mlsanityData to 14 Oct 2026

Encoder-decoder with Multi-level Attention for 3D Human Shape and Pose Estimation

arXiv 2109.02303 ↗First posted 6 Sep 2021cs.CVcited by 62

Not on the map. Why?

Abstract (arXiv)

3D human shape and pose estimation is the essential task for human motion analysis, which is widely used in many 3D applications. However, existing methods cannot simultaneously capture the relations at multiple levels, including spatial-temporal level and human joint level. Therefore they fail to make accurate predictions in some hard scenarios when there is cluttered background, occlusion, or extreme pose. To this end, we propose Multi-level Attention Encoder-Decoder Network (MAED), including a Spatial-Temporal Encoder (STE) and a Kinematic Topology Decoder (KTD) to model multi-level attentions in a unified framework. STE consists of a series of cascaded blocks based on Multi-Head Self-Attention, and each block uses two parallel branches to learn spatial and temporal attention respectively. Meanwhile, KTD aims at modeling the joint level attention. It regards pose estimation as a top-down hierarchical process similar to SMPL kinematic tree. With the training set of 3DPW, MAED outperforms previous state-of-the-art methods by 6.2, 7.2, and 2.4 mm of PA-MPJPE on the three widely used benchmarks 3DPW, MPI-INF-3DHP, and Human3.6M respectively. Our code is available at https://github.com/ziniuwan/maed.

Key facts. Cited by 62 papers in the map (data through 14 Oct 2026). Builds on 36 of its 45 references that are in the map. First posted on arXiv 6 Sep 2021.

Builds on

36 of 45 references.

References · 36

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  5. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  6. 2020End-to-End Object Detection with Transformerscited by 7,414
  7. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
  8. 2020Training data-efficient image transformers & distillation through attentioncited by 4,586
  9. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,422
  10. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,612
  11. 2020Point Transformercited by 1,470
  12. 2017Random Erasing Data Augmentationcited by 1,239
24 more
  1. 2021Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNetcited by 1,101
  2. 2019Cross-lingual Language Model Pretrainingcited by 1,090
  3. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,064
  4. 2020Pre-Trained Image Processing Transformercited by 893
  5. 2017End-to-end Recovery of Human Shape and Posecited by 885
  6. 2019Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loopcited by 627
  7. 2019VIBE: Video Inference for Human Body Pose and Shape Estimationcited by 620
  8. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 494
  9. 2021Bottleneck Transformers for Visual Recognitioncited by 364
  10. 2020Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentationcited by 326
  11. 2018Learning 3D Human Dynamics from Videocited by 316
  12. 2018Video Action Transformer Networkcited by 316
  13. 2020I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Imagecited by 274
  14. 2019Convolutional Mesh Regression for Single-Image Human Shape Reconstructioncited by 270
  15. 2020Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Posecited by 248
  16. 2017Unite the People: Closing the Loop Between 3D and 2D Human Representationscited by 205
  17. 2017PoseTrack: A Benchmark for Human Pose Estimation and Trackingcited by 173
  18. 2020Monocular Expressive Body Regression through Body-Driven Attentioncited by 155
  19. 2019Exploiting temporal context for 3D human pose estimation in the wildcited by 110
  20. 20203D Human Motion Estimation via Motion Compression and Refinementcited by 98
  21. 2019Human Mesh Recovery from Monocular Images via a Skeleton-disentangled Representationcited by 87
  22. 2020Synthetic Training for Accurate 3D Human Pose and Shape Estimation in the Wildcited by 82
  23. 2015Sparseness Meets Deepness: 3D Human Pose Estimation from Monocular Videocited by 54
  24. 2018MultiPoseNet: Fast Multi-Person Pose Estimation using Pose Residual Networkcited by 47

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 11; 2023: 16; 2024: 18; 2025: 6; 2026: 10.

62 papers.

Sort:

By area:

  1. 2022Executing your Commands via Motion Diffusion in Latent Spacecited by 575
  2. 2023Humans in 4D: Reconstructing and Tracking Humans with Transformerscited by 350
  3. 2022CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimationcited by 238
  4. 2023WHAM: Reconstructing World-grounded Humans with Accurate 3D Motioncited by 206
  5. 2022MotionBERT: A Unified Perspective on Learning Human Motion Representationscited by 193
  6. 2022PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Imagescited by 153
  7. 2024World-Grounded Human Motion Recovery via Gravity-View Coordinatescited by 137
  8. 2024TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videoscited by 106
  9. 2022Recovering 3D Human Mesh from Monocular Images: A Surveycited by 103
  10. 2021SmoothNet: A Plug-and-Play Network for Refining Human Poses in Videoscited by 64
  11. 2023EgoHumans: An Egocentric 3D Multi-Human Benchmarkcited by 60
  12. 2023C·ASE: Learning Conditional Adversarial Skill Embeddings for Physics-based Characterscited by 55
38 more
  1. 2023Global-to-Local Modeling for Video-based 3D Human Pose and Shape Estimationcited by 47
  2. 2023NIKI: Neural Inverse Kinematics with Invertible Neural Networks for 3D Human Pose and Shape Estimationcited by 45
  3. 20233D Human Mesh Estimation from Virtual Markerscited by 44
  4. 2022D&D: Learning Human Dynamics from Dynamic Cameracited by 41
  5. 2023PSVT: End-to-End Multi-person 3D Pose and Shape Estimation with Progressive Video Transformerscited by 32
  6. 2024PhysPT: Physics-aware Pretrained Transformer for Estimating Human Dynamics from Monocular Videoscited by 28
  7. 2023CIMI4D: A Large Multimodal Climbing Motion Dataset under Human-scene Interactionscited by 27
  8. 2023Co-Evolution of Pose and Mesh for 3D Human Body Estimation from Videocited by 25
  9. 2023Sampling is Matter: Point-guided 3D Human Mesh Reconstructioncited by 24
  10. 2024AniMer: Animal Pose and Shape Estimation Using Family Aware Transformercited by 20
  11. 2022Learning Variational Motion Prior for Video-based Motion Capturecited by 17
  12. 2023RenderIH: A Large-scale Synthetic Dataset for 3D Interacting Hand Pose Estimationcited by 16
  13. 2024RELI11D: A Comprehensive Multimodal Human Motion Dataset and Methodcited by 16
  14. 2024Learn2Talk: 3D Talking Face Learns from 2D Talking Facecited by 16
  15. 2022Occluded Human Body Capture with Self-Supervised Spatial-Temporal Motion Priorcited by 15
  16. 2024Fast Encoder-Based 3D from Casual Videos via Point Track Processingcited by 14
  17. 2025Reconstructing 4D Spatial Intelligence: A Surveycited by 14
  18. 2022MPT: Mesh Pre-Training with Transformers for Human Pose and Mesh Reconstructioncited by 11
  19. 2024Lifting Motion to the 3D World via 2D Diffusioncited by 11
  20. 2023Recovering 3D Hand Mesh Sequence from a Single Blurry Image: A New Dataset and Temporal Unfoldingcited by 10
  21. 2024STAF: 3D Human Mesh Recovery from Video with Spatio-Temporal Alignment Fusioncited by 9
  22. 2024SMPLer: Taming Transformers for Monocular 3D Human Shape and Pose Estimationcited by 9
  23. 2023Capturing the motion of every joint: 3D human pose and shape estimation with independent tokenscited by 8
  24. 2025AniMer+: Unified Pose and Shape Estimation Across Mammalia and Aves via Family-Aware Transformercited by 7
  25. 2022Snipper: A Spatiotemporal Transformer for Simultaneous Multi-Person 3D Pose Estimation Tracking and Forecasting on a Video Snippetcited by 6
  26. 2024HumMUSS: Human Motion Understanding using State Space Modelscited by 6
  27. 2026Towards Motion Turing Test: Evaluating Human-Likeness in Humanoid Robotscited by 4
  28. 2022Human Body Measurement Estimation with Adversarial Augmentationcited by 3
  29. 2024ViMo: Generating Motions from Casual Videoscited by 3
  30. 2024Optimizing Local-Global Dependencies for Accurate 3D Human Pose Estimationcited by 3
  31. 2025ClimbingCap: Multi-Modal Dataset and Method for Rock Climbing in World Coordinatecited by 3
  32. 2026QuaMo: Quaternion Motions for Vision-based 3D Human Kinematics Capturecited by 3
  33. 2024HeatFormer: A Neural Optimizer for Multiview Human Mesh Recoverycited by 2
  34. 2026AnyLift: Scaling Motion Reconstruction from Internet Videos via 2D Diffusioncited by 2
  35. 2024MoManifold: Learning to Measure 3D Human Motion via Decoupled Joint Acceleration Manifoldscited by 1
  36. 2025Spectral Compression Transformer with Line Pose Graph for Monocular 3D Human Pose Estimationcited by 1
  37. 2026FlashCap: Millisecond-Accurate Human Motion Capture via Flashing LEDs and Event-Based Visioncited by 1
  38. 2026LAMP: Localization Aware Multi-camera People Tracking in Metric 3D Worldcited by 1

50 most cited of 62 All 62 (JSON)