TY  - CONF
AU  - Raul Gomez
AU  - Ali Furkan Biten
AU  - Lluis Gomez
AU  - Jaume Gibert
AU  - Marçal Rusiñol
AU  - Dimosthenis Karatzas
A2  - ICDAR
PY  - 2019//
TI  - Selective Style Transfer for Text
BT  - 15th International Conference on Document Analysis and Recognition
SP  - 805
EP  - 812
KW  - transfer
KW  - text style transfer
KW  - data augmentation
KW  - scene text detection
N2  - This paper explores the possibilities of image style transfer applied to text maintaining the original transcriptions. Results on different text domains (scene text, machine printed text and handwritten text) and cross-modal results demonstrate that this is feasible, and open different research lines. Furthermore, two architectures for selective style transfer, which meanstransferring style to only desired image pixels, are proposed. Finally, scene text selective style transfer is evaluated as a data augmentation technique to expand scene text detection datasets, resulting in a boost of text detectors performance. Our implementation of the described models is publicly available.
UR  - https://ieeexplore.ieee.org/abstract/document/8977953
L1  - http://refbase.cvc.uab.es/files/GBG2019.pdf
UR  - http://dx.doi.org/10.1109/ICDAR.2019.00134
N1  - DAG; 600.129; 600.135; 601.338; 601.310; 600.121
ID  - Raul Gomez2019
ER  -