mlsanityData to 7 Oct 2026

Refined Temporal Pyramidal Compression-and-Amplification Transformer for 3D Human Pose Estimation

arXiv 2309.01365 ↗First posted 4 Sep 2023cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Accurately estimating the 3D pose of humans in video sequences requires both accuracy and a well-structured architecture. With the success of transformers, we introduce the Refined Temporal Pyramidal Compression-and-Amplification (RTPCA) transformer. Exploiting the temporal dimension, RTPCA extends intra-block temporal modeling via its Temporal Pyramidal Compression-and-Amplification (TPCA) structure and refines inter-block feature interaction with a Cross-Layer Refinement (XLR) module. In particular, TPCA block exploits a temporal pyramid paradigm, reinforcing key and value representation capabilities and seamlessly extracting spatial semantics from motion sequences. We stitch these TPCA blocks with XLR that promotes rich semantic representation through continuous interaction of queries, keys, and values. This strategy embodies early-stage information with current flows, addressing typical deficits in detail and stability seen in other transformer-based methods. We demonstrate the effectiveness of RTPCA by achieving state-of-the-art results on Human3.6M, HumanEva-I, and MPI-INF-3DHP benchmarks with minimal computational overhead. The source code is available at https://github.com/hbing-l/RTPCA.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 48 of its 71 references that are in the map. First posted on arXiv 4 Sep 2023.

Builds on

48 of 71 references.

References · 48

  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. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  5. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  6. 2020End-to-End Object Detection with Transformerscited by 7,384
  7. 2018UNet++: A Nested U-Net Architecture for Medical Image Segmentationcited by 1,518
  8. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  9. 2019EfficientDet: Scalable and Efficient Object Detectioncited by 1,018
  10. 2021CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classificationcited by 806
  11. 2021Transformer in Transformercited by 632
  12. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 493
36 more
  1. 2021TransReID: Transformer-based Object Re-Identificationcited by 432
  2. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
  3. 20183D human pose estimation in video with temporal convolutions and semi-supervised trainingcited by 401
  4. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
  5. 20213D Human Pose Estimation with Spatial and Temporal Transformerscited by 271
  6. 2017Integral Human Pose Regressioncited by 255
  7. 2016Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Posecited by 220
  8. 2019Semantic Graph Convolutional Networks for 3D Human Pose Regressioncited by 204
  9. 2022MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Videocited by 158
  10. 2021MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimationcited by 151
  11. 2017Compositional Human Pose Regressioncited by 124
  12. 2018Ordinal Depth Supervision for 3D Human Pose Estimationcited by 107
  13. 2020SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approachcited by 94
  14. 2021Exploiting Temporal Contexts with Strided Transformer for 3D Human Pose Estimationcited by 94
  15. 2021Graph Stacked Hourglass Networks for 3D Human Pose Estimationcited by 94
  16. 2023PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimationcited by 91
  17. 2021PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimationcited by 88
  18. 2020Motion Guided 3D Pose Estimation from Videoscited by 85
  19. 2021Conditional Directed Graph Convolution for 3D Human Pose Estimationcited by 52
  20. 2023Implicit Temporal Modeling with Learnable Alignment for Video Recognitioncited by 44
  21. 2016Deep Kinematic Pose Regressioncited by 40
  22. 2021Context Modeling in 3D Human Pose Estimation: A Unified Perspectivecited by 37
  23. 2022Hypergraph Transformer for Skeleton-based Action Recognitioncited by 36
  24. 2019Trajectory Space Factorization for Deep Video-Based 3D Human Pose Estimationcited by 30
  25. 2020Graph and Temporal Convolutional Networks for 3D Multi-person Pose Estimation in Monocular Videoscited by 23
  26. 2023HDFormer: High-order Directed Transformer for 3D Human Pose Estimationcited by 23
  27. 2022GSRFormer: Grounded Situation Recognition Transformer with Alternate Semantic Attention Refinementcited by 20
  28. 2023PoSynDA: Multi-Hypothesis Pose Synthesis Domain Adaptation for Robust 3D Human Pose Estimationcited by 12
  29. 2022CrossFormer: Cross Spatio-Temporal Transformer for 3D Human Pose Estimationcited by 11
  30. 2021GraFormer: Graph Convolution Transformer for 3D Pose Estimationcited by 10
  31. 2023HSTFormer: Hierarchical Spatial-Temporal Transformers for 3D Human Pose Estimationcited by 9
  32. 2022DH-AUG: DH Forward Kinematics Model Driven Augmentation for 3D Human Pose Estimationcited by 8
  33. 2023Overcoming Topology Agnosticism: Enhancing Skeleton-Based Action Recognition through Redefined Skeletal Topology Awarenesscited by 8
  34. 2022ACRNet: Attention Cube Regression Network for Multi-view Real-time 3D Human Pose Estimation in Telemedicinecited by 2
  35. 2023ConvFormer: Parameter Reduction in Transformer Models for 3D Human Pose Estimation by Leveraging Dynamic Multi-Headed Convolutional Attentioncited by 1
  36. 2023Spatio-temporal MLP-graph network for 3D human pose estimationcited by 1

Built on by

Not cited yet.