File Download
Supplementary

Conference Paper: Hidden Markov modeling of eye movements with image information leads to better discovery of regions of interest

TitleHidden Markov modeling of eye movements with image information leads to better discovery of regions of interest
Authors
KeywordsEye-tracking
Face recognition
Hidden Markov Model
Machine learning
Issue Date2016
PublisherCognitive Science Society. The Conference Proceedings' website is located at http://mindmodeling.org/cogsci2016/index.html
Citation
The 38th Annual Meeting of the Cognitive Science Society (CogSci 2016), Philadelphia, PA., 10-13 August 2016. In Conference Proceedings, 2016, p. 1032-1037 How to Cite?
AbstractHidden Markov models (HMM) can describe the spatial and temporal characteristics of eye-tracking recordings in cognitive tasks. Here, we introduce a new HMM approach. We developed HMMs based on fixation locations and we also used image information as an input feature. We demonstrate the benefits of the newly proposed model in a face recognition study wherein an HMM was developed for every subject. Discovery of regions of interest on facial stimuli is improved compared to earlier approaches. Moreover, clustering of the newly developed HMMs lead to very distinct groups. The newly developed approach also allows reconstructing image information at fixation.
DescriptionConference Theme: Integrating Psychological, Philosophical, Linguistic, Computational and Neural Perspectives
Poster Session 2: no. 56
Persistent Identifierhttp://hdl.handle.net/10722/232765

 

DC FieldValueLanguage
dc.contributor.authorBrueggemann, S-
dc.contributor.authorChan, AB-
dc.contributor.authorHsiao, JHW-
dc.date.accessioned2016-09-20T05:32:10Z-
dc.date.available2016-09-20T05:32:10Z-
dc.date.issued2016-
dc.identifier.citationThe 38th Annual Meeting of the Cognitive Science Society (CogSci 2016), Philadelphia, PA., 10-13 August 2016. In Conference Proceedings, 2016, p. 1032-1037-
dc.identifier.urihttp://hdl.handle.net/10722/232765-
dc.descriptionConference Theme: Integrating Psychological, Philosophical, Linguistic, Computational and Neural Perspectives-
dc.descriptionPoster Session 2: no. 56-
dc.description.abstractHidden Markov models (HMM) can describe the spatial and temporal characteristics of eye-tracking recordings in cognitive tasks. Here, we introduce a new HMM approach. We developed HMMs based on fixation locations and we also used image information as an input feature. We demonstrate the benefits of the newly proposed model in a face recognition study wherein an HMM was developed for every subject. Discovery of regions of interest on facial stimuli is improved compared to earlier approaches. Moreover, clustering of the newly developed HMMs lead to very distinct groups. The newly developed approach also allows reconstructing image information at fixation.-
dc.languageeng-
dc.publisherCognitive Science Society. The Conference Proceedings' website is located at http://mindmodeling.org/cogsci2016/index.html-
dc.relation.ispartofProceedings of the 38th Annual Conference of the Cognitive Science Society, CogSci 2016-
dc.rightsCreative Commons: Attribution 3.0 Hong Kong License-
dc.subjectEye-tracking-
dc.subjectFace recognition-
dc.subjectHidden Markov Model-
dc.subjectMachine learning-
dc.titleHidden Markov modeling of eye movements with image information leads to better discovery of regions of interest-
dc.typeConference_Paper-
dc.identifier.emailHsiao, JHW: jhsiao@hku.hk-
dc.identifier.authorityHsiao, JHW=rp00632-
dc.description.naturepostprint-
dc.identifier.hkuros263211-
dc.identifier.spage1032-
dc.identifier.epage1037-
dc.publisher.placeUnited States-
dc.customcontrol.immutablesml 161007-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats