Stars
OpenCap Monocular: 3D Human Kinematics and Dynamics From a Single Smartphone Video
[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer
VPoser: Variational Human Pose Prior
This repository provides motion datasets collected by Bandai Namco Research Inc
API to support AIST++ Dataset: https://google.github.io/aistplusplus_dataset
Official implementation of Transformer-Based Multi-Grained Features for Person Re-Identification (WACV23 workshop).
A large-scale video dataset for the training and evaluation of 3D human pose estimation models
OpenMMLab Pose Estimation Toolbox and Benchmark.
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"
Code for "HumVis: Human-Centric Visual Analysis System", ACM MM 2023 Demo
Download a copy of your Garmin Connect data, including stats and GPX tracks.
[ICCV 2023] PyTorch Implementation of "MotionBERT: A Unified Perspective on Learning Human Motion Representations"
This repo is official implementation of HumanBench (CVPR2023)
BoT-SORT: Robust Associations Multi-Pedestrian Tracking
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
[CVPR 2022] Part-based Pseudo Label Refinement for Unsupervised Person Re-identification
A python package for turning sports video into csv files
Utilities for processing OpenCap data.