VTKEL: A resource for Visual-Textual-Knowledge Entity Linking

Shahi Dost, Luciano Serafini, Marco Rospocher, Lamberto Ballan, Alessandro SperdutiFigshare 2019 · DOI · OpenAlex

Abstract

VTKL dataset, contains documents composed of pictures with five corresponding textual captions for each image. The VTKL dataset is obtained by extending the Flikr30k dataset, designed for visual-textual mention alignment, with links to YAGO ontolgy, one of the largest <em>web knowledge base</em>. These links are obtained automatically by processing each image caption with PIKES, an <em>NLP</em> tool for <em>entity recognition</em> and <em>linking</em>.
BibTeX
@inproceedings{dost2019vtkel,
  author = {Shahi Dost and Luciano Serafini and Marco Rospocher and Lamberto Ballan and Alessandro Sperduti},
  title = {{VTKEL: A resource for Visual-Textual-Knowledge Entity Linking}},
  booktitle = {Figshare},
  year = {2019},
  doi = {10.6084/m9.figshare.7882781.v3},
}

Loading related content...

Figure