ICDAR2017 Competition on Reading Chinese Text in the Wild (RCTW-17)

Research output: Contribution to journal › Conference article › Research › peer-review

Standard

ICDAR2017 Competition on Reading Chinese Text in the Wild (RCTW-17). / Shi, Baoguang; Yao, Cong; Liao, Minghui; Yang, Mingkun; Xu, Pei; Cui, Linyan; Belongie, Serge; Lu, Shijian; Bai, Xiang.

In: Proceedings of the International Conference on Document Analysis and Recognition, ICDAR, 02.07.2017, p. 1429-1434.

Research output: Contribution to journal › Conference article › Research › peer-review

Harvard

Shi, B, Yao, C, Liao, M, Yang, M, Xu, P, Cui, L, Belongie, S, Lu, S & Bai, X 2017, 'ICDAR2017 Competition on Reading Chinese Text in the Wild (RCTW-17)', Proceedings of the International Conference on Document Analysis and Recognition, ICDAR, pp. 1429-1434. https://doi.org/10.1109/ICDAR.2017.233

APA

Shi, B., Yao, C., Liao, M., Yang, M., Xu, P., Cui, L., Belongie, S., Lu, S., & Bai, X. (2017). ICDAR2017 Competition on Reading Chinese Text in the Wild (RCTW-17). Proceedings of the International Conference on Document Analysis and Recognition, ICDAR, 1429-1434. https://doi.org/10.1109/ICDAR.2017.233

Vancouver

Shi B, Yao C, Liao M, Yang M, Xu P, Cui L et al. ICDAR2017 Competition on Reading Chinese Text in the Wild (RCTW-17). Proceedings of the International Conference on Document Analysis and Recognition, ICDAR. 2017 Jul 2;1429-1434. https://doi.org/10.1109/ICDAR.2017.233

Author

Shi, Baoguang ; Yao, Cong ; Liao, Minghui ; Yang, Mingkun ; Xu, Pei ; Cui, Linyan ; Belongie, Serge ; Lu, Shijian ; Bai, Xiang. / ICDAR2017 Competition on Reading Chinese Text in the Wild (RCTW-17). In: Proceedings of the International Conference on Document Analysis and Recognition, ICDAR. 2017 ; pp. 1429-1434.

Bibtex

@inproceedings{ea7ae20485e142bfb56fff5a37aa95d9,
title = "ICDAR2017 Competition on Reading Chinese Text in the Wild (RCTW-17)",
abstract = "Chinese is the most widely used language in the world. Algorithms that read Chinese text in natural images facilitate applications of various kinds. Despite the large potential value, datasets and competitions in the past primarily focus on English, which bares very different characteristics than Chinese. This report introduces RCTW, a new competition that focuses on Chinese text reading. The competition features a large-scale dataset with over 12,000 annotated images. Two tasks, namely text localization and end-To-end recognition, are set up. The competition took place from January 20 to May 31, 2017. 23 valid submissions were received from 19 teams. This report includes dataset description, task definitions, evaluation protocols, and results summaries and analysis. Through this competition, we call for more future research on the Chinese text reading problem.",
keywords = "Competition, Dataset, Detection, Recognition, Text",
author = "Baoguang Shi and Cong Yao and Minghui Liao and Mingkun Yang and Pei Xu and Linyan Cui and Serge Belongie and Shijian Lu and Xiang Bai",
note = "Funding Information: ACKNOWLEDGMENT The challenge is supported in part by NSFC 61222308. The authors thank Dr. Fei Yin and Dr. Cheng-Lin Liu for their suggestions. The authors also thank Zhiyong Liu, Yang Yang, Zhiqiang Zhang, Rui Yu and Xuelei Zhang for their efforts in annotating the data. Publisher Copyright: {\textcopyright} 2017 IEEE.; 14th IAPR International Conference on Document Analysis and Recognition, ICDAR 2017 ; Conference date: 09-11-2017 Through 15-11-2017",
year = "2017",
month = jul,
day = "2",
doi = "10.1109/ICDAR.2017.233",
language = "English",
pages = "1429--1434",
journal = "Proceedings of the International Conference on Document Analysis and Recognition, ICDAR",
issn = "1520-5363",

}

RIS

TY - GEN

T1 - ICDAR2017 Competition on Reading Chinese Text in the Wild (RCTW-17)

AU - Shi, Baoguang

AU - Yao, Cong

AU - Liao, Minghui

AU - Yang, Mingkun

AU - Xu, Pei

AU - Cui, Linyan

AU - Belongie, Serge

AU - Lu, Shijian

AU - Bai, Xiang

N1 - Funding Information: ACKNOWLEDGMENT The challenge is supported in part by NSFC 61222308. The authors thank Dr. Fei Yin and Dr. Cheng-Lin Liu for their suggestions. The authors also thank Zhiyong Liu, Yang Yang, Zhiqiang Zhang, Rui Yu and Xuelei Zhang for their efforts in annotating the data. Publisher Copyright: © 2017 IEEE.

PY - 2017/7/2

Y1 - 2017/7/2

N2 - Chinese is the most widely used language in the world. Algorithms that read Chinese text in natural images facilitate applications of various kinds. Despite the large potential value, datasets and competitions in the past primarily focus on English, which bares very different characteristics than Chinese. This report introduces RCTW, a new competition that focuses on Chinese text reading. The competition features a large-scale dataset with over 12,000 annotated images. Two tasks, namely text localization and end-To-end recognition, are set up. The competition took place from January 20 to May 31, 2017. 23 valid submissions were received from 19 teams. This report includes dataset description, task definitions, evaluation protocols, and results summaries and analysis. Through this competition, we call for more future research on the Chinese text reading problem.

AB - Chinese is the most widely used language in the world. Algorithms that read Chinese text in natural images facilitate applications of various kinds. Despite the large potential value, datasets and competitions in the past primarily focus on English, which bares very different characteristics than Chinese. This report introduces RCTW, a new competition that focuses on Chinese text reading. The competition features a large-scale dataset with over 12,000 annotated images. Two tasks, namely text localization and end-To-end recognition, are set up. The competition took place from January 20 to May 31, 2017. 23 valid submissions were received from 19 teams. This report includes dataset description, task definitions, evaluation protocols, and results summaries and analysis. Through this competition, we call for more future research on the Chinese text reading problem.

KW - Competition

KW - Dataset

KW - Detection

KW - Recognition

KW - Text

UR - http://www.scopus.com/inward/record.url?scp=85045202391&partnerID=8YFLogxK

U2 - 10.1109/ICDAR.2017.233

DO - 10.1109/ICDAR.2017.233

M3 - Conference article

AN - SCOPUS:85045202391

SP - 1429

EP - 1434

JO - Proceedings of the International Conference on Document Analysis and Recognition, ICDAR

JF - Proceedings of the International Conference on Document Analysis and Recognition, ICDAR

SN - 1520-5363

T2 - 14th IAPR International Conference on Document Analysis and Recognition, ICDAR 2017

Y2 - 9 November 2017 through 15 November 2017

ER -

ID: 301826449