Temporal archetypal analysis for action segmentation

Fotiadou, Eftychia, Panagakis, Yannis ORCID: https://orcid.org/0000-0003-0153-5210 and Pantic, Maja (2017) Temporal archetypal analysis for action segmentation. 2017 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017). In: 2017 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017), 30 May - 03 June 2017, Washington, DC, USA. ISBN 9781509040230. [Conference or Workshop Item] (doi:10.1109/FG.2017.66)

Preview

PDF - Final accepted version (with author's formatting) Download (625kB) | Preview

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.

Actions (login required)

View Item

Statistics

DownloadsShow export options

Export as CSVXMLJSON

Activity Overview

6 month trend

246Downloads

6 month trend

253Hits

Additional statistics are available via IRStats2.