Better Appearance Models for Pictorial Structures

M. Eichner; V. Ferrari

Better Appearance Models for Pictorial Structures

M. Eichner, V. Ferrari

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

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.

Original language	English
Title of host publication	British Machine Vision Conference
Number of pages	11
Publication status	Published - 1 Sept 2009

Access to Document

Eichner Ferrari 2009 Better appearance modelsAccepted author manuscript, 5.92 MB

http://www.bmva.org/bmvc/2009/Papers/Paper055/Paper055.html

Cite this

@inproceedings{dac0e39fbf5543d5b52d63895f1ff6e4,

title = "Better Appearance Models for Pictorial Structures",

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. ",

author = "M. Eichner and V. Ferrari",

year = "2009",

month = sep,

day = "1",

language = "English",

booktitle = "British Machine Vision Conference",

}

TY - GEN

T1 - Better Appearance Models for Pictorial Structures

AU - Eichner, M.

AU - Ferrari, V.

PY - 2009/9/1

Y1 - 2009/9/1

N2 - 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.

AB - 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.

M3 - Conference contribution

BT - British Machine Vision Conference

ER -

Better Appearance Models for Pictorial Structures

Abstract

Access to Document

Fingerprint

Cite this