ICDAR2017 Robust Reading Challenge on COCO-Text

Publikation: Bidrag til tidsskrift › Konferenceartikel › Forskning › fagfællebedømt

Standard

ICDAR2017 Robust Reading Challenge on COCO-Text. / Belongie, Serge; Gómez, Raúl; Shi, Baoguang; Gomez-Pujol, Lluis; Neumann, Lukas; Veit, Andreas; Matas, Jiri; Karatzas, Dimosthenis.

I: IEEE Xplore Digital Library, 29.01.2018.

Publikation: Bidrag til tidsskrift › Konferenceartikel › Forskning › fagfællebedømt

Harvard

Belongie, S, Gómez, R, Shi, B, Gomez-Pujol, L, Neumann, L, Veit, A, Matas, J & Karatzas, D 2018, 'ICDAR2017 Robust Reading Challenge on COCO-Text', IEEE Xplore Digital Library. https://doi.org/10.1109/ICDAR.2017.234

APA

Belongie, S., Gómez, R., Shi, B., Gomez-Pujol, L., Neumann, L., Veit, A., Matas, J., & Karatzas, D. (2018). ICDAR2017 Robust Reading Challenge on COCO-Text. IEEE Xplore Digital Library. https://doi.org/10.1109/ICDAR.2017.234

Vancouver

Belongie S, Gómez R, Shi B, Gomez-Pujol L, Neumann L, Veit A o.a. ICDAR2017 Robust Reading Challenge on COCO-Text. IEEE Xplore Digital Library. 2018 jan. 29. https://doi.org/10.1109/ICDAR.2017.234

Author

Belongie, Serge ; Gómez, Raúl ; Shi, Baoguang ; Gomez-Pujol, Lluis ; Neumann, Lukas ; Veit, Andreas ; Matas, Jiri ; Karatzas, Dimosthenis. / ICDAR2017 Robust Reading Challenge on COCO-Text. I: IEEE Xplore Digital Library. 2018.

Bibtex

@inproceedings{cb9f423ff9f74bd09a2b71157424962d,
title = "ICDAR2017 Robust Reading Challenge on COCO-Text",
abstract = "This report presents the final results of the ICDAR 2017 Robust Reading Challenge on COCO-Text. A challenge on scene text detection and recognition based on the largest real scene text dataset currently available: the COCO-Text dataset. The competition is structured around three tasks: Text Localization, Cropped Word Recognition and End-To-End Recognition. The competition received a total of 27 submissions over the different opened tasks. This report describes the datasets and the ground truth, details the performance evaluation protocols used and presents the final results along with a brief summary of the participating methods.",
author = "Serge Belongie and Ra{\'u}l G{\'o}mez and Baoguang Shi and Lluis Gomez-Pujol and Lukas Neumann and Andreas Veit and Jiri Matas and Dimosthenis Karatzas",
year = "2018",
month = jan,
day = "29",
doi = "10.1109/ICDAR.2017.234",
language = "English",
journal = "IEEE Xplore Digital Library",

}

RIS

TY - GEN

T1 - ICDAR2017 Robust Reading Challenge on COCO-Text

AU - Belongie, Serge

AU - Gómez, Raúl

AU - Shi, Baoguang

AU - Gomez-Pujol, Lluis

AU - Neumann, Lukas

AU - Veit, Andreas

AU - Matas, Jiri

AU - Karatzas, Dimosthenis

PY - 2018/1/29

Y1 - 2018/1/29

N2 - This report presents the final results of the ICDAR 2017 Robust Reading Challenge on COCO-Text. A challenge on scene text detection and recognition based on the largest real scene text dataset currently available: the COCO-Text dataset. The competition is structured around three tasks: Text Localization, Cropped Word Recognition and End-To-End Recognition. The competition received a total of 27 submissions over the different opened tasks. This report describes the datasets and the ground truth, details the performance evaluation protocols used and presents the final results along with a brief summary of the participating methods.

AB - This report presents the final results of the ICDAR 2017 Robust Reading Challenge on COCO-Text. A challenge on scene text detection and recognition based on the largest real scene text dataset currently available: the COCO-Text dataset. The competition is structured around three tasks: Text Localization, Cropped Word Recognition and End-To-End Recognition. The competition received a total of 27 submissions over the different opened tasks. This report describes the datasets and the ground truth, details the performance evaluation protocols used and presents the final results along with a brief summary of the participating methods.

U2 - 10.1109/ICDAR.2017.234

DO - 10.1109/ICDAR.2017.234

M3 - Conference article

JO - IEEE Xplore Digital Library

JF - IEEE Xplore Digital Library

ER -

ID: 307526853