Temporal archetypal analysis for action segmentation

Conference paper


Fotiadou, E., Panagakis, Y. and Pantic, M. 2017. Temporal archetypal analysis for action segmentation. 2017 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017). Washington, DC, USA 30 May - 03 Jun 2017 Institute of Electrical and Electronics Engineers (IEEE). pp. 490-496 https://doi.org/10.1109/FG.2017.66
TypeConference paper
TitleTemporal archetypal analysis for action segmentation
AuthorsFotiadou, E., Panagakis, Y. and Pantic, M.
Abstract

Unsupervised learning of invariant representations that efficiently describe high-dimensional time series has several applications in dynamic visual data analysis. Clearly, the problem becomes more challenging when dealing with multiple time series arising from different modalities. A prominent example of this multimodal setting is the human motion which can be represented by multimodal time series of pixel intensities, depth maps, and motion capture data. Here, we study, for the first time, the problem of unsupervised learning of temporally and modality invariant informative representations, referred to as archetypes, from multiple time series originating from different modalities. To this end a novel method, coined as temporal archetypal analysis, is proposed. The performance of the proposed method is assessed by conducting experiments in unsupervised action segmentation. Experimental results on three different real world datasets using single modal and multimodal visual representations indicate the robustness and effectiveness of the proposed methods, outperforming compared state-of-the-art methods by a large, in most of the cases, margin.

LanguageEnglish
Conference2017 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017)
Page range490-496
ISBN
Hardcover9781509040230
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Publication dates
Print01 May 2017
Online29 Jun 2017
Publication process dates
Deposited06 Mar 2018
Accepted17 Feb 2017
Output statusPublished
Accepted author manuscript
Copyright Statement

© 2017 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

Digital Object Identifier (DOI)https://doi.org/10.1109/FG.2017.66
Book title2017 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017)
Permalink -

https://repository.mdx.ac.uk/item/8786y

Download files


Accepted author manuscript
  • 9
    total views
  • 1
    total downloads
  • 1
    views this month
  • 0
    downloads this month

Export as