Jie's Notes


  • 首页

  • 分类

  • 归档

  • 标签

  • 简历

text detection paper && dataset

发表于 2019-05-21 | 分类于 科研

相关论文

2019

  • AAAI Scene Text Detection with Supervised Pyramid Context Network
  • TIP TextField: Learning A Deep Direction Field for Irregular Scene Text Detection
  • CVPR Pyramid Mask Text Detector
  • CVPR Character Region Awareness for Text Detection
  • CVPR Look More Than Once: An Accurate Detector for Text of Arbitrary Shapes
  • CVPR Shape Robust Text Detection with Progressive Scale Expansion Network
  • CVPR Tightness-aware Evaluation Protocol for Scene Text Detection
  • CVPR Towards Robust Curve Text Detection with Conditional Spatial Expansion
  • arxiv MSR: Multi-Scale Shape Regression for Scene Text Detection
  • arxiv TextMountain: Accurate Scene Text Detection via Instance Segmentation
  • arxiv TextCohesion: Detecting Text for Arbitrary Shapes
  • arxiv Arbitrary Shape Scene Text Detection with Adaptive Text Region Representation

2018

  • ECCV Accurate Scene Text Detection through Border Semantics Awareness and Bootstrapping
  • ECCV Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes
  • CVPR FOTS: Fast Oriented Text Spotting with a Unified Network
  • IJCAI IncepText: A New Inception-Text Module with Deformable PSROI Pooling for Multi-Oriented Scene Text Detection
  • TIP TextBoxes++: A Single-Shot Oriented Scene Text Detector
  • CVPR Rotation-Sensitive Regression for Oriented Scene Text Detection
  • CVPR Single Shot TextSpotter with Explicit Alignment and Attention
  • CVPR Multi-Oriented Scene Text Detection via Corner Localization and Region Segmentation
  • AAAI Feature Enhancement Network: A Refined Scene Text Detector
  • AAAI PixelLink: Detecting Scene Text via Instance Segmentation
  • AAAI SEE: Towards Semi-Supervised End-to-End Scene Text Recognition
  • ICPR Fused Text Segmentation Networks for Multi-oriented Scene Text Detection

2017

  • AAAI TextBoxes: A Fast Text Detector with a Single Deep Neural Network
  • CVPR Deep Matching Prior Network: Toward Tighter Multi-oriented Text Detection
  • CVPR Detecting Oriented Text in Natural Images by Linking Segments
  • CVPR EAST: An Efficient and Accurate Scene Text Detector
  • ICCV Single Shot Text Detector with Regional Attention

2016

  • CVPR Synthetic Data for Text Localisation in Natural Images
  • ECCV Detecting Text in Natural Image with Connectionist Text Proposal Network

文本检测数据集

  • CTW1500
    • paper
    • data
  • Chinese Text in the Wild(CTW)
    • paper
    • data
  • Reading Chinese Text in the Wild(RCTW-17)
    • paper
    • data
  • ICPR MWI 2018 competition
    • data
  • Total-Text
    • paper
    • data
  • Google FSNS(谷歌街景文本数据集)
    • paper
    • data
  • COCO-TEXT
    • paper
    • data
  • Synthetic Data for Text Localisation
    • paper
    • data
    • code Eng
    • code Chi
  • Synthetic Word Dataset
    • data
  • Caffe-ocr中文合成数据
    • data

object detection

发表于 2018-03-19 | 分类于 科研

img

1.two stage

  • 2013 RCNN
  • 2014 SPP-Net
  • 2015 Fast R-CNN
  • 2016 Faster R-CNN
  • 更好的特征网络
    • 2016 HyperNet
    • 2016 MS-CNN
    • 2016 PVANet
    • 2017 Light-Head R-CNN
  • 更精准的RPN
    • 2015 MR-CNN
    • 2016 FPN
    • 2016 CRAFT
  • 更完善的ROI分类
    • 2016 R—FCN、 2017 CoupleNet
    • 2017 Mask R-CNN
    • 2017 Cascade R-CNN
  • 样本后处理
    • 2016 OHEM
    • 2017 Soft-NMS
    • 2017 A-Fast-RCNN
  • 更大的mini-Batch
    • 2017 MegDet

2. one stage

  • 2013 overFeat
  • 2015 YOLO、2016 YOLO9000
  • 2015 G-CNN
  • 2015 SSD
  • 2017 RON

Hello World

发表于 2017-07-19

Welcome to Hexo! This is your very first post. Check documentation for more info. If you get any problems when using Hexo, you can find the answer in troubleshooting or you can ask me on GitHub.

Quick Start

Create a new post

1
$ hexo new "My New Post"

More info: Writing

Run server

1
$ hexo server

More info: Server

Generate static files

1
$ hexo generate

More info: Generating

Deploy to remote sites

1
$ hexo deploy

More info: Deployment

cjstyle

cjstyle

凡心所向,素履以往。

3 日志
1 分类
5 标签
© 2019 cjstyle