VideoX: a collection of video cross-modal models

国服PCR公主连结 多开自动农场脚本 基于opencv+UIAutomator

Official PyTorch Implementation of Learning Self-Similarity in Space and Time as Generalized Motion for Video Action Recognition, ICCV 2021

pycorrector is a toolkit for text error correction. 文本纠错，Kenlm，Seq2Seq_Attention，BERT，MacBERT，ELECTRA，ERNIE，Transformer等模型实现，开箱即用。

pytorch实现 Bert 做seq2seq任务，使用unilm方案,现在也可以做自动摘要，文本分类，情感分析，NER，词性标注等任务,支持t5模型，支持GPT2进行文章续写。

Video Action Understanding: A Tutorial

A detector oblivious keypoint matcher

基于pytorch写的CRNN文字识别~简化写法帮助入门

As-Projective-As-Possible (APAP) Image Stitching with Moving DLT - Python Implementation

code for Confidence-aware Non-repetitive Multimodal Transformers for TextCaps (AAAI 2021)

《深入浅出图神经网络：GNN原理解析》配套代码

ctcloss + centerloss crnn text recognition

SuperGlue: Learning Feature Matching with Graph Neural Networks (CVPR 2020, Oral)

Project code for ACM MM2020 paper: "TextRay: Contour-based Geometric Modeling for Arbitrary-shaped Scene Text Detection"

APAP FOR IMAGE STITCHING

Data and implementation of ECCV2020 paper 'Adaptive Text Recognition through Visual Matching'

table structure recognition

The code of "Mask TextSpotter v3: Segmentation Proposal Network for Robust Scene Text Spotting"

Extremely simple implement for Chinese OCR by PyTorch.

A pytorch re-implementation of Real-time Scene Text Detection with Differentiable Binarization

Deep relational reasoning graph network for arbitrary shape text detection; Accepted by CVPR 2020 (Oral). http://arxiv.org/abs/2003.07493

超轻量级中文ocr，支持竖排文字识别, 支持ncnn推理 , psenet(8.5M) + crnn(6.3M) + anglenet(1.5M) 总模型仅17M

A PyTorch implementation of "ContourNet: Taking a Further Step toward Accurate Arbitrary-shaped Scene Text Detection"

A PyTorch implementation of Mask TextSpotter

Captcha or Scene Text Recognition Implement with Pytorch

基于飞桨的OCR工具库，包含总模型仅8.6M的超轻量级中文OCR，单模型支持中英文数字组合识别、竖排文本识别、长文本识别。同时支持多种文本检测、文本识别的训练算法。