PatFig: Generating Short and Long Captions for Patent Figures

Dana Aubakirova (1, 2) , Kim Gerdes (1, 3, 2) , Lufei Liu (2)

1 LISN - Laboratoire Interdisciplinaire des Sciences du Numérique
2 Qatent - Qatent SAS
3 Université Paris-Saclay

This paper introduces Qatent PatFig, a novel large-scale patent figure dataset comprising 30,000+ patent figures from over 11,000 European patent applications. For each figure, this dataset provides short and long captions, reference numerals, their corresponding terms, and the minimal claim set that describes the interactions between the components of the image. To assess the usability of the dataset, we finetune an LVLM model on Qatent PatFig to generate short and long descriptions, and we investigate the effects of incorporating various text-based cues at the prediction stage of the patent figure captioning process.

Domaines: Apprentissage [cs.LG]; Intelligence artificielle [cs.AI]; Vision par ordinateur et reconnaissance de formes [cs.CV]

Dana Aubakirova, Kim Gerdes, Lufei Liu. PatFig: Generating Short and Long Captions for Patent Figures. ICCV workshop: CLVL: 5th Workshop on Closing the Loop Between Vision and Language, Computer Vision Foundation, Oct 2023, Paris, France. pp.2843-2849, ⟨10.1109/ICCVW60793.2023.00305⟩. ⟨hal-04408316⟩