Improving object detection in paintings based on time contexts

Maria Cristina Marinescu, Artem Reshetnikov, Joaquim More Lopez

Producción científica: Capítulo del libroContribución a congreso/conferenciarevisión exhaustiva

4 Citas (Scopus)

Resumen

This paper proposes a novel approach to object detection for the Cultural Heritage domain, which relies on combining Deep Learning and semantic metadata about candidate objects extracted from existing sources such as Wikidata, dictionaries, or Google NGram. Working with cultural heritage presents challenges not present in every-day images. In computer vision, object detection models are usually trained with datasets whose classes are not imaginary concepts, and have neither symbolic nor time-specific dimensions. Apart from this conceptual problem, the paintings are limited in number and represent the same concept in potentially very different styles. Finally, the metadata associated with the images is often poor or inexistent, which makes it hard to properly train a model. Our approach can improve the precision of object detection by placing the classes detected by a neural network model in time, based on the dates of their first known use. By taking into account the time of inception of objects such as the TV, cell phone, or scissors, and the appearance of some objects in the geographical space that corresponds to a painting (e.g. bananas or broccoli in 15th century Europe), we can correct and refine the detected objects based on their chronologic probability.

Idioma originalInglés
Título de la publicación alojadaProceedings - 20th IEEE International Conference on Data Mining Workshops, ICDMW 2020
EditoresGiuseppe Di Fatta, Victor Sheng, Alfredo Cuzzocrea, Carlo Zaniolo, Xindong Wu
EditorialIEEE Computer Society
Páginas926-932
Número de páginas7
ISBN (versión digital)9781728190129
DOI
EstadoPublicada - nov 2020
Publicado de forma externa
Evento20th IEEE International Conference on Data Mining Workshops, ICDMW 2020 - Virtual, Sorrento, Italia
Duración: 17 nov 202020 nov 2020

Serie de la publicación

NombreIEEE International Conference on Data Mining Workshops, ICDMW
Volumen2020-November
ISSN (versión impresa)2375-9232
ISSN (versión digital)2375-9259

Conferencia

Conferencia20th IEEE International Conference on Data Mining Workshops, ICDMW 2020
País/TerritorioItalia
CiudadVirtual, Sorrento
Período17/11/2020/11/20

Huella

Profundice en los temas de investigación de 'Improving object detection in paintings based on time contexts'. En conjunto forman una huella única.

Citar esto