Multi-View Face Pose Estimation Based on Supervised ISA Learning

Authors:
XianHuan Peng;XinWen Hou;QianSheng Cheng
Affiliations:
-;-;-
Venue:
FGR '02 Proceedings of the Fifth IEEE International Conference on Automatic Face and Gesture Recognition
Year:
2002

Citing 0
Cited 4

Real-time View-based Face Alignment using Active Wavelet Networks

AMFG '03 Proceedings of the IEEE International Workshop on Analysis and Modeling of Faces and Gestures
Face Pose Estimation and Synthesis by 2D Morphable Model

Computational Intelligence and Security
A view-based statistical system for multi-view face detection and pose estimation

Image and Vision Computing
Head pose estimation in seminar room using multi view face detectors

CLEAR'06 Proceedings of the 1st international evaluation conference on Classification of events, activities and relationships

Quantified Score

Hi-index	0.00

Visualization

Abstract

Independent subspace analysis (ISA) is able to learn view-subspaces unsupervisedly from (view-unlabled) multi-view face examples \cite{Li-ISA-ICCV-01}. In this paper, we explain underlying reasons for the emergent formation of ISA view-subspaces. Based on the analysis, we present a supervised method for more effective learning of view-subspace, assuming that view-labeled face examples are available. The models thus learned give more accurate pose estimation than obtained with the unsupervised ISA.