GXYM

DRRG

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

TextBPN-Plus-Plus

Arbitrary Shape Text Detection via Boundary Transformer；The paper at: https://arxiv.org/abs/2205.05320, which has been accepted by IEEE Transactions on Multimedia (T-MM 2023).

TextBPN

Adaptive Boundary Proposal Network for Arbitrary Shape Text Detection； Accepted by ICCV2021；The paper at: http://arxiv.org/abs/2107.12664

TextPMs

Arbitrary Shape Text Detection via Segmentation with Probability Maps; accepted by TPAMI2022

GHM_Loss

The tensorflow implementation of GHM loss include class loss and regression loss. GHM loss is peoposed in "Gradient Harmonized Single-stage Detector" published on AAAI 2019 (Oral).

KPN

The code of Kernel Proposal Network for Arbitrary Shape Text Detection. The paper has been accepted by TNNLS 2022, which is available at: https://arxiv.org/abs/2203.06410

OHEM-loss

tensorflow implementation of OHEM loss and Support the sigmoid or softmax entropy loss

GloRe

Tensorflow implementation of Global Reasoning unit (GloRe) from Graph-Based Global Reasoning Networks. GCN Network Blok

Focal-loss

The code is tensorflow implement for focal loss for Dense Object Detection. https://arxiv.org/abs/1708.02002

AnalysisEEG

2020年研究生数学建模竞赛C题-脑电波分析（代码及数据）

TaggingTool

An annotation tool for target detection and text detection, which supports both image and video media files and only supports Windows system environment. labelMe, Tagging, Annotation.

TextFormat_To_cocoJson

converting detection txt format for COCO json format

GTR

Scene text recognition

python-Interface-Cpp

Interface　python code by C++ , support python3

GXYM.github.io

MultimodalOCR

On the Hidden Mystery of OCR in Large Multimodal Models (Evaluation Pipeline)

unilm

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities