Cross-modal (text and figures) Analysis of a Scientific Corpus from Semantic Scholar - images

In this notebook we show the application of cross-modal techniques to improve the categorization of scientific papers through content related to figures, using both the textual part (captions) and the visual part (figures, diagrams, images) jointly. To this purpose, we use several CNN models and execute some experiments, illustrating our approach. This deposit contains high quality versions of the images used in the analysis.