Image transformations designed for Scene Text Recognition (STR) data augmentation. Published at ICCV 2021 Workshop on Interactive Labeling and Data Augmentation for Vision.

Segmentation models with pretrained backbones. PyTorch.

Official implementation of "SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers"

ABCNet_Chinese

1st Solution For ICDAR 2021 Competition on Mathematical Formula Detection（公式检测冠军方案）

deep learning for image processing including classification and object-detection etc.

RefineMask (CVPR 2021)

Production First and Production Ready End-to-End Speech Recognition Toolkit

【C++面试&C++学习指南】 这里整理了C++后端研发工程师面试和工作必备的知识点 。

轻量级文字识别技术创新大赛终榜第5名

Differentiable Multi-Granularity Human Representation Learning for Instance-Aware Human Semantic Parsing

更新的yolov5检测人脸和关键点，只依赖opencv库就可以运行，程序包含C++和Python两个版本的

Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognition

SOLOv2 pytorch (without mmdetection and mmcv)

[WACV2021] Oriented Object Detection in Aerial Images with Box Boundary-Aware Vectors

Pytorch implementation of "M-LSD: Towards Light-weight and Real-time Line Segment Detection"

基于各种机器学习和深度学习的中文微博情感分析

文本识别的数据增强

Code for "Primitive Representation Learning for Scene Text Recognition" (CVPR 2021)

使用GAN擦出文档印章 remove stamp by GAN

The project is an official implementation of our CVPR2019 paper "Deep High-Resolution Representation Learning for Human Pose Estimation"

An implementation of EQFace: A Simple Explicit Quality Network for Face Recognition (https://arxiv.org/abs/2105.00634, CVPR2021 AMFG Workshop)

一个目标检测的通用框架(不需要cuda编译)，支持Yolo全系列(v2~v5)、EfficientDet、RetinaNet、Cascade-RCNN等SOTA网络。

Official implementation of our CVPR2021 paper "OTA: Optimal Transport Assignment for Object Detection" in Pytorch.

🤘 awesome-semantic-segmentation

Focal Inverse Distance Transform Maps for Crowd Localization and Counting in Dense Crowd

Several simple examples for popular neural network toolkits calling custom CUDA operators.

An out-of-box human parsing representation extractor.

PyTorch implementation of EfficientNetV2