Joint training of a convolutional network and a graphical model for human pose estimation

Jonathan Tompson, Arjun Jain, Yann LeCun, Christoph Bregler

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

Abstract

This paper proposes a new hybrid architecture that consists of a deep Convolutional Network and a Markov Random Field. We show how this architecture is successfully applied to the challenging problem of articulated human pose estimation in monocular images. The architecture can exploit structural domain constraints such as geometric relationships between body joint locations. We show that joint training of these two model paradigms improves performance and allows us to significantly outperform existing state-of-the-art techniques.

Original languageEnglish (US)
Title of host publicationAdvances in Neural Information Processing Systems
PublisherNeural information processing systems foundation
Pages1799-1807
Number of pages9
Volume2
EditionJanuary
StatePublished - 2014
Event28th Annual Conference on Neural Information Processing Systems 2014, NIPS 2014 - Montreal, Canada
Duration: Dec 8 2014Dec 13 2014

Other

Other28th Annual Conference on Neural Information Processing Systems 2014, NIPS 2014
CountryCanada
CityMontreal
Period12/8/1412/13/14

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing

Cite this

Tompson, J., Jain, A., LeCun, Y., & Bregler, C. (2014). Joint training of a convolutional network and a graphical model for human pose estimation. In Advances in Neural Information Processing Systems (January ed., Vol. 2, pp. 1799-1807). Neural information processing systems foundation.

Joint training of a convolutional network and a graphical model for human pose estimation. / Tompson, Jonathan; Jain, Arjun; LeCun, Yann; Bregler, Christoph.

Advances in Neural Information Processing Systems. Vol. 2 January. ed. Neural information processing systems foundation, 2014. p. 1799-1807.

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

Tompson, J, Jain, A, LeCun, Y & Bregler, C 2014, Joint training of a convolutional network and a graphical model for human pose estimation. in Advances in Neural Information Processing Systems. January edn, vol. 2, Neural information processing systems foundation, pp. 1799-1807, 28th Annual Conference on Neural Information Processing Systems 2014, NIPS 2014, Montreal, Canada, 12/8/14.
Tompson J, Jain A, LeCun Y, Bregler C. Joint training of a convolutional network and a graphical model for human pose estimation. In Advances in Neural Information Processing Systems. January ed. Vol. 2. Neural information processing systems foundation. 2014. p. 1799-1807
Tompson, Jonathan ; Jain, Arjun ; LeCun, Yann ; Bregler, Christoph. / Joint training of a convolutional network and a graphical model for human pose estimation. Advances in Neural Information Processing Systems. Vol. 2 January. ed. Neural information processing systems foundation, 2014. pp. 1799-1807
@inproceedings{467a64cc72e249ffac0bd706929ab3a3,
title = "Joint training of a convolutional network and a graphical model for human pose estimation",
abstract = "This paper proposes a new hybrid architecture that consists of a deep Convolutional Network and a Markov Random Field. We show how this architecture is successfully applied to the challenging problem of articulated human pose estimation in monocular images. The architecture can exploit structural domain constraints such as geometric relationships between body joint locations. We show that joint training of these two model paradigms improves performance and allows us to significantly outperform existing state-of-the-art techniques.",
author = "Jonathan Tompson and Arjun Jain and Yann LeCun and Christoph Bregler",
year = "2014",
language = "English (US)",
volume = "2",
pages = "1799--1807",
booktitle = "Advances in Neural Information Processing Systems",
publisher = "Neural information processing systems foundation",
edition = "January",

}

TY - GEN

T1 - Joint training of a convolutional network and a graphical model for human pose estimation

AU - Tompson, Jonathan

AU - Jain, Arjun

AU - LeCun, Yann

AU - Bregler, Christoph

PY - 2014

Y1 - 2014

N2 - This paper proposes a new hybrid architecture that consists of a deep Convolutional Network and a Markov Random Field. We show how this architecture is successfully applied to the challenging problem of articulated human pose estimation in monocular images. The architecture can exploit structural domain constraints such as geometric relationships between body joint locations. We show that joint training of these two model paradigms improves performance and allows us to significantly outperform existing state-of-the-art techniques.

AB - This paper proposes a new hybrid architecture that consists of a deep Convolutional Network and a Markov Random Field. We show how this architecture is successfully applied to the challenging problem of articulated human pose estimation in monocular images. The architecture can exploit structural domain constraints such as geometric relationships between body joint locations. We show that joint training of these two model paradigms improves performance and allows us to significantly outperform existing state-of-the-art techniques.

UR - http://www.scopus.com/inward/record.url?scp=84930634156&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84930634156&partnerID=8YFLogxK

M3 - Conference contribution

VL - 2

SP - 1799

EP - 1807

BT - Advances in Neural Information Processing Systems

PB - Neural information processing systems foundation

ER -