Active pictorial structures

File Description SizeFormat 
antonakos2015active.pdfAccepted version435.73 kBAdobe PDFView/Open
Title: Active pictorial structures
Authors: Antonakos, E
Alabort-I-Medina, J
Zafeiriou, S
Item Type: Conference Paper
Abstract: © 2015 IEEE.In this paper we present a novel generative deformable model motivated by Pictorial Structures (PS) and Active Appearance Models (AAMs) for object alignment in-the-wild. Inspired by the tree structure used in PS, the proposed Active Pictorial Structures (APS)1 model the appearance of the object using multiple graph-based pairwise normal distributions (Gaussian Markov Random Field) between the patches extracted from the regions around adjacent landmarks. We show that this formulation is more accurate than using a single multivariate distribution (Principal Component Analysis) as commonly done in the literature. APS employ a weighted inverse compositional Gauss-Newton optimization with fixed Jacobian and Hessian that achieves close to real-time performance and state-of-the-art results. Finally, APS have a spring-like graph-based deformation prior term that makes them robust to bad initializations. We present extensive experiments on the task of face alignment, showing that APS outperform current state-of-the-art methods. To the best of our knowledge, the proposed method is the first weighted inverse compositional technique that proves to be so accurate and efficient at the same time.
Issue Date: 14-Oct-2015
Date of Acceptance: 7-Jun-2015
URI: http://hdl.handle.net/10044/1/31946
DOI: https://dx.doi.org/10.1109/CVPR.2015.7299182
ISBN: 9781467369640
ISSN: 1063-6919
Publisher: IEEE
Start Page: 5435
End Page: 5444
Journal / Book Title: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Copyright Statement: © 2015 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works
Sponsor/Funder: Engineering & Physical Science Research Council (EPSRC)
Engineering & Physical Science Research Council (EPSRC)
Funder's Grant Number: EP/J017787/1
EP/L026813/1
Conference Name: CVPR 2015
Publication Status: Published
Start Date: 2015-06-07
Conference Place: Boston, MA
Appears in Collections:Faculty of Engineering
Computing



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Creative Commonsx