Hierarchical conditional random fields for parts based models matching


Autoria(s): Roig Noguera, Gemma
Contribuinte(s)

Agència de Gestió d'Ajuts Universitaris i de Recerca

Fernández Ubiergo, Gabriel

Data(s)

01/06/2012

Resumo

A parts based model is a parametrization of an object class using a collection of landmarks following the object structure. The matching of parts based models is one of the problems where pairwise Conditional Random Fields have been successfully applied. The main reason of their effectiveness is tractable inference and learning due to the simplicity of involved graphs, usually trees. However, these models do not consider possible patterns of statistics among sets of landmarks, and thus they sufffer from using too myopic information. To overcome this limitation, we propoese a novel structure based on a hierarchical Conditional Random Fields, which we explain in the first part of this memory. We build a hierarchy of combinations of landmarks, where matching is performed taking into account the whole hierarchy. To preserve tractable inference we effectively sample the label set. We test our method on facial feature selection and human pose estimation on two challenging datasets: Buffy and MultiPIE. In the second part of this memory, we present a novel approach to multiple kernel combination that relies on stacked classification. This method can be used to evaluate the landmarks of the parts-based model approach. Our method is based on combining responses of a set of independent classifiers for each individual kernel. Unlike earlier approaches that linearly combine kernel responses, our approach uses them as inputs to another set of classifiers. We will show that we outperform state-of-the-art methods on most of the standard benchmark datasets.

Formato

23 p.

Identificador

http://hdl.handle.net/2072/196359

Idioma(s)

cat

Relação

Els ajuts de l'AGAUR;2011FI_B2 00048

Direitos

info:eu-repo/semantics/openAccess

L'accés als continguts d'aquest document queda condicionat a l'acceptació de les condicions d'ús establertes per la següent llicència Creative Commons: http://creativecommons.org/licenses/by-nc-nd/3.0/es/

Fonte

RECERCAT (Dipòsit de la Recerca de Catalunya)

Palavras-Chave #Simulació per ordinador #Biometria
Tipo

info:eu-repo/semantics/article

info:eu-repo/semantics/draft