Stars
HY-Motion model for 3D human motion or 3D character animation generation.
[NeurIPS 2023] Official implementation of the paper "Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset"
[NeurIPS 2023] MotionGPT: Human Motion as a Foreign Language, a unified motion-language generation model using LLMs
This repository contains the official implementation of "The Language of Motion: Unifying Verbal and Non-verbal Language of 3D Human Motion".
An end-to-end library for editing and rendering motion of 3D characters with deep learning [SIGGRAPH 2020]
[ICLR 2025] Pytorch Implementation of "Aligning Motion Generation with Human Perceptions".
The official PyTorch implementation of the paper "Human Motion Diffusion Model"
The official repo for [NeurIPS'22] "ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation" and [TPAMI'23] "ViTPose++: Vision Transformer for Generic Body Pose Estimation"
[ECCV 2022] ByteTrack: Multi-Object Tracking by Associating Every Detection Box
[ICCV2021] Official code for "Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition"
Python library to run Kinect Azure DK SDK functions
Automatic Depression Detection: a GRU/ BiLSTM-based Model and An Emotional Audio-Textual Corpus
This is the GitHub page for publicly available emotional speech data.
A toolbox for skeleton-based action recognition.
Dataset and benchmark suite for Parkinson’s gait analysis — NeurIPS 2025 D&B submission
Spatial Temporal Graph Convolutional Networks for Emotion Perception from Gaits
pytorch implementation of openpose including Hand and Body Pose Estimation.
OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation
Take an Emotion Walk: Perceiving Emotions from Gaits Using Hierarchical Attention Pooling and Affective Mapping
OpenMMLab Pose Estimation Toolbox and Benchmark.
[CVPR 25 Highlight] H-MoRe: Learning Human-centric Motion Representation for Action Analysis
《动手学深度学习》：面向中文读者、能运行、可讨论。中英文版被70多个国家的500多所大学用于教学。
A flexible and extensible framework for gait recognition. You can focus on designing your own models and comparing with state-of-the-arts easily with the help of OpenGait.