zhaoyang10

GFA-CNN

The tensorflow code for our "Learning Generalizable and Identity-Discriminative Representations forFace Anti-Spoofing" (GFA-CNN)

time-series-forecasting-baselines

By a chance of time forecasting competition, we build this repository for baselines.

ObjectDetection-OneStageDet

2s-AGCN

Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition in CVPR19

ChampSim

ChampSim repository

codeforces-gym

Dassl.pytorch

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

Deep-Learning-Project-Template

A best practice for deep learning project template architecture.

epipolar-transformers

Epipolar Transformers (CVPR 2020)

Episodic-DG

This is the repo for the paper "Episodic Training for Domain Generalization" https://arxiv.org/abs/1902.00113

fast-reid

[WIP] SOTA ReID Methods and Toolbox

frankmocap

A Strong and Easy-to-use Single View 3D Hand+Body Pose Estimator

Hermes

A speculative mechanism to accelerate long-latency off-chip load requests by removing on-chip cache access latency from their critical path, as described by MICRO 2022 paper by Bera et al. (https://arxiv.org/pdf/2209.00188.pdf)

image-play

Code for reproducing the results in "Forecasting Human Dynamics from Static Images"

integral-human-pose

Integral Human Pose Regression

language2pose

Language2Pose: Natural Language Grounded Pose Forecasting

mocogan

MoCoGAN: Decomposing Motion and Content for Video Generation

multiperson

openpose

OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation

pygcn

Graph Convolutional Networks in PyTorch

pytorch-image-models

PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more

stargan-v2

StarGAN v2 - Official PyTorch Implementation

stylegan

StyleGAN - Official TensorFlow Implementation

tinyml

transferlearning

Everything about Transfer Learning and Domain Adaptation--迁移学习

VIBE

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

video-to-pose3D

Convert video to 3D pose in one-key.

VideoPose3D

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

YOLOv3_PyTorch

Full implementation of YOLOv3 in PyTorch

zhaoyang.github.io

Notes