Improving object detection in paintings based on time contexts

Maria Cristina Marinescu, Artem Reshetnikov, Joaquim More Lopez

Producció científica: Capítol de llibreContribució a congrés/conferènciaAvaluat per experts

5 Cites (Scopus)

Resum

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 originalAnglès
Títol de la publicacióProceedings - 20th IEEE International Conference on Data Mining Workshops, ICDMW 2020
EditorsGiuseppe Di Fatta, Victor Sheng, Alfredo Cuzzocrea, Carlo Zaniolo, Xindong Wu
EditorIEEE Computer Society
Pàgines926-932
Nombre de pàgines7
ISBN (electrònic)9781728190129
DOIs
Estat de la publicacióPublicada - de nov. 2020
Publicat externament
Esdeveniment20th IEEE International Conference on Data Mining Workshops, ICDMW 2020 - Virtual, Sorrento, Italy
Durada: 17 de nov. 202020 de nov. 2020

Sèrie de publicacions

NomIEEE International Conference on Data Mining Workshops, ICDMW
Volum2020-November
ISSN (imprès)2375-9232
ISSN (electrònic)2375-9259

Conferència

Conferència20th IEEE International Conference on Data Mining Workshops, ICDMW 2020
País/TerritoriItaly
CiutatVirtual, Sorrento
Període17/11/2020/11/20

Fingerprint

Navegar pels temes de recerca de 'Improving object detection in paintings based on time contexts'. Junts formen un fingerprint únic.

Com citar-ho