mlsanityData to 7 Oct 2026

Contrastive Representation Learning for Hand Shape Estimation

arXiv 2106.04324 ↗First posted 8 Jun 2021cs.CVcited by 34

Not on the map. Why?

Abstract (arXiv)

This work presents improvements in monocular hand shape estimation by building on top of recent advances in unsupervised learning. We extend momentum contrastive learning and contribute a structured collection of hand images, well suited for visual representation learning, which we call HanCo. We find that the representation learned by established contrastive learning methods can be improved significantly by exploiting advanced background removal techniques and multi-view information. These allow us to generate more diverse instance pairs than those obtained by augmentations commonly used in exemplar based approaches. Our method leads to a more suitable representation for the hand shape estimation task and shows a 4.7% reduction in mesh error and a 3.6% improvement in F-score compared to an ImageNet pretrained baseline. We make our benchmark dataset publicly available, to encourage further research into this direction.

Key facts. Cited by 34 papers in the map (data through 7 Oct 2026). Builds on 32 of its 44 references that are in the map. First posted on arXiv 8 Jun 2021.

Builds on

32 of 44 references.

References · 32

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  3. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  4. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  5. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
  6. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  7. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,586
  8. 2016Context Encoders: Feature Learning by Inpaintingcited by 1,424
  9. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,379
  10. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,375
  11. 2014How transferable are features in deep neural networks?cited by 1,216
  12. 2016Colorful Image Colorizationcited by 1,113
20 more
  1. 2018Deep Clustering for Unsupervised Learning of Visual Featurescited by 1,020
  2. 2017End-to-end Recovery of Human Shape and Posecited by 883
  3. 2013DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognitioncited by 422
  4. 2019Learning joint reconstruction of hands and manipulated objectscited by 377
  5. 2019FreiHAND: A Dataset for Markerless Capture of Hand Pose and Shape from Single RGB Imagescited by 271
  6. 2017Hand Keypoint Detection in Single Images using Multiview Bootstrappingcited by 231
  7. 2017First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotationscited by 229
  8. 20193D Hand Shape and Pose from Images in the Wildcited by 190
  9. 20193D Hand Shape and Pose Estimation from a Single RGB Imagecited by 174
  10. 2020Weakly-Supervised Mesh-Convolutional Hand Reconstruction in the Wildcited by 146
  11. 2017Real-Time User-Guided Image Colorization with Learned Deep Priorscited by 123
  12. 2017Deep Image Harmonizationcited by 120
  13. 2020Epipolar Transformerscited by 117
  14. 2019Pushing the Envelope for RGB-based Dense 3D Hand Pose Estimation via Neural Renderingcited by 115
  15. 2020Weakly Supervised 3D Hand Pose Estimation via Biomechanical Constraintscited by 97
  16. 2018Cross-modal Deep Variational Hand Pose Estimationcited by 89
  17. 2018Learning Monocular 3D Human Pose Estimation from Multi-view Imagescited by 70
  18. 2020DeepHandMesh: A Weakly-supervised Deep Encoder-Decoder Framework for High-fidelity Hand Mesh Modelingcited by 49
  19. 2019Micro-Batch Training with Batch-Channel Normalization and Weight Standardizationcited by 45
  20. 20163D Hand Pose Tracking and Estimation Using Stereo Matchingcited by 35

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 8; 2023: 7; 2024: 6; 2025: 4; 2026: 7.

34 papers.

Sort:

By area:

  1. 2021MobRecon: Mobile-Friendly Hand Mesh Reconstruction from Monocular Imagecited by 74
  2. 2022HARP: Personalized Hand Reconstruction from a Monocular RGB Videocited by 28
  3. 2022Interacting Hand-Object Pose Estimation via Dense Mutual Attentioncited by 22
  4. 2024OHTA: One-shot Hand Avatar via Data-driven Implicit Priorscited by 18
  5. 2024SignMusketeers: An Efficient Multi-Stream Approach for Sign Language Translation at Scalecited by 18
  6. 2022Efficient Annotation and Learning for 3D Hand Pose Estimation: A Surveycited by 17
  7. 2022TempCLR: Reconstructing Hands via Time-Coherent Contrastive Learningcited by 17
  8. 2024Dense Hand-Object(HO) GraspNet with Full Grasping Taxonomy and Dynamicscited by 15
  9. 2022Domain Adaptive Hand Keypoint and Pixel Localization in the Wildcited by 14
  10. 2023HandNeRF: Learning to Reconstruct Hand-Object Interaction Scene from a Single RGB Imagecited by 10
  11. 2023HaMuCo: Hand Pose Estimation via Multiview Collaborative Self-Supervised Learningcited by 7
  12. 2023Rethinking Self-Supervised Visual Representation Learning in Pre-training for 3D Human Pose and Shape Estimationcited by 7
22 more
  1. 2023Towards Robust and Expressive Whole-body Human Pose and Shape Estimationcited by 6
  2. 2024Self-Supervised Learning with Generative Adversarial Networks for Electron Microscopycited by 5
  3. 2025JGHand: Joint-Driven Animatable Hand Avater via 3D Gaussian Splattingcited by 3
  4. 2026EgoForce: Forearm-Guided Camera-Space 3D Hand Pose from a Monocular Egocentric Cameracited by 3
  5. 2021Multi-view Image-based Hand Geometry Refinement using Differentiable Monte Carlo Ray Tracingcited by 2
  6. 2022Neural Marionette: Unsupervised Learning of Motion Skeleton and Latent Dynamics from Volumetric Videocited by 2
  7. 2022Self-Supervised Contrastive Representation Learning for 3D Mesh Segmentationcited by 2
  8. 2024SiMA-Hand: Boosting 3D Hand-Mesh Reconstruction by Single-to-Multi-View Adaptationcited by 2
  9. 2025HandOcc: NeRF-based Hand Rendering with Occupancy Networkscited by 2
  10. 2022MBW: Multi-view Bootstrapping in the Wildcited by 1
  11. 2026EgoEMG: A Multimodal Egocentric Dataset with Bilateral EMG and Vision for Hand Pose Estimationcited by 1
  12. 2026GeoHand: Unlocking Prior Geometry Knowledge for Monocular 3D Hand Reconstructioncited by 1
  13. 2023ShaRPy: Shape Reconstruction and Hand Pose Estimation from RGB-D with Uncertaintycited by 0
  14. 2023Self-supervised Optimization of Hand Pose Estimation using Anatomical Features and Iterative Learningcited by 0
  15. 2023HandMIM: Pose-Aware Self-Supervised Learning for 3D Hand Mesh Estimationcited by 0
  16. 2024Automated Patient Positioning with Learned 3D Hand Gesturescited by 0
  17. 2025Direction-Aware Hybrid Representation Learning for 3D Hand Pose and Shape Estimationcited by 0
  18. 2025Fitting Image Diffusion Models on Video Datasetscited by 0
  19. 2026A Multi-View Pipeline and Benchmark Dataset for 3D Hand Pose Estimation in Surgerycited by 0
  20. 2026UST-Hand: An Uncertainty-aware Spatiotemporal Point Cloud Interaction Network for 3D Self-supervised Hand Pose Estimationcited by 0
  21. 2026OASIS: Occlusion-aware Single-image Hand Avatar Reconstruction via 3D Gaussian Splattingcited by 0
  22. 2026DigitCode: Symbolic Tokenization of Hand Motion by Anatomical Unitscited by 0