mlsanityData to 7 Oct 2026

MotionAGFormer: Enhancing 3D Human Pose Estimation with a Transformer-GCNFormer Network

arXiv 2310.16288 ↗First posted 25 Oct 2023cs.CVcited by 62

Not on the map. Why?

Abstract (arXiv)

Recent transformer-based approaches have demonstrated excellent performance in 3D human pose estimation. However, they have a holistic view and by encoding global relationships between all the joints, they do not capture the local dependencies precisely. In this paper, we present a novel Attention-GCNFormer (AGFormer) block that divides the number of channels by using two parallel transformer and GCNFormer streams. Our proposed GCNFormer module exploits the local relationship between adjacent joints, outputting a new representation that is complementary to the transformer output. By fusing these two representation in an adaptive way, AGFormer exhibits the ability to better learn the underlying 3D structure. By stacking multiple AGFormer blocks, we propose MotionAGFormer in four different variants, which can be chosen based on the speed-accuracy trade-off. We evaluate our model on two popular benchmark datasets: Human3.6M and MPI-INF-3DHP. MotionAGFormer-B achieves state-of-the-art results, with P1 errors of 38.4mm and 16.2mm, respectively. Remarkably, it uses a quarter of the parameters and is three times more computationally efficient than the previous leading model on Human3.6M dataset. Code and models are available at https://github.com/TaatiTeam/MotionAGFormer.

Key facts. Cited by 62 papers in the map (data through 7 Oct 2026). Builds on 44 of its 57 references that are in the map. First posted on arXiv 25 Oct 2023.

Builds on

44 of 57 references.

References · 44

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  4. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  5. 2016Layer Normalizationcited by 5,579
  6. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  7. 2022CoCa: Contrastive Captioners are Image-Text Foundation Modelscited by 1,265
  8. 2021MetaFormer Is Actually What You Need for Visioncited by 523
  9. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 493
  10. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
  11. 2020Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognitioncited by 339
  12. 2021Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognitioncited by 317
32 more
  1. 2022DETRs with Collaborative Hybrid Assignments Trainingcited by 273
  2. 20213D Human Pose Estimation with Spatial and Temporal Transformerscited by 271
  3. 2017Integral Human Pose Regressioncited by 255
  4. 2020Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Posecited by 248
  5. 2016Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Posecited by 220
  6. 2019Semantic Graph Convolutional Networks for 3D Human Pose Regressioncited by 204
  7. 2022MotionBERT: A Unified Perspective on Learning Human Motion Representationscited by 188
  8. 2019Learnable Triangulation of Human Posecited by 160
  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. 2017VNect: Real-time 3D Human Pose Estimation with a Single RGB Cameracited by 129
  12. 2018Ordinal Depth Supervision for 3D Human Pose Estimationcited by 107
  13. 2021Exploiting Temporal Contexts with Strided Transformer for 3D Human Pose Estimationcited by 94
  14. 2021Graph Stacked Hourglass Networks for 3D Human Pose Estimationcited by 94
  15. 2023PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimationcited by 91
  16. 2020Motion Guided 3D Pose Estimation from Videoscited by 85
  17. 2022Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 85
  18. 2022Learning Multi-dimensional Edge Feature-based AU Relation Graph for Facial Action Unit Recognitioncited by 81
  19. 2022P-STMO: Pre-Trained Spatial Temporal Many-to-One Model for 3D Human Pose Estimationcited by 80
  20. 2020Lightweight Multi-View 3D Pose Estimation through Camera-Disentangled Representationcited by 57
  21. 2019HEMlets Pose: Learning Part-Centric Heatmap Triplets for Accurate 3D Human Pose Estimationcited by 50
  22. 2023GLA-GCN: Global-local Adaptive Graph Convolutional Network for 3D Human Pose Estimation from Monocular Videocited by 46
  23. 2020AdaFuse: Adaptive Multiview Fusion for Accurate Human Pose Estimation in the Wildcited by 40
  24. 2022Uplift and Upsample: Efficient 3D Human Pose Estimation with Uplifting Transformerscited by 33
  25. 2022Towards All-in-one Pre-training via Maximizing Multi-modal Mutual Informationcited by 31
  26. 2020Traffic Control Gesture Recognition for Autonomous Vehiclescited by 24
  27. 2023HDFormer: High-order Directed Transformer for 3D Human Pose Estimationcited by 23
  28. 2022Learnable human mesh triangulation for 3D human pose and shape estimationcited by 16
  29. 2023HSTFormer: Hierarchical Spatial-Temporal Transformers for 3D Human Pose Estimationcited by 9
  30. 2023Weakly Supervised Multi-Modal 3D Human Body Pose Estimation for Autonomous Drivingcited by 8
  31. 2022On-Board Pedestrian Trajectory Prediction Using Behavioral Featurescited by 5
  32. 2023Double-chain Constraints for 3D Human Pose Estimation in Images and Videoscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 12; 2025: 29; 2026: 21.

62 papers.

Sort:

By area:

  1. 2024A Comprehensive Survey of Action Quality Assessment: Method and Benchmarkcited by 20
  2. 2024AutoSoccerPose: Automated 3D posture Analysis of Soccer Shot Movementscited by 15
  3. 2025AthletePose3D: A Benchmark Dataset for 3D Human Pose Estimation and Kinematic Validation in Athletic Movementscited by 14
  4. 2024In My Perspective, In My Hands: Accurate Egocentric 2D Hand Pose and Action Recognitioncited by 12
  5. 2024Pose Magic: Efficient and Temporally Consistent Human Pose Estimation with a Hybrid Mamba-GCN Networkcited by 12
  6. 20243D Pose-Based Temporal Action Segmentation for Figure Skating: A Fine-Grained and Jump Procedure-Aware Annotation Approachcited by 7
  7. 2024HumMUSS: Human Motion Understanding using State Space Modelscited by 6
  8. 2024Benchmarking Skeleton-based Motion Encoder Models for Clinical Applications: Estimating Parkinson's Disease Severity in Walking Sequencescited by 6
  9. 2025AthleticsPose: Authentic Sports Motion Dataset on Athletic Field and Evaluation of Monocular 3D Pose Estimation Abilitycited by 6
  10. 2025H2OT: Hierarchical Hourglass Tokenizer for Efficient Video Pose Transformerscited by 5
  11. 2025CARE-PD: A Multi-Site Anonymized Clinical Dataset for Parkinson's Disease Gait Assessmentcited by 5
  12. 2025HGMamba: Enhancing 3D Human Pose Estimation with a HyperGCN-Mamba Networkcited by 4
38 more
  1. 2025FastHMR: Accelerating Human Mesh Recovery via Token and Layer Merging with Diffusion Decodingcited by 4
  2. 2026THFM: A Unified Video Foundation Model for 4D Human Perception and Beyondcited by 4
  3. 2024Optimizing Local-Global Dependencies for Accurate 3D Human Pose Estimationcited by 3
  4. 2025AGIR: Assessing 3D Gait Impairment with Reasoning based on LLMscited by 3
  5. 2025A Structure-aware and Motion-adaptive Framework for 3D Human Pose Estimation with Mambacited by 3
  6. 2025Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learningcited by 3
  7. 2024Platypose: Calibrated Zero-Shot Multi-Hypothesis 3D Human Motion Estimationcited by 2
  8. 2024STGFormer: Spatio-Temporal GraphFormer for 3D Human Pose Estimation in Videocited by 2
  9. 2024SPiKE: 3D Human Pose from Point Cloud Sequencescited by 2
  10. 2025NanoHTNet: Nano Human Topology Network for Efficient 3D Human Pose Estimationcited by 2
  11. 2025PoseBench3D: A Cross-Dataset Analysis Framework for 3D Human Pose Estimation via Pose Lifting Networkscited by 2
  12. 2025Mamba-Driven Topology Fusion for Monocular 3D Human Pose Estimationcited by 2
  13. 2025Learning Human Motion with Temporally Conditional Mambacited by 2
  14. 2026Breaking Coordinate Overfitting: Geometry-Aware WiFi Sensing for Cross-Layout 3D Pose Estimationcited by 2
  15. 2026Motion-Adaptive Multi-Scale Temporal Modelling with Skeleton-Constrained Spatial Graphs for Efficient 3D Human Pose Estimationcited by 2
  16. 2026MuPPet: Multi-person 2D-to-3D Pose Liftingcited by 2
  17. 2025Spectral Compression Transformer with Line Pose Graph for Monocular 3D Human Pose Estimationcited by 1
  18. 2025StarPose: 3D Human Pose Estimation via Spatial-Temporal Autoregressive Diffusioncited by 1
  19. 2025SasMamba: A Lightweight Structure-Aware Stride State Space Model for 3D Human Pose Estimationcited by 1
  20. 2025Age-Inclusive 3D Human Mesh Recovery for Action-Preserving Data Anonymizationcited by 1
  21. 2025FastDDHPose: Towards Unified, Efficient, and Disentangled 3D Human Pose Estimationcited by 1
  22. 2026SIMSPINE: A Biomechanics-Aware Simulation Framework for 3D Spine Motion Annotation and Benchmarkingcited by 1
  23. 2026VIMCAN: Visual-Inertial 3D Human Pose Estimation with Hybrid Mamba-Cross-Attention Networkcited by 1
  24. 2026Aggregate, Don't Adapt: Subject-Level Posterior Aggregation and Transductive Calibration for Cross-Site Parkinsonian Gait Severitycited by 1
  25. 2026More Motion Is Not Always Better Motion: Corpus Composition Governs Whether Augmentation Helps SMPL-Based Parkinsonian Gait Severity Estimationcited by 1
  26. 2024LangPose: Language-Aligned Motion for Robust 3D Human Pose Estimationcited by 0
  27. 2025Towards Training-Free Open-World Classification with 3D Generative Modelscited by 0
  28. 2025Dual-stream Transformer-GCN Model with Contextualized Representations Learning for Monocular 3D Human Pose Estimationcited by 0
  29. 2025HDiffTG: A Lightweight Hybrid Diffusion-Transformer-GCN Architecture for 3D Human Pose Estimationcited by 0
  30. 2025KASportsFormer: Kinematic Anatomy Enhanced Transformer for 3D Human Pose Estimation on Short Sports Scene Videocited by 0
  31. 2025VIFSS: View-Invariant and Figure Skating-Specific Pose Representation Learning for Temporal Action Segmentationcited by 0
  32. 2025Efficient Diffusion-Based 3D Human Pose Estimation with Hierarchical Temporal Pruningcited by 0
  33. 2025Paving the Way Towards Kinematic Assessment Using Monocular Video: A Preclinical Benchmark of State-of-the-Art Deep-Learning-Based 3D Human Pose Estimators Against Inertial Sensors in Daily Living Activitiescited by 0
  34. 2025Valeo Near-Field: a novel dataset for pedestrian intent detectioncited by 0
  35. 2025PRGCN: A Graph Memory Network for Cross-Sequence Pattern Reuse in 3D Human Pose Estimationcited by 0
  36. 2025Physics Informed Human Posture Estimation Based on 3D Landmarks from Monocular RGB-Videoscited by 0
  37. 2025PoseMoE: Mixture-of-Experts Network for Monocular 3D Human Pose Estimationcited by 0
  38. 2026SEAL-pose: Enhancing 3D Human Pose Estimation via a Learned Loss for Structural Consistencycited by 0

50 most cited of 62 All 62 (JSON)