Publications Workshop · 2020
Visual and Textual Deep Feature Fusion for Document Image Classification
In one paragraph
A two-stream architecture that jointly learns visual features of document images and embeddings of their text, with an investigation of widely used backbones and word-embedding procedures.
Cite
@inproceedings{bakkali2020visual,
title = {{Visual and Textual Deep Feature Fusion for Document Image Classification}},
author = {Bakkali, Souhail and Ming, Zuheng and Coustaty, Mickaël and Rusiñol, Marçal},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
pages = {562--563},
year = {2020},
doi = {10.1109/CVPRW50498.2020.00289}
}