Code for paper: Memory Augment is All Your Need for image restoration(cloud,rain,shadow removal, low-light image enhancement, image deblur)即插即用提点的记忆模块

MegCup 2022第7名解决方案（8.983分，非RNN形式）

RAW-based blind denoising, 1st place in MegCup 2022 (Team Feedback)

RAW-based blind denoising, 3rd place in MegCup 2022 (Team Feedforward)

2022DCIC-基于文本字符的交易验证码识别

验证码识别

2021AIWIN交通银行手写字体OCR识别Top1方案

2021DIGIX 小样本菜单识别 星光卓越奖 小小快乐队伍 方案及源代码

利用语言模型，纠正OCR识别错误

从NLP出发对于OCR的深度实践集锦，重在实战

微信大数据2021 1st，qq浏览器2021 3rd，mind新闻推荐2020 1st，NAIC2020 AI+遥感影像 2nd

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows" on Object Detection and Instance Segmentation.

This is an official implementation for "Video Swin Transformers".

QQ浏览器2021AI算法大赛赛道一 第1名 方案

qq browser multimodal video similarity contest

More readable and flexible yolov5 with more backbone(gcn, resnet, shufflenet, moblienet, efficientnet, hrnet, swin-transformer, etc) and (cbam，dcn and so on), and tensorrt

PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.

The official code for “DocTr: Document Image Transformer for Geometric Unwarping and Illumination Correction”, ACM MM, Oral Paper, 2021.

ML模型代码

An open-source toolbox for action understanding based on PyTorch

[ECCV 2022] ByteTrack: Multi-Object Tracking by Associating Every Detection Box

研究生数学建模，本科生数学建模、数学建模竞赛优秀论文，数学建模算法，LaTeX论文模板，算法思维导图，参考书籍，Matlab软件教程，PPT

YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite

Replication of MOT project - DeepSort with attention blocks.

A platform for building proxies to bypass network restrictions.

Fast MOT base on yolo+deepsort, support yolo3 and yolo4

Chinese text detection and recognition based on CTPN + DENSENET using Keras and Tensor Flow，使用keras和tensorflow基于CTPN+Densenet实现的中文文本检测和识别