mlsanityData to 7 Oct 2026

Chirality Nets for Human Pose Regression

arXiv 1911.00029 ↗First posted 31 Oct 2019cs.CV cs.LGcited by 31

Not on the map. Why?

Abstract (arXiv)

We propose Chirality Nets, a family of deep nets that is equivariant to the "chirality transform," i.e., the transformation to create a chiral pair. Through parameter sharing, odd and even symmetry, we propose and prove variants of standard building blocks of deep nets that satisfy the equivariance property, including fully connected layers, convolutional layers, batch-normalization, and LSTM/GRU cells. The proposed layers lead to a more data efficient representation and a reduction in computation by exploiting symmetry. We evaluate chirality nets on the task of human pose regression, which naturally exploits the left/right mirroring of the human body. We study three pose regression tasks: 3D pose estimation from video, 2D pose forecasting, and skeleton based activity recognition. Our approach achieves/matches state-of-the-art results, with more significant gains on small datasets and limited-data settings.

Key facts. Cited by 31 papers in the map (data through 7 Oct 2026). First posted on arXiv 31 Oct 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 10; 2023: 5; 2024: 1; 2025: 6; 2026: 3.

31 papers.

Sort:

By area:

  1. 20213D Human Pose Estimation with Spatial and Temporal Transformerscited by 271
  2. 2022MotionBERT: A Unified Perspective on Learning Human Motion Representationscited by 188
  3. 2022MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Videocited by 158
  4. 2022Learning 3D Human Pose Estimation from Dozens of Datasets using a Geometry-Aware Autoencoder to Bridge Between Skeleton Formatscited by 50
  5. 2022DEVIANT: Depth EquiVarIAnt NeTwork for Monocular 3D Object Detectioncited by 48
  6. 2021Pose with Style: Detail-Preserving Pose-Guided Image Synthesis with Conditional StyleGANcited by 45
  7. 2021Learning 3D Representations of Molecular Chirality with Invariance to Bond Rotationscited by 29
  8. 2022Ray3D: ray-based 3D human pose estimation for monocular absolute 3D localizationcited by 25
  9. 2022Equivariance Discovery by Learned Parameter-Sharingcited by 18
  10. 2022Learnable Polyphase Sampling for Shift Invariant and Equivariant Convolutional Networkscited by 18
  11. 2023Making Vision Transformers Truly Shift-Equivariantcited by 16
  12. 2023Truly Scale-Equivariant Deep Nets with Fourier Layerscited by 16
19 more
  1. 2022CrossFormer: Cross Spatio-Temporal Transformer for 3D Human Pose Estimationcited by 11
  2. 2022Total Variation Optimization Layers for Computer Visioncited by 8
  3. 2021Unsupervised domain adaptation for clinician pose estimation and instance segmentation in the operating roomcited by 7
  4. 2022IVT: An End-to-End Instance-guided Video Transformer for 3D Pose Estimationcited by 6
  5. 2023On discrete symmetries of robotics systems: A group-theoretic and data-driven analysiscited by 6
  6. 2023Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Surveycited by 6
  7. 20253D Skeleton-Based Action Recognition: A Reviewcited by 6
  8. 2021Motion Projection Consistency Based 3D Human Pose Estimation with Virtual Bones from Monocular Videoscited by 5
  9. 2025Group Downsampling with Equivariant Anti-aliasingcited by 3
  10. 2025Symmetry Understanding of 3D Shapes via Chirality Disentanglementcited by 3
  11. 2025Local Scale Equivariance with Latent Deep Equilibrium Canonicalizercited by 2
  12. 2025CLIPSym: Delving into Symmetry Detection with CLIPcited by 2
  13. 2026Flow Matching for Probabilistic Monocular 3D Human Pose Estimationcited by 2
  14. 2023ConvFormer: Parameter Reduction in Transformer Models for 3D Human Pose Estimation by Leveraging Dynamic Multi-Headed Convolutional Attentioncited by 1
  15. 2024Towards Precise 3D Human Pose Estimation with Multi-Perspective Spatial-Temporal Relational Transformerscited by 1
  16. 2025SplashNet: Split-and-Share Encoders for Accurate and Efficient Typing with Surface Electromyographycited by 1
  17. 2021Occlusion-Invariant Rotation-Equivariant Semi-Supervised Depth Based Cross-View Gait Pose Estimationcited by 0
  18. 2026Tunable Soft Equivariance with Guaranteescited by 0
  19. 2026CQF-HMR: Continuous Quaternion Flows for Probabilistic 3D Human Mesh Recovery from a Single Imagecited by 0