BizhuWu

Detectron

FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.

LLaVA

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

awesome-self-supervised-learning

A curated list of awesome self-supervised methods

VideoPose3D

Efficient 3D human pose estimation in video using 2D keypoint trajectories

ViT-pytorch

Pytorch reimplementation of the Vision Transformer (An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale)

MotionGPT

[NeurIPS 2023] MotionGPT: Human Motion as a Foreign Language, a unified motion-language generation model using LLMs

MotionBERT

[ICCV 2023] PyTorch Implementation of "MotionBERT: A Unified Perspective on Learning Human Motion Representations"

HumanML3D

HumanML3D: A large and diverse 3d human motion-language dataset.

OMG

[ECCV 2024] OMG: Occlusion-friendly Personalized Multi-concept Generation In Diffusion Models

Long-CLIP

[ECCV 2024] official code for "Long-CLIP: Unlocking the Long-Text Capability of CLIP"

T2M-GPT

(CVPR 2023) Pytorch implementation of “T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations”

Awesome-Skeleton-based-Action-Recognition

A curated paper list of awesome skeleton-based action recognition.

CTR-GCN

[ICCV2021] Official code for "Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition"

HCN-pytorch

A pytorch reproduction of { Co-occurrence Feature Learning from Skeleton Data for Action Recognition and Detection with Hierarchical Aggregation }.

PoseGPT

MotionGPT

The official PyTorch implementation of the paper "MotionGPT: Finetuned LLMs are General-Purpose Motion Generators"

SGN

This is the implementation of CVPR2020 paper “Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognition”.

BABEL

Code accompanying the BABEL dataset (CVPR 2021).

posescript

actiongpt

Official pytorch implementation of Action-GPT

flame

Official implementation of the paper "FLAME: Free-form Language-based Motion Synthesis & Editing"

TM2T

Official implementation of "TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts (ECCV2022)"

human-motion-prediction-pytorch

Simple baselines and RNNs for predicting human motion. Presented at CVPR 17. This pytorch implementation is based on the original one by the authors

AimCLR

This is an official PyTorch implementation of "Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-supervised Action Recognition" in AAAI2022.

SUP

The Biomotion Lab SMPL Unity Player (bmlSUP) is a tool to play SMPL-H model animations in Unity Game Engine

Pro-Motion

Plan, Posture and Go: Towards Open-World Text-to-Motion Generation

SemanticBoost

Official rope of SemanticBoost: Elevating Motion Generation with Augmented Textual Cues

Kinetics-TPS

ICCV DeeperAction Challenge - Kinetics-TPS Challenge on Part-level Action Parsing and Action Recognition.

OS-SAR

omg-project