Manifold Alignment for Person Independent Appearance-Based Gaze Estimation
Authors:
- Timo SchneiderTSTimo Schneider
- Boris SchauerteBSBoris Schauerte
- Rainer StiefelhagenRSRainer Stiefelhagen
- 1 August 2014
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10514651,p. 1167-1172
Abstract
We show that dually supervised manifold embedding can improve the performance of machine learning based person-independent and thus calibration-free gaze estimation. For this purpose, we perform a manifold embedding for each person in the training dataset and then learn a linear transformation that aligns the individual, person-dependent manifolds. We evaluate the effect of manifold alignment on the recently presented Columbia dataset, where we analyze the influence on 6 regression methods and 8 feature variants. Using manifold alignment, we are able to improve the person-independent gaze estimation performance by up to 31.2 % compared to the best approach without manifold alignment.Keywords
This publication has 20 references indexed in Scilit:
- Person independent 3D gaze estimation from remote RGB-D cameras2013
- Gaze estimation from multimodal Kinect data2012
- LIBSVMACM Transactions on Intelligent Systems and Technology, 2011
- A Head Pose-free Approach for Appearance-based Gaze Estimation2011
- Synchronized Submanifold Embedding for Person-Independent Pose Estimation and BeyondIEEE Transactions on Image Processing, 2008
- An Incremental Learning Method for Unconstrained Gaze Estimation2008
- Biased Manifold Embedding: A Framework for Person-Independent Head Pose Estimation2007
- An Introduction to Kernel and Nearest-Neighbor Nonparametric RegressionThe American Statistician, 1992
- Multivariate Adaptive Regression SplinesThe Annals of Statistics, 1991
- Texture Unit, Texture Spectrum, And Texture AnalysisIEEE Transactions on Geoscience and Remote Sensing, 1990