Authors: Anna Altynova, Valeria Kolycheva, Dmitry Grigoriev & Alexander Semenov
Journal: IAES International Journal of Artificial Intelligence
Abstract: Image captioning is a question of great interest in a wide range of applications.In the art market there is a particularly acute shortage of specialized machinelearning methods for accelerated and at the same time in-depth study of oftentoo specific aspects of art. One of the main difficulties is caused by ambiguousnames of art works, as well as clarifying (in practice, often complicating under-standing and perception) signatures of the authors to them. Although previousresearch has established that captioning of photos can be done with high efficacy,there is little published data about generation of captions for artistic paintings.In this research, we utilize a transformer architecture to generate an artionymfor a given painting in author’s manner. We describe the model and report itsperformance on different art styles. We assess the model performance with anexpert evaluation and image captioning metrics, and then discuss their capacityto analyze art-related names.
Journal: IAES International Journal of Artificial Intelligence
Abstract: Image captioning is a question of great interest in a wide range of applications.In the art market there is a particularly acute shortage of specialized machinelearning methods for accelerated and at the same time in-depth study of oftentoo specific aspects of art. One of the main difficulties is caused by ambiguousnames of art works, as well as clarifying (in practice, often complicating under-standing and perception) signatures of the authors to them. Although previousresearch has established that captioning of photos can be done with high efficacy,there is little published data about generation of captions for artistic paintings.In this research, we utilize a transformer architecture to generate an artionymfor a given painting in author’s manner. We describe the model and report itsperformance on different art styles. We assess the model performance with anexpert evaluation and image captioning metrics, and then discuss their capacityto analyze art-related names.