Heterogeneous Multi-task Learning for Human Pose Estimation with Deep Convolutional Neural Network
Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review
Author(s)
Related Research Unit(s)
Detail(s)
Original language | English |
---|---|
Pages (from-to) | 19-36 |
Journal / Publication | International Journal of Computer Vision |
Volume | 113 |
Issue number | 1 |
Online published | 26 Sept 2014 |
Publication status | Published - May 2015 |
Link(s)
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
Citation Format(s)
Heterogeneous Multi-task Learning for Human Pose Estimation with Deep Convolutional Neural Network. / Li, Sijin; Liu, Zhi-Qiang; Chan, Antoni B.
In: International Journal of Computer Vision, Vol. 113, No. 1, 05.2015, p. 19-36.
In: International Journal of Computer Vision, Vol. 113, No. 1, 05.2015, p. 19-36.
Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review