PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Better appearance models for pictorial structures
Marcin Eichner and Vittorio Ferrari
In: BMVC 2009, 7-10 Sep 2009, London, UK.

Abstract

We present a novel approach for estimating body part appearance models for pictorial structures. We learn latent relationships between the appearance of different body parts from annotated images, which then help in estimating better appearance models on novel images. The learned appearance models are general, in that they can be plugged into any pictorial structure engine. In a comprehensive evaluation we demonstrate the bene?ts brought by the new appearance models to an existing articulated human pose estimation algorithm, on hundreds of highly challenging images from the TV series Buffy the vampire slayer and the PASCAL VOC 2008 challenge.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Oral)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Machine Vision
ID Code:5468
Deposited By:Marcin Eichner
Deposited On:27 September 2009