University of Oulu

L. Zafeiriou, E. Antonakos, S. Zafeiriou and M. Pantic, "Joint Unsupervised Deformable Spatio-Temporal Alignment of Sequences," 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, 2016, pp. 3382-3390. doi: 10.1109/CVPR.2016.368

Joint unsupervised deformable spatio-temporal alignment of sequences

Saved in:
Author: Zafeiriou, Lazaros1; Antonakos, Epameinondas1; Zafeiriou, Stefanos1,2;
Organizations: 1Imperial College London, UK
2Center for Machine Vision and Signal Analysis, University of Oulu, Finland
3University of Twente, The Netherlands
Format: article
Version: accepted version
Access: open
Online Access: PDF Full Text (PDF, 1.4 MB)
Persistent link:
Language: English
Published: Institute of Electrical and Electronics Engineers, 2016
Publish Date: 2019-02-27


Typically, the problems of spatial and temporal alignment of sequences are considered disjoint. That is, in order to align two sequences, a methodology that (non)-rigidly aligns the images is first applied, followed by temporal alignment of the obtained aligned images. In this paper, we propose the first, to the best of our knowledge, methodology that can jointly spatio-temporally align two sequences, which display highly deformable texture-varying objects. We show that by treating the problems of deformable spatial and temporal alignment jointly, we achieve better results than considering the problems independent. Furthermore, we show that deformable spatio-temporal alignment of faces can be performed in an unsupervised manner (i.e., without employing face trackers or building person-specific deformable models).

see all

ISBN Print: 978-1-4673-8851-1
Pages: 3382 - 3390
DOI: 10.1109/CVPR.2016.368
Host publication: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Conference: IEEE Conference on Computer Vision and Pattern Recognition
Type of Publication: A4 Article in conference proceedings
Field of Science: 113 Computer and information sciences
Funding: The work of E. Antonakos was supported by EPSRC project EP/J017787/1 (4DFAB). The work of S. Zafeiriou was funded by the FiDiPro program of Tekes (project number: 1849/31/2015). The work of M. Pantic and L. Zafeiriou was partially supported by EPSRC project EP/N007743/1 (FACER2VM).
Copyright information: © 2016 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.