3D ResNets for Action Recognition (CVPR 2018)

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

TorchGeo: datasets, samplers, transforms, and pre-trained models for geospatial data

Automatic colorization using deep neural networks. "Colorful Image Colorization." In ECCV, 2016.

An API standard for multi-agent reinforcement learning environments, with popular reference environments and related utilities

Code for reproducing results in "Glow: Generative Flow with Invertible 1x1 Convolutions"

Official implementation of CVPR2020 paper "VIBE: Video Inference for Human Body Pose and Shape Estimation"

Hands-on Deep Reinforcement Learning, published by Packt

The project is an official implement of our ECCV2018 paper "Simple Baselines for Human Pose Estimation and Tracking(https://arxiv.org/abs/1804.06208)"

This repository includes the official project of TransUNet, presented in our paper: TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation.

Project Page for "LISA: Reasoning Segmentation via Large Language Model"

Elegant PyTorch implementation of paper Model-Agnostic Meta-Learning (MAML)

Simple and easily configurable grid world environments for reinforcement learning

SMPL-X

🦁 Lion, new optimizer discovered by Google Brain using genetic algorithms that is purportedly better than Adam(w), in Pytorch

[ICCV 2019] TSM: Temporal Shift Module for Efficient Video Understanding

Large Language-and-Vision Assistant for Biomedicine, built towards multimodal GPT-4 level capabilities.

ALIbaba's Collection of Encoder-decoders from MinD (Machine IntelligeNce of Damo) Lab

Expressive Body Capture: 3D Hands, Face, and Body from a Single Image

Awesome machine learning for combinatorial optimization papers.

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"

Project page for End-to-end Recovery of Human Shape and Pose

Code & Models for Temporal Segment Networks (TSN) in ECCV 2016

DomainBed is a suite to test domain generalization algorithms

solo-learn: a library of self-supervised methods for visual representation learning powered by Pytorch Lightning

Official code of "HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation", CVPR 2021

A simple baseline for 3d human pose estimation in tensorflow. Presented at ICCV 17.

A PyTorch toolbox for domain generalization, domain adaptation and semi-supervised learning.

An Open-sourced Knowledgable Large Language Model Framework.