mlsanityData to 14 Oct 2026

(Fusionformer):Exploiting the Joint Motion Synergy with Fusion Network Based On Transformer for 3D Human Pose Estimation

arXiv 2210.04006 ↗First posted 8 Oct 2022cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

For the current 3D human pose estimation task, a group of methods mainly learn the rules of 2D-3D projection from spatial and temporal correlation. However, earlier methods model the global features of the entire body joint in the time domain, but ignore the motion trajectory of individual joint. The recent work [29] considers that there are differences in motion between different joints and deals with the temporal relationship of each joint separately. However, we found that different joints show the same movement trends under some specific actions. Therefore, our proposed Fusionformer method introduces a self-trajectory module and a mutual-trajectory module based on the spatio-temporal module .After that, the global spatio-temporal features and local joint trajectory features are fused through a linear network in a parallel manner. To eliminate the influence of bad 2D poses on 3D projections, finally we also introduce a pose refinement network to balance the consistency of 3D projections. In addition, we evaluate the proposed method on two benchmark datasets (Human3.6M, MPI-INF-3DHP). Comparing our method with the baseline method poseformer, the results show an improvement of 2.4% MPJPE and 4.3% P-MPJPE on the Human3.6M dataset, respectively.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 31 of its 43 references that are in the map. First posted on arXiv 8 Oct 2022.

Builds on

31 of 43 references.

References · 31

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  5. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  6. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,064
  7. 2018Dual Attention Network for Scene Segmentationcited by 1,003
  8. 20183D human pose estimation in video with temporal convolutions and semi-supervised trainingcited by 403
  9. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
  10. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
  11. 2016RMPE: Regional Multi-person Pose Estimationcited by 340
  12. 2020I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Imagecited by 274
19 more
  1. 20213D Human Pose Estimation with Spatial and Temporal Transformerscited by 272
  2. 2017Integral Human Pose Regressioncited by 256
  3. 2022MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Videocited by 159
  4. 2021MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimationcited by 151
  5. 2017Compositional Human Pose Regressioncited by 124
  6. 2018Ordinal Depth Supervision for 3D Human Pose Estimationcited by 107
  7. 2021Graph Stacked Hourglass Networks for 3D Human Pose Estimationcited by 95
  8. 2020SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approachcited by 94
  9. 2021Exploiting Temporal Contexts with Strided Transformer for 3D Human Pose Estimationcited by 94
  10. 2019Cross View Fusion for 3D Human Pose Estimationcited by 90
  11. 2017Exploiting temporal information for 3D pose estimationcited by 89
  12. 2020Motion Guided 3D Pose Estimation from Videoscited by 85
  13. 2021DOLG: Single-Stage Image Retrieval with Deep Orthogonal Fusion of Local and Global Featurescited by 54
  14. 2021Conditional Directed Graph Convolution for 3D Human Pose Estimationcited by 52
  15. 2021Graph-Based 3D Multi-Person Pose Estimation Using Multi-View Imagescited by 38
  16. 2019Trajectory Space Factorization for Deep Video-Based 3D Human Pose Estimationcited by 30
  17. 2019Not All Parts Are Created Equal: 3D Pose Estimation by Modelling Bi-directional Dependencies of Body Partscited by 19
  18. 2018Bio-LSTM: A Biomechanically Inspired Recurrent Neural Network for 3D Pedestrian Pose and Gait Predictioncited by 13
  19. 2022CrossFormer: Cross Spatio-Temporal Transformer for 3D Human Pose Estimationcited by 11

Built on by

Not cited yet.