mlsanityData to 7 Oct 2026

CrossFormer: Cross Spatio-Temporal Transformer for 3D Human Pose Estimation

arXiv 2203.13387 ↗First posted 24 Mar 2022cs.CVcited by 11

Not on the map. Why?

Abstract (arXiv)

3D human pose estimation can be handled by encoding the geometric dependencies between the body parts and enforcing the kinematic constraints. Recently, Transformer has been adopted to encode the long-range dependencies between the joints in the spatial and temporal domains. While they had shown excellence in long-range dependencies, studies have noted the need for improving the locality of vision Transformers. In this direction, we propose a novel pose estimation Transformer featuring rich representations of body joints critical for capturing subtle changes across frames (i.e., inter-feature representation). Specifically, through two novel interaction modules; Cross-Joint Interaction and Cross-Frame Interaction, the model explicitly encodes the local and global dependencies between the body joints. The proposed architecture achieved state-of-the-art performance on two popular 3D human pose estimation datasets, Human3.6 and MPI-INF-3DHP. In particular, our proposed CrossFormer method boosts performance by 0.9% and 0.3%, compared to the closest counterpart, PoseFormer, using the detected 2D poses and ground-truth settings respectively.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 31 of its 49 references that are in the map. First posted on arXiv 24 Mar 2022.

Builds on

31 of 49 references.

References · 31

  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. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  5. 2017Mask R-CNNcited by 7,259
  6. 2017Squeeze-and-Excitation Networkscited by 4,763
  7. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
  8. 2017Non-local Neural Networkscited by 2,290
  9. 2018Group Normalizationcited by 1,514
  10. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 493
  11. 2020End-to-End Human Pose and Mesh Reconstruction with Transformerscited by 417
  12. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
19 more
  1. 20183D human pose estimation in video with temporal convolutions and semi-supervised trainingcited by 401
  2. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
  3. 2020I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Imagecited by 274
  4. 20213D Human Pose Estimation with Spatial and Temporal Transformerscited by 271
  5. 2021LocalViT: Analyzing Locality in Vision Transformerscited by 228
  6. 2019Semantic Graph Convolutional Networks for 3D Human Pose Regressioncited by 204
  7. 2017VNect: Real-time 3D Human Pose Estimation with a Single RGB Cameracited by 129
  8. 2021RegionViT: Regional-to-Local Attention for Vision Transformerscited by 126
  9. 2018Ordinal Depth Supervision for 3D Human Pose Estimationcited by 107
  10. 2020SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approachcited by 94
  11. 2021Exploiting Temporal Contexts with Strided Transformer for 3D Human Pose Estimationcited by 94
  12. 2021Graph Stacked Hourglass Networks for 3D Human Pose Estimationcited by 94
  13. 2017Exploiting temporal information for 3D pose estimationcited by 89
  14. 2020Motion Guided 3D Pose Estimation from Videoscited by 85
  15. 2020Cascaded deep monocular 3D human pose estimation with evolutionary training datacited by 80
  16. 2018Compact Generalized Non-local Networkcited by 36
  17. 2019Chirality Nets for Human Pose Regressioncited by 31
  18. 2019Trajectory Space Factorization for Deep Video-Based 3D Human Pose Estimationcited by 30
  19. 2021Learning Discriminative Representations for Multi-Label Image Recognitioncited by 4

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 4; 2024: 2; 2025: 2.

11 papers.

  1. 2022Visual Attention Methods in Deep Learning: An In-Depth Surveycited by 37
  2. 2023HDFormer: High-order Directed Transformer for 3D Human Pose Estimationcited by 23
  3. 20223D Vision with Transformers: A Surveycited by 21
  4. 2023Occlusion Robust 3D Human Pose Estimation with StridedPoseGraphFormer and Data Augmentationcited by 3
  5. 2025SCJD: Sparse Correlation and Joint Distillation for Efficient 3D Human Pose Estimationcited by 2
  6. 2023EVOPOSE: A Recursive Transformer For 3D Human Pose Estimation With Kinematic Structure Priorscited by 1
  7. 2024Multi-hop graph transformer network for 3D human pose estimationcited by 1
  8. 2024Adaptive Convolutional Forecasting Network Based on Time Series Feature-Drivencited by 1
  9. 2022(Fusionformer):Exploiting the Joint Motion Synergy with Fusion Network Based On Transformer for 3D Human Pose Estimationcited by 0
  10. 2023Refined Temporal Pyramidal Compression-and-Amplification Transformer for 3D Human Pose Estimationcited by 0
  11. 2025Towards Autonomous Riding: A Review of Perception, Planning, and Control in Intelligent Two-Wheelerscited by 0