method: 4Paradigm-Data-Intelligence2019-05-30

Authors: ACVG

Description: Recognition model: Based on Transformer with backbone ResNet50. A voting process is done to identify the language of recognized transcript. Train-set: 2017 MLT task2 train-set & 2019 MLT task2 train-set & 2019 MLT Synthetic dataset.

method: HUST(GSPA)2019-01-19

Authors: Changxu Cheng

Description: Convolution layers followed by 2 branches: Global Squeezer (GS) and Patch Aggregator (PA). Other process is the same as in HUST (GS). The paper will be available soon.

method: CLOVA-AI / PAPAGO2018-08-01

Authors: Sunghyo Chung, Youngmin Baek, Hwalsuk Lee, Jaegul Choo

Description: We formulate script identification as a semantic segmentation task. We use both MLT task1 and task2 datasets for training. CLOVA-AI team, Naver Corp.

Ranking Table

Description Paper Source Code
DateMethodScript classification accuracy
2019-05-304Paradigm-Data-Intelligence90.12%
2019-01-19HUST(GSPA)89.42%
2018-08-01CLOVA-AI / PAPAGO89.01%
2019-01-17HUST(GS)88.51%
2017-07-02CNN based method 788.09%
2017-06-28SCUT-DLVClab87.69%
2017-07-01CNN based method 487.33%
2017-07-01CNN based method 586.97%
2017-06-30CNN based method 286.60%
2017-07-02BLCT86.34%
2017-07-02BLCT86.24%
2017-06-02ecn-based method82.20%
2017-07-01TH-DL80.72%
2017-07-01An approach towards Word-Level Multi-Script Identification using Deep Transfer Features and SVM74.81%
2017-07-01TNet48.33%
2017-07-01TH-CNN43.22%

Ranking Graphic