. 2020End-to-End Human Pose and Mesh Reconstruction with Transformerscited by 417
  3. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
  4. 20183D human pose estimation in video with temporal convolutions and semi-supervised trainingcited by 401
  5. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
  6. 2016RMPE: Regional Multi-person Pose Estimationcited by 340
  7. 2019Learning Deep Transformer Models for Machine Translationcited by 309
  8. 2020I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Imagecited by 274
  9. 2019Cross-Modal Self-Attention Network for Referring Image Segmentationcited by 263
  10. 2018Adaptive Input Representations for Neural Language Modelingcited by 226
  11. 2019Semantic Graph Convolutional Networks for 3D Human Pose Regressioncited by 204
  12. 2017VNect: Real-time 3D Human Pose Estimation with a Single RGB Cameracited by 129
  13. 2017Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approachcited by 114
  14. 2020Towards Deeper Graph Neural Networks with Differentiable Group Normalizationcited by 113
  15. 2018Ordinal Depth Supervision for 3D Human Pose Estimationcited by 107
  16. 2020SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approachcited by 94
  17. 2017Exploiting temporal information for 3D pose estimationcited by 89
  18. 2020Motion Guided 3D Pose Estimation from Videoscited by 85
  19. 2020Cascaded deep monocular 3D human pose estimation with evolutionary training datacited by 80
  20. 2019Chirality Nets for Human Pose Regressioncited by 31
  21. 2019Trajectory Space Factorization for Deep Video-Based 3D Human Pose Estimationcited by 30
  22. 2020Anatomy-aware 3D Human Pose Estimation with Bone-based Pose Decompositioncited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 13; 2022: 54; 2023: 71; 2024: 46; 2025: 53; 2026: 34.

271 papers.

Sort:

By area:

  1. 2023SkySense: A Multi-Modal Remote Sensing Foundation Model Towards Universal Interpretation for Earth Observation Imagerycited by 202
  2. 2022MotionBERT: A Unified Perspective on Learning Human Motion Representationscited by 188
  3. 2022MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Videocited by 158
  4. 2021MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimationcited by 151
  5. 2022AvatarPoser: Articulated Full-Body Pose Tracking from Sparse Motion Sensingcited by 107
  6. 2021TokenPose: Learning Keypoint Tokens for Human Pose Estimationcited by 106
  7. 2022Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformercited by 99
  8. 2022DiffPose: Toward More Reliable 3D Pose Estimationcited by 99
  9. 2022HandOccNet: Occlusion-Robust 3D Hand Mesh Estimation Networkcited by 95
  10. 2021Exploiting Temporal Contexts with Strided Transformer for 3D Human Pose Estimationcited by 94
  11. 2023PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimationcited by 91
  12. 2022Cross-Attention of Disentangled Modalities for 3D Human Mesh Recovery with Transformerscited by 81
38 more
  1. 2023Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregationcited by 81
  2. 2022P-STMO: Pre-Trained Spatial Temporal Many-to-One Model for 3D Human Pose Estimationcited by 80
  3. 2022MST++: Multi-stage Spectral-wise Transformer for Efficient Spectral Reconstructioncited by 72
  4. 2022Coarse-to-Fine Sparse Transformer for Hyperspectral Image Reconstructioncited by 67
  5. 2022Degradation-Aware Unfolding Half-Shuffle Transformer for Spectral Compressive Imagingcited by 66
  6. 2021SmoothNet: A Plug-and-Play Network for Refining Human Poses in Videoscited by 64
  7. 2023MotionAGFormer: Enhancing 3D Human Pose Estimation with a Transformer-GCNFormer Networkcited by 62
  8. 2022GFPose: Learning 3D Human Pose Prior with Gradient Fieldscited by 57
  9. 2023Revisiting Token Pruning for Object Detection and Instance Segmentationcited by 50
  10. 2023GLA-GCN: Global-local Adaptive Graph Convolutional Network for 3D Human Pose Estimation from Monocular Videocited by 46
  11. 2023Realistic Full-Body Tracking from Sparse Observations via Joint-Level Modelingcited by 41
  12. 2023EmotionGesture: Audio-Driven Diverse Emotional Co-Speech 3D Gesture Generationcited by 40
  13. 2022Faster VoxelPose: Real-time 3D Human Pose Estimation by Orthographic Projectioncited by 39
  14. 2023Bringing Inputs to Shared Domains for 3D Interacting Hands Recovery in the Wildcited by 36
  15. 2022Global-local Motion Transformer for Unsupervised Skeleton-based Action Learningcited by 33
  16. 2022Uplift and Upsample: Efficient 3D Human Pose Estimation with Uplifting Transformerscited by 33
  17. 2024KTPFormer: Kinematics and Trajectory Prior Knowledge-Enhanced Transformer for 3D Human Pose Estimationcited by 33
  18. 2021TransFusion: Cross-view Fusion with Transformer for 3D Human Pose Estimationcited by 32
  19. 2023PSVT: End-to-End Multi-person 3D Pose and Shape Estimation with Progressive Video Transformerscited by 31
  20. 2023POTTER: Pooling Attention Transformer for Efficient Human Mesh Recoverycited by 31
  21. 2021End-to-End Trainable Multi-Instance Pose Estimation with Transformerscited by 30
  22. 2022DeciWatch: A Simple Baseline for 10x Efficient 2D and 3D Pose Estimationcited by 29
  23. 2022DiffuPose: Monocular 3D Human Pose Estimation via Denoising Diffusion Probabilistic Modelcited by 29
  24. 2022Human Joint Kinematics Diffusion-Refinement for Stochastic Motion Predictioncited by 28
  25. 2022Holistic Interaction Transformer Network for Action Detectioncited by 28
  26. 2023DARE-GRAM : Unsupervised Domain Adaptation Regression by Aligning Inverse Gram Matricescited by 28
  27. 2022PPT: token-Pruned Pose Transformer for monocular and multi-view human pose estimationcited by 27
  28. 2022Ray3D: ray-based 3D human pose estimation for monocular absolute 3D localizationcited by 25
  29. 2023Co-Evolution of Pose and Mesh for 3D Human Body Estimation from Videocited by 25
  30. 2023Back to Optimization: Diffusion-based Zero-Shot 3D Human Pose Estimationcited by 24
  31. 2022Weakly Supervised 3D Multi-person Pose Estimation for Large-scale Scenes based on Monocular Camera and Single LiDARcited by 23
  32. 2023HDFormer: High-order Directed Transformer for 3D Human Pose Estimationcited by 23
  33. 20233D Human Pose Perception from Egocentric Stereo Videoscited by 23
  34. 2021Regularity Learning via Explicit Distribution Modeling for Skeletal Video Anomaly Detectioncited by 22
  35. 2024HMD-Poser: On-Device Real-time Human Motion Tracking from Scalable Sparse Observationscited by 22
  36. 2021A Lightweight Graph Transformer Network for Human Mesh Reconstruction from 2D Human Posecited by 21
  37. 2022GraphMLP: A Graph MLP-Like Architecture for 3D Human Pose Estimationcited by 21
  38. 20223D Vision with Transformers: A Surveycited by 21

50 most cited of 271 All 271 (JSON)