University of Oulu

P. Tzirakis, M. A. Nicolaou, B. Schuller and S. Zafeiriou, "Time-series Clustering with Jointly Learning Deep Representations, Clusters and Temporal Boundaries," 2019 14th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2019), Lille, France, 2019, pp. 1-5. doi: 10.1109/FG.2019.8756618

Time-series clustering with jointly learning deep representations, clusters and temporal boundaries

Saved in:
Author: Tzirakis, Panagiotis1; Nicolaou, Mihalis A.2; Schuller, Björn1,3;
Organizations: 1Department of Computing, Imperial College London, UK
2Computation-based Science and Technology Research Centre, The Cyprus Institute, Cyprus
3ZD.B Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Germany
4Center for Machine Vision and Signal Analysis, University of Oulu, Oulu, Finland
Format: article
Version: accepted version
Access: open
Online Access: PDF Full Text (PDF, 0.2 MB)
Persistent link:
Language: English
Published: Institute of Electrical and Electronics Engineers, 2019
Publish Date: 2020-03-24


Clustering and segmentation of temporal data is an important task across several fields, with prominent applications in computer vision and machine learning such as face and gesture segmentation. Several related methods have been proposed in literature, focusing on learning temporal boundaries and clusters, with recent works focusing on learning deep representations for clustering. However, none of the proposed methods is suitable for jointly learning segments, clusters, as well as representations. In this paper, we propose the first methodology that simultaneously discovers suitable deep representations, as well as clusters and temporal boundaries, with the clustering process providing supervisory cues for updating temporal boundaries and training the proposed deep learning architecture. We demonstrate the power of the proposed approach on a human motion segmentation task using the CMU-MMAC database. Our method provides the best results with respect to normalized mutual information compared to other clustering algorithms.

see all

ISBN: 978-1-7281-0089-0
ISBN Print: 978-1-7281-0090-6
Pages: 1 - 5
Article number: 8756618
DOI: 10.1109/FG.2019.8756618
Host publication: 14th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2019, 14-18 May 2019, Lille, France
Conference: IEEE International Conference on Automatic Face and Gesture Recognition
Type of Publication: A4 Article in conference proceedings
Field of Science: 113 Computer and information sciences
Funding: The support of the EPSRC Center for Doctoral Training in High Performance Embedded and Distributed Systems (HiPEDS, Grant Reference EP/L016796/1) is gratefully acknowledged. Dr. Zafeiriou acknowledges support from a Google Faculty award, as well as from the EPSRC fellowship Deform (EP/S010203/1).
Copyright information: © 2019 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.