Interest estimation based on dynamic bayesian networks for visual attentive presentation agents

Boris Brandherm, Helmut Prendinger, Mitsuru Ishizuka

Research output: Chapter in Book/Report/Conference proceedingConference contribution

11 Citations (Scopus)

Abstract

In this paper, we describe an interface consisting of a virtual showroom where a team of two highly realistic 3D agents presents product items in an entertaining and attractive way. The presentation flow adapts to users' attentiveness, or lack thereof, and may thus provide a more personalized and userattractive experience of the presentation. In order to infer users' attention and visual interest regarding interface objects, our system analyzes eye movements in real-time. Interest detection algorithms used in previous research determine an object of interest based on the time that eye gaze dwells on that object. However, this kind of algorithm is not well suited for dynamic presentations where the goal is to assess the user's focus of attention regarding a dynamically changing presentation. Here, the current context of the object of attention has to be considered, i.e., whether the visual object is part of (or contributes to) the current presentation content or not. Therefore, we propose a new approach that estimates the interest (or non-interest) of a user by means of dynamic Bayesian networks. Each of a predefined set of visual objects has a dynamic Bayesian network assigned to it, which calculates the current interest of the user in this object. The estimation takes into account (1) each new gaze point, (2) the current context of the object, and (3) preceding estimations of the object itself. Based on these estimations the presentation agents can provide timely and appropriate response.

Original languageEnglish
Title of host publicationProceedings of the 9th International Conference on Multimodal Interfaces, ICMI'07
Pages346-349
Number of pages4
DOIs
Publication statusPublished - 2007
Externally publishedYes
Event9th International Conference on Multimodal Interfaces, ICMI 2007 - Nagoya
Duration: 2007 Nov 122007 Nov 15

Other

Other9th International Conference on Multimodal Interfaces, ICMI 2007
CityNagoya
Period07/11/1207/11/15

Fingerprint

Bayesian networks
Eye movements

Keywords

  • Human factors

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition
  • Human-Computer Interaction

Cite this

Brandherm, B., Prendinger, H., & Ishizuka, M. (2007). Interest estimation based on dynamic bayesian networks for visual attentive presentation agents. In Proceedings of the 9th International Conference on Multimodal Interfaces, ICMI'07 (pp. 346-349) https://doi.org/10.1145/1322192.1322253

Interest estimation based on dynamic bayesian networks for visual attentive presentation agents. / Brandherm, Boris; Prendinger, Helmut; Ishizuka, Mitsuru.

Proceedings of the 9th International Conference on Multimodal Interfaces, ICMI'07. 2007. p. 346-349.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Brandherm, B, Prendinger, H & Ishizuka, M 2007, Interest estimation based on dynamic bayesian networks for visual attentive presentation agents. in Proceedings of the 9th International Conference on Multimodal Interfaces, ICMI'07. pp. 346-349, 9th International Conference on Multimodal Interfaces, ICMI 2007, Nagoya, 07/11/12. https://doi.org/10.1145/1322192.1322253
Brandherm B, Prendinger H, Ishizuka M. Interest estimation based on dynamic bayesian networks for visual attentive presentation agents. In Proceedings of the 9th International Conference on Multimodal Interfaces, ICMI'07. 2007. p. 346-349 https://doi.org/10.1145/1322192.1322253
Brandherm, Boris ; Prendinger, Helmut ; Ishizuka, Mitsuru. / Interest estimation based on dynamic bayesian networks for visual attentive presentation agents. Proceedings of the 9th International Conference on Multimodal Interfaces, ICMI'07. 2007. pp. 346-349
@inproceedings{1477be1fca704d4eb3543b7d5f705fe5,
title = "Interest estimation based on dynamic bayesian networks for visual attentive presentation agents",
abstract = "In this paper, we describe an interface consisting of a virtual showroom where a team of two highly realistic 3D agents presents product items in an entertaining and attractive way. The presentation flow adapts to users' attentiveness, or lack thereof, and may thus provide a more personalized and userattractive experience of the presentation. In order to infer users' attention and visual interest regarding interface objects, our system analyzes eye movements in real-time. Interest detection algorithms used in previous research determine an object of interest based on the time that eye gaze dwells on that object. However, this kind of algorithm is not well suited for dynamic presentations where the goal is to assess the user's focus of attention regarding a dynamically changing presentation. Here, the current context of the object of attention has to be considered, i.e., whether the visual object is part of (or contributes to) the current presentation content or not. Therefore, we propose a new approach that estimates the interest (or non-interest) of a user by means of dynamic Bayesian networks. Each of a predefined set of visual objects has a dynamic Bayesian network assigned to it, which calculates the current interest of the user in this object. The estimation takes into account (1) each new gaze point, (2) the current context of the object, and (3) preceding estimations of the object itself. Based on these estimations the presentation agents can provide timely and appropriate response.",
keywords = "Human factors",
author = "Boris Brandherm and Helmut Prendinger and Mitsuru Ishizuka",
year = "2007",
doi = "10.1145/1322192.1322253",
language = "English",
isbn = "9781595938176",
pages = "346--349",
booktitle = "Proceedings of the 9th International Conference on Multimodal Interfaces, ICMI'07",

}

TY - GEN

T1 - Interest estimation based on dynamic bayesian networks for visual attentive presentation agents

AU - Brandherm, Boris

AU - Prendinger, Helmut

AU - Ishizuka, Mitsuru

PY - 2007

Y1 - 2007

N2 - In this paper, we describe an interface consisting of a virtual showroom where a team of two highly realistic 3D agents presents product items in an entertaining and attractive way. The presentation flow adapts to users' attentiveness, or lack thereof, and may thus provide a more personalized and userattractive experience of the presentation. In order to infer users' attention and visual interest regarding interface objects, our system analyzes eye movements in real-time. Interest detection algorithms used in previous research determine an object of interest based on the time that eye gaze dwells on that object. However, this kind of algorithm is not well suited for dynamic presentations where the goal is to assess the user's focus of attention regarding a dynamically changing presentation. Here, the current context of the object of attention has to be considered, i.e., whether the visual object is part of (or contributes to) the current presentation content or not. Therefore, we propose a new approach that estimates the interest (or non-interest) of a user by means of dynamic Bayesian networks. Each of a predefined set of visual objects has a dynamic Bayesian network assigned to it, which calculates the current interest of the user in this object. The estimation takes into account (1) each new gaze point, (2) the current context of the object, and (3) preceding estimations of the object itself. Based on these estimations the presentation agents can provide timely and appropriate response.

AB - In this paper, we describe an interface consisting of a virtual showroom where a team of two highly realistic 3D agents presents product items in an entertaining and attractive way. The presentation flow adapts to users' attentiveness, or lack thereof, and may thus provide a more personalized and userattractive experience of the presentation. In order to infer users' attention and visual interest regarding interface objects, our system analyzes eye movements in real-time. Interest detection algorithms used in previous research determine an object of interest based on the time that eye gaze dwells on that object. However, this kind of algorithm is not well suited for dynamic presentations where the goal is to assess the user's focus of attention regarding a dynamically changing presentation. Here, the current context of the object of attention has to be considered, i.e., whether the visual object is part of (or contributes to) the current presentation content or not. Therefore, we propose a new approach that estimates the interest (or non-interest) of a user by means of dynamic Bayesian networks. Each of a predefined set of visual objects has a dynamic Bayesian network assigned to it, which calculates the current interest of the user in this object. The estimation takes into account (1) each new gaze point, (2) the current context of the object, and (3) preceding estimations of the object itself. Based on these estimations the presentation agents can provide timely and appropriate response.

KW - Human factors

UR - http://www.scopus.com/inward/record.url?scp=57649171251&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=57649171251&partnerID=8YFLogxK

U2 - 10.1145/1322192.1322253

DO - 10.1145/1322192.1322253

M3 - Conference contribution

AN - SCOPUS:57649171251

SN - 9781595938176

SP - 346

EP - 349

BT - Proceedings of the 9th International Conference on Multimodal Interfaces, ICMI'07

ER -