Eye gaze is an important non-verbal cue for human affect analysis. Recent gaze estimation work indicated that information from the full face region can benefit performance. Pushing this idea further, we propose an appearance-based method that, in contrast to a long-standing line of work in computer vision, only takes the full face image as input. Our method encodes the face image using a convolutional neural network with spatial weights applied on the feature maps to flexibly suppress or enhance information in different facial regions. Through extensive evaluation, we show that our full-face method significantly outperforms the state of the art for both 2D and 3D gaze estimation, achieving improvements of up to 14.3% on MPIIGaze and 27.7% on EYEDIAP for person-independent 3D gaze estimation. We further show that this improvement is consistent across different illumination conditions and gaze directions and particularly pronounced for the most challenging extreme head poses.
%0 Report
%1 zhang16_arxiv
%A Zhang, Xucong
%A Sugano, Yusuke
%A Fritz, Mario
%A Bulling, Andreas
%D 2016
%K hcics vis
%P 1--10
%T It's Written All Over Your Face: Full-Face Appearance-Based Gaze Estimation
%U https://arxiv.org/abs/1611.08860
%X Eye gaze is an important non-verbal cue for human affect analysis. Recent gaze estimation work indicated that information from the full face region can benefit performance. Pushing this idea further, we propose an appearance-based method that, in contrast to a long-standing line of work in computer vision, only takes the full face image as input. Our method encodes the face image using a convolutional neural network with spatial weights applied on the feature maps to flexibly suppress or enhance information in different facial regions. Through extensive evaluation, we show that our full-face method significantly outperforms the state of the art for both 2D and 3D gaze estimation, achieving improvements of up to 14.3% on MPIIGaze and 27.7% on EYEDIAP for person-independent 3D gaze estimation. We further show that this improvement is consistent across different illumination conditions and gaze directions and particularly pronounced for the most challenging extreme head poses.
@techreport{zhang16_arxiv,
abstract = {Eye gaze is an important non-verbal cue for human affect analysis. Recent gaze estimation work indicated that information from the full face region can benefit performance. Pushing this idea further, we propose an appearance-based method that, in contrast to a long-standing line of work in computer vision, only takes the full face image as input. Our method encodes the face image using a convolutional neural network with spatial weights applied on the feature maps to flexibly suppress or enhance information in different facial regions. Through extensive evaluation, we show that our full-face method significantly outperforms the state of the art for both 2D and 3D gaze estimation, achieving improvements of up to 14.3% on MPIIGaze and 27.7% on EYEDIAP for person-independent 3D gaze estimation. We further show that this improvement is consistent across different illumination conditions and gaze directions and particularly pronounced for the most challenging extreme head poses.},
added-at = {2024-07-11T10:05:52.000+0200},
author = {Zhang, Xucong and Sugano, Yusuke and Fritz, Mario and Bulling, Andreas},
biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2f01622136a07806d7cbdc8b447a1bcb4/hcics},
interhash = {aff95254a3e4799683ca1e1faac8e691},
intrahash = {f01622136a07806d7cbdc8b447a1bcb4},
keywords = {hcics vis},
note = {arXiv:1611.08860},
pages = {1--10},
timestamp = {2024-07-11T10:11:36.000+0200},
title = {It's Written All Over Your Face: Full-Face Appearance-Based Gaze Estimation},
url = {https://arxiv.org/abs/1611.08860},
year = 2016
}
