Recurrent CNN for 3D Gaze Estimation using Appearance and Shape Cues
Abstract
Gaze behavior is an important non-verbal cue in social signal processing and human-computer interaction. In this paper, we tackle the problem of person- and head pose-independent 3D gaze estimation from remote cameras, using a multi-modal recurrent convolutional neural network (CNN). We propose to combine face, eyes region, and face landmarks as individual streams in a CNN to estimate gaze in still images. Then, we exploit the dynamic nature of gaze by feeding the learned features of all the frames in a sequence to a many-to-one recurrent module that predicts the 3D gaze vector of the last frame. Our multi-modal static solution is evaluated on a wide range of head poses and gaze directions, achieving a significant improvement of 14.6% over the state of the art on EYEDIAP dataset, further improved by 4% when the temporal modality is included.
Cite
@article{arxiv.1805.03064,
title = {Recurrent CNN for 3D Gaze Estimation using Appearance and Shape Cues},
author = {Cristina Palmero and Javier Selva and Mohammad Ali Bagheri and Sergio Escalera},
journal= {arXiv preprint arXiv:1805.03064},
year = {2018}
}
Comments
Proc. of British Machine Vision Conference (BMVC), BMVC 2018. Errata: in pg.5 the camera matrices of the transformation matrix W should be interchanged (correct version: W=C_n*M*(C_o)^-1)