Unsupervised discovery of visual object class hierarchies

Objects in the world can be arranged into a hierarchy based on their semantic meaning (e.g. organism - animal - feline - cat). What about defining a hierarchy based on the visual appearance of objects? This paper investigates ways to automatically discover a hierarchical structure for the visual wor...

ver descrição completa

Detalhes bibliográficos
Principais autores: Sivic, J, Russell, BC, Zisserman, A, Freeman, WT, Efros, AA
Formato: Conference item
Idioma:English
Publicado em: IEEE 2008