TY - CONF
T1 - Fusing deep learned and hand-crafted features of appearance, shape, and dynamics for automatic pain estimation
AU - Egede, Joy Onyekachukwu
AU - Valstar, Michel F.
AU - Martinez, Brais
N1 - Note: Published in 2017 IEEE 12th International Conference on Automatic Face & Gesture Recognition (FG 2017). Piscataway, N.J. : IEEE, c2017. Electronic ISBN: 978-1-5090-4023-0. pp. 689-696, doi:10.1109/FG.2017.87 © 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
PY - 2017/5/30
Y1 - 2017/5/30
N2 - Automatic continuous time, continuous value assessment of a patient's pain from face video is highly sought after by the medical profession. Despite the recent advances in deep learning that attain impressive results in many domains, pain estimation risks not being able to benefit from this due to the difficulty in obtaining data sets of considerable size. In this work we propose a combination of hand-crafted and deep-learned features that makes the most of deep learning techniques in small sample settings. Encoding shape, appearance, and dynamics, our method significantly outperforms the current state of the art, attaining a RMSE error of less than 1 point on a 16-level pain scale, whilst simultaneously scoring a 67.3% Pearson correlation coefficient between our predicted pain level time series and the ground truth.
AB - Automatic continuous time, continuous value assessment of a patient's pain from face video is highly sought after by the medical profession. Despite the recent advances in deep learning that attain impressive results in many domains, pain estimation risks not being able to benefit from this due to the difficulty in obtaining data sets of considerable size. In this work we propose a combination of hand-crafted and deep-learned features that makes the most of deep learning techniques in small sample settings. Encoding shape, appearance, and dynamics, our method significantly outperforms the current state of the art, attaining a RMSE error of less than 1 point on a 16-level pain scale, whilst simultaneously scoring a 67.3% Pearson correlation coefficient between our predicted pain level time series and the ground truth.
KW - Pain, Estimation, Feature extraction, Face, Shape, Physiology, Machine learning
KW - Pain, Estimation, Feature extraction, Face, Shape, Physiology, Machine learning
M3 - Paper
SP - 689
EP - 696
T2 - 12th IEEE Conference on Face and Gesture Recognition (FG 2017)
Y2 - 30 May 2017 through 3 June 2017
ER -