Skip to Main content Skip to Navigation
Documents associated with scientific events

Learning to Recover 3D Human Pose from Silhouettes

Ankur Agarwal 1 Bill Triggs 1
1 LEAR - Learning and recognition in vision
GRAVIR - IMAG - Laboratoire d'informatique GRAphique, VIsion et Robotique de Grenoble, Inria Grenoble - Rhône-Alpes, CNRS - Centre National de la Recherche Scientifique : FR71
Abstract : We will describe our ongoing work on learning-based methods for recovering 3D human body pose and motion from single images and from monocular image sequences. The methods work directly with raw image observations and require neither an explicit 3D body model nor a prior labelling of body parts in the image.
Keywords : visual learning human motion nonlinear regression kernel methods
Document type :
Documents associated with scientific events
Complete list of metadata
https://hal.inria.fr/inria-00548548
Contributor : Thoth Team <>
Submitted on : Monday, December 20, 2010 - 9:09:36 AM
Last modification on : Monday, December 28, 2020 - 3:44:02 PM
Long-term archiving on: : Monday, March 21, 2011 - 3:15:13 AM

Files

Vignette du document
Triggs-snowbird-abstract.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00548548, version 1

Collections

INRIA | IMAG | CNRS | INRIA-MECSCI | UGA

Citation

Ankur Agarwal, Bill Triggs. Learning to Recover 3D Human Pose from Silhouettes. Yann LeCun and Yoshua Bengio. Learning 2004 - Abstracts of the 2004 Snowbird Learning Workshop, Apr 2004, Snowbird, United States. 2004. ⟨inria-00548548⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

473

Files downloads

261

 

Contact                    Legal Notice                    Personal Data