Appearance Sharing for Collective Human Pose Estimation

M. Eichner, Vittorio Ferrari

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

While human pose estimation (HPE) techniques usually process each test image independently, in real applications images come in collections containing interdependent images. Often several images have similar backgrounds or show persons wearing similar clothing (foreground). We present a novel human pose estimation technique to exploit these dependencies by sharing appearance models between images. Our technique automatically determines which images in the collection should share appearance. We extend the state-of-the art HPE model of Yang and Ramanan to include our novel appearance sharing cues and demonstrate on the highly challenging Leeds Sports Poses dataset that they lead to better results than traditional single-image pose estimation.
Original languageEnglish
Title of host publicationComputer Vision – ACCV 2012
Subtitle of host publication11th Asian Conference on Computer Vision, Daejeon, Korea, November 5-9, 2012, Revised Selected Papers, Part I
PublisherSpringer
Pages138
Number of pages151
ISBN (Electronic)978-3-642-37331-2
ISBN (Print)978-3-642-37330-5
DOIs
Publication statusPublished - 2013

Publication series

NameLecture Notes in Computer Science
PublisherSpringer Berlin Heidelberg
Volume7724
ISSN (Print)0302-9743

Fingerprint

Dive into the research topics of 'Appearance Sharing for Collective Human Pose Estimation'. Together they form a unique fingerprint.

Cite this