Head pose estimation using learned discretization
Lists
Only you see this
Abstract
We address the problem of automated discretization for continuous labels in the context of head pose estimation from overhead cameras. Due to the lack of visual detail, precise head pose estimates are not always possible. A common approach is to discretize the space of head pose angles, turning a real-valued prediction task into a coarser (ordered) classification variant. Often, however, the ranges are arbitrarily defined (e.g., dividing up parameter space evenly). Our work incorporates label discretization into the feature learning process and improves the accuracy of coarse head pan angle prediction from overhead cameras on a benchmark dataset.
BibTeX
@inproceedings{kim2017head,
author = {Se Yeon Kim and Scott Spurlock and Richard Souvenir},
title = {{Head pose estimation using learned discretization}},
booktitle = {ICIP},
year = {2017},
url = {https://openreview.net/forum?id=x_qQ6NPWgs},
}Loading related content...