SOTAVerified

Recurrent CNN for 3D Gaze Estimation using Appearance and Shape Cues

2018-05-08Code Available0· sign in to hype

Cristina Palmero, Javier Selva, Mohammad Ali Bagheri, Sergio Escalera

Code Available — Be the first to reproduce this paper.

Reproduce

Code

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.

Tasks

Benchmark Results

DatasetModelMetricClaimedVerifiedStatus
EYEDIAP (floating target)RecurrentGaze (Temporal)Angular Error5.19Unverified
EYEDIAP (floating target)RecurrentGaze (Static)Angular Error5.43Unverified
EYEDIAP (screen target)RecurrentGaze (Static)Angular Error3.38Unverified
EYEDIAP (screen target)RecurrentGaze (Temporal)Angular Error3.4Unverified

Reproductions