Heterogeneous Multi-task Learning for Human Pose Estimation with Deep Convolutional Neural Network

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review

73 Scopus Citations
View graph of relations

Author(s)

Detail(s)

Original languageEnglish
Pages (from-to)19-36
Journal / PublicationInternational Journal of Computer Vision
Volume113
Issue number1
Online published26 Sept 2014
Publication statusPublished - May 2015

Abstract

We propose a heterogeneous multi-task learning framework for human pose estimation from monocular images using a deep convolutional neural network. In particular, we simultaneously learn a human pose regressor and sliding-window body-part and joint-point detectors in a deep network architecture. We show that including the detection tasks helps to regularize the network, directing it to converge to a good solution. We report competitive and state-of-art results on several datasets. We also empirically show that the learned neurons in the middle layer of our network are tuned to localized body parts.

Research Area(s)

  • Deep Learning, Human Pose Estimation