liuguoyou Goto Github PK
Name: 刘国友
Type: User
Bio: xiaomi
Name: 刘国友
Type: User
Bio: xiaomi
Standardizing weights to accelerate micro-batch training
[WACV'18] Where and Who? Automatic Semantic-Aware Person Composition
Image Aesthetics Estimation (WACV18)
Winograd minimal convolution algorithm generator for convolutional neural networks.
A facial landmarks regressor
android 音视频播放SDK,几句代码即可实现音视频播放功能(支持:http、https、rtsp、rtp、rtmp、byte[]、加密视频和各种文件格式视频;包含视频截图、音轨选择、自定义视频滤镜、变速变调、声道切换、无缝切换surface(surfaceview和textureview)、视频比例设置等。)~
[SIGGRAPH Asia 2022 Technical Papers' Best Paper Award]
CODE
The repository containing tools and information about the WoodScape dataset.
Official PyTorch implement for WSR (Towards Lighter and Faster: Learning Wavelets Progressively for Image Super-Resolution).
A simple consistency training framework for semi-supervised image semantic segmentation
Official code for "X-HRNet: Towards Lightweight Human Pose Estimation with Spatially Unidimensional Self-Attention"
Automatically exported from code.google.com/p/xdog-demo
Source code for xfields (SIGGRAPH Asia 2020)
The official repo for Xihe: A 3D Vision-based Lighting Estimation Framework for Mobile Augmented Reality (MobiSys'21)
[SIGGRAPH2009] Modeling Human Color Perception under Extended Luminance Levels. This code provides a color appearance model (CAM) for high-dynamic-range (HDR) imaging. This code can be used for HDR tone-mapping and inverse tone-mapping.
A tool for efficient semi-supervised video object segmentation (great results with minimal manual labor) and a dataset for benchmarking
High-efficiency floating-point neural network inference operators for mobile and Web
XNOR-Net, CUDNN5 supported version of XNOR-Net-caffe: https://github.com/loswensiana/BWN-XNOR-caffe
Learning a Spatial Activation Function for Efficient Image Restoration
YangMingShan is a collection of iOS UI components that we created while building Yahoo apps.
Implementation of CVPR2019 paper - Photo Wake-Up: 3D Character Animation from a Single Photo
The pytorch re-implement of the official efficientdet with SOTA performance in real time and pretrained weights.
[archiving soon]
A practical hand tracking engine.
The first competitive instance segmentation approach that runs on small edge devices at real-time speeds.
YOLO9000: Better, Faster, Stronger - Real-Time Object Detection. 9000 classes!
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.