Of gods and goats: weakly supervised learning of figurative art

The objective of this paper is to automatically annotate images of gods and animals in decorations on classical Greek vases. Such images often require expert knowledge in labelling. We start from a large dataset of images of vases with associated brief text descriptions. <br> We develop a wea...

Celý popis

Podrobná bibliografie
Hlavní autoři: Crowley, E, Zisserman, A
Médium: Conference item
Jazyk:English
Vydáno: British Machine Vision Association and Society for Pattern Recognition 2013