RCTW-17

ICDAR2017 Competition on Reading Chinese Text in the Wild

Introduction

RCTW-17 is a competition on reading Chinese Text in images. For training and testing, we provide a large-scale dataset that consists of various kinds of images, including street views, posters, menus, indoor scenes, and screenshots. See Dataset and Tasks for details.

News

  • The rctw-17 train dataset has been refineed to provide better and clearer annotations.We advise that all competitors should redownload the new rctw-17 train dataset from the dataset page!

  • The rctw-17 test dataset has been uploaded to test your model.All competitors can download the rctw-17 test dataset from the dataset page for testing!

  • The rctw-17 submission is open now! All competitors can submit the rctw-17 results under the guidance of the Task1 evaluation page and Task2 evaluation page!

Example Images

Example images

Organization Team

  • Baoguang Shi PhD student of the School of Electronic Information and Communications, Huazhong University of Science and Technology, China
  • Cong Yao Senior researcher at Megvii Technology Inc., China
  • Serge Belongie Professor at Cornell Tech and the Department of Computer Science at Cornell University, United States
  • Shijian Lu Head of Visual Attention Lab, Institute for Infocomm Research, A*STAR
  • Xiang Bai Professor of the School of Electronic Information and Communications, Huazhong University of Science and Technology

Important Dates

  • January 20 - April 30, 2017: Registration open
  • April 15, 2017: Test dataset available
  • April 15, 2017: Submission open
  • April 30, 2017: Submission deadline

20 Comments

FMT 2019-07-23 09:42

Attention please

The dataset entries from hust.edu.cn is unavailable, please download the datasets from Baidu Drive(training set) / Google Drive(testing set) .

SnoopyDream 2019-05-28 22:36

训练集的教育网的链接出错了

Songyt 2019-05-15 10:17

您好,第一次提交已经好几天还没有消息,请问还在审核吗?

xysszjs 2019-04-10 15:56

请问,参赛者可否允许知道其他参赛者有无使用额外数据?

Songyu 2018-12-31 09:55

提交task1是会500错误

Schumann @Songyu 2019-07-24 16:23

遇到同样的问题,请问解决了吗?

FMT 2018-10-18 13:04

Attention please

The old domain "icdar2017chinese.site" has been deprecated. The address of this site has been changed to "rctw.vlrlab.net" and the mail address of committee has been changed to "rctw@vlrlab.net".

clement10601 @FMT 2018-12-13 10:55

Unable to browse url for training set

http://mclab.eic.hust.edu.cn/UpLoadFiles/dataset/icdar2017/

Songyu 2018-08-22 11:00

您好,一般提交Task1多久会有结果?

FMT @Songyu 2018-10-18 13:08

首次提交需要管理员审核,人工审核通过之后,之后的提交都由服务器立即发送结果。

Songyu @FMT 2018-12-31 10:01

谢谢

chixma 2018-07-24 17:06

您好,我今天第一次提交Task1结果,但提交结果的时候出现如下错误,不知是否提交成功,请问该如何解决?

413 Request Entity Too Large

nginx/1.10.3 (Ubuntu)

FMT @chixma 2018-07-24 18:51

已解决,谢谢

sneffort @FMT 2018-09-21 22:01

请问该问题要怎么样解决,同样碰到此问题

Redaimao 2018-07-08 15:59

你好,测试集没办法下载,请问有百度云链接吗

HMH @Redaimao 2018-07-24 14:59

新增了下载通道

dugujiujian @Redaimao 2018-07-12 14:27

测试集无法下载

20103983yu @dugujiujian 2018-09-14 12:13

测试集无法下载

FMT @20103983yu 2018-10-18 13:11

We have added an entry of Google Drive.

zhoulinyuan 2018-07-07 02:04

有几张图像位置坐标是错的