Publications Journal · 2023
VLCDoC: Vision-Language Contrastive Pre-Training Model for Cross-Modal Document Classification
In one paragraph
Learns cross-modal document representations from language and vision by aligning intra- and inter-modality relationships with a contrastive objective, instead of merging features into one joint space; effective on both small- and large-scale document classification datasets.
Cite
@article{bakkali2023vlcdoc,
title = {{VLCDoC: Vision-Language Contrastive Pre-Training Model for Cross-Modal Document Classification}},
author = {Bakkali, Souhail and Ming, Zuheng and Coustaty, Mickaël and Rusiñol, Marçal and Ramos Terrades, Oriol},
journal = {Pattern Recognition},
volume = {139},
pages = {109419},
year = {2023},
doi = {10.1016/j.patcog.2023.109419},
url = {https://arxiv.org/abs/2205.12029}
}