Přístupnostní navigace
E-application
Search Search Close
Detail publikačního výsledku
BEDNAŘÍK, R.; EIVAZI, S.; HRADIŠ, M.
Original Title
Gaze and Conversational Engagement in Multiparty Video Conversation: An annotation scheme and classification
English Title
Type
Paper in proceedings outside WoS and Scopus
Original Abstract
When using a multiparty video mediated system, interacting partic-ipants assume a range of various roles and exhibit behaviors accord-ing to how engaged in the communication they are. In this paper wefocus on estimation of conversational engagement fromgaze signal.In particular, we present an annotation scheme for conversationalengagement, a statistical analysis of gaze data across varying levelsof engagement, and we classify vectors of computed eye trackingmeasures. The results show that in 74% of cases the level of en-gagement can be correctly classified.
English abstract
Keywords
gaze tracking
Key words in English
Authors
RIV year
2013
Released
22.10.2012
Publisher
Association for Computing Machinery
Location
Santa Monica
ISBN
978-1-4503-1516-6
Book
4th Workshop on Eye Gaze in Intelligent Human Machine Interaction
Pages from
1
Pages to
5
Pages count
Full text in the Digital Library
http://hdl.handle.net/
BibTex
@inproceedings{BUT97049, author="Roman {Bednařík} and Shahram {Eivazi} and Michal {Hradiš}", title="Gaze and Conversational Engagement in Multiparty Video Conversation: An annotation scheme and classification", booktitle="4th Workshop on Eye Gaze in Intelligent Human Machine Interaction", year="2012", pages="1--5", publisher="Association for Computing Machinery", address="Santa Monica", doi="10.1145/2401836.2401846", isbn="978-1-4503-1516-6" }