s-shamil / HandFormer
[ECCV '24] On the Utility of 3D Hand Poses for Action Recognition
☆9Updated last month
Alternatives and similar repositories for HandFormer:
Users that are interested in HandFormer are comparing it to the libraries listed below
- [CVPR2024] Official implementation of the paper: Skeleton-in-Context: Unified Skeleton Sequence Modeling with In-Context Learning☆38Updated 7 months ago
- Official implementation of the ICCV 2023 paper "Masked Motion Predictors are Strong 3D Action Representation Learners"☆45Updated last year
- ☆32Updated 2 years ago
- This is the official implementation of Global-local Motion Transformer for Unsupervised Skeleton-based Action Learning (ECCV 2022).☆22Updated last year
- Self-Supervised 3D Keypoint Discovery from Multi-View Videos☆20Updated last year
- [ICCV 2023] Latent Action Composition for Skeleton-based Action Segmentation☆17Updated last year
- ☆15Updated 8 months ago
- Official implementation for "Exploring Vision Transformers for 3D Human Motion-Language Models with Motion Patches" (CVPR 2024)☆20Updated 6 months ago
- ☆27Updated 2 years ago
- This is a repository contains the implementation of our AAAI'23 oral paper Hierarchical Contrast for Unsupervised Skeleton-based Action R…☆34Updated last year
- code from cvpr 2021 paper 'Unsupervised Human Pose Estimation through Transforming Shape Templates'☆33Updated 2 years ago
- This is the official implementation of the paper "MotionMixer: MLP-based 3D Human Body Pose Forecasting" (IJCAI 2022, oral-presentation).☆50Updated 2 years ago
- Official implementation of paper "Trajectory-Aware Body Interaction Transformer for Multi-Person Pose Forecasting".☆38Updated 11 months ago
- The project is an official implementation of our paper "A Lightweight Graph Transformer Network for Human Mesh Reconstruction from 2D Hum…☆28Updated last year
- InterFormer method to generate a reaction motion based on an action motion with 3D skeletons☆24Updated last year
- [CVPR2022] Decoupling and Recoupling Spatiotemporal Representation for RGB-D-based Motion Recognition☆22Updated last year
- [NeurIPS 2023] "A Single 2D Pose With Context is Worth Hundreds for 3D Human Pose Estimation" official implementation.☆72Updated 5 months ago
- ☆21Updated 11 months ago
- Code repository for the paper "Learning Discriminative Representations for Skeleton Based Action Recognition". CVPR 2023☆53Updated last year
- ☆18Updated 7 months ago
- AAAI 2025☆17Updated last week
- ☆22Updated last year
- This is the official implementation of "Back to Optimization: Diffusion-based Zero-Shot 3D Human Pose Estimation"☆36Updated last month
- Official Implementation for WACV'23 paper "Uplift and Upsample: Efficient 3D Human Pose Estimation with Uplifting Transformers"☆32Updated last year
- This is an official PyTorch implementation of "Zero-shot Skeleton-based Action Recognition via Mutual Information Estimation and Maximiza…☆23Updated last year
- Code for the CVPR'23 paper: "STMT: A Spatial-Temporal Mesh Transformer for MoCap-Based Action Recognition"☆20Updated last month
- [AAAI 2023 Distinguished Paper] Two Heads are Better than One: Image-Point Cloud Network for Depth-Based 3D Hand Pose Estimation☆12Updated last year
- ICASSP 2024☆14Updated 2 months ago
- FinePOSE: Fine-Grained Prompt-Driven 3D Human Pose Estimation via Diffusion Models☆74Updated 4 months ago
- Re-implementation for ICCV23 "Social Diffusion: Long-term Multiple Human Motion Anticipation"☆24Updated last year