Header

UZH-Logo

Maintenance Infos

Non parametric, self organizing, scalable modeling of spatiotemporal inputs: the sign language paradigm


Caridakis, G; Karpouzis, K; Drosopoulos, A; Kollias, S (2012). Non parametric, self organizing, scalable modeling of spatiotemporal inputs: the sign language paradigm. Neural Networks, 36:157-166.

Abstract

Modeling and recognizing spatiotemporal, as opposed to static input, is a challenging task since it incorporates input dynamics as part of the problem. The vast majority of existing methods tackle the problem as an extension of the static counterpart, using dynamics, such as input derivatives, at feature level and adopting artificial intelligence and machine learning techniques originally designed for solving problems that do not specifically address the temporal aspect. The proposed approach deals with temporal and spatial aspects of the spatiotemporal domain in a discriminative as well as coupling manner. Self Organizing Maps (SOM) model the spatial aspect of the problem and Markov models its temporal counterpart. Incorporation of adjacency, both in training and classification, enhances the overall architecture with robustness and adaptability. The proposed scheme is validated both theoretically, through an error propagation study, and experimentally, on the recognition of individual signs, performed by different, native Greek Sign Language users. Results illustrate the architecture's superiority when compared to Hidden Markov Model techniques and variations both in terms of classification performance and computational cost.

Abstract

Modeling and recognizing spatiotemporal, as opposed to static input, is a challenging task since it incorporates input dynamics as part of the problem. The vast majority of existing methods tackle the problem as an extension of the static counterpart, using dynamics, such as input derivatives, at feature level and adopting artificial intelligence and machine learning techniques originally designed for solving problems that do not specifically address the temporal aspect. The proposed approach deals with temporal and spatial aspects of the spatiotemporal domain in a discriminative as well as coupling manner. Self Organizing Maps (SOM) model the spatial aspect of the problem and Markov models its temporal counterpart. Incorporation of adjacency, both in training and classification, enhances the overall architecture with robustness and adaptability. The proposed scheme is validated both theoretically, through an error propagation study, and experimentally, on the recognition of individual signs, performed by different, native Greek Sign Language users. Results illustrate the architecture's superiority when compared to Hidden Markov Model techniques and variations both in terms of classification performance and computational cost.

Statistics

Citations

2 citations in Web of Science®
2 citations in Scopus®
Google Scholar™

Altmetrics

Additional indexing

Item Type:Journal Article, refereed, original work
Communities & Collections:04 Faculty of Medicine > University Hospital Zurich > Clinic for Neuroradiology
Dewey Decimal Classification:610 Medicine & health
Language:English
Date:2012
Deposited On:06 Feb 2014 12:54
Last Modified:05 Apr 2016 17:30
Publisher:Elsevier
ISSN:0893-6080
Publisher DOI:https://doi.org/10.1016/j.neunet.2012.10.001
PubMed ID:23137923

Download

Full text not available from this repository.
View at publisher