Towards a model of information seek-ing by integrating visual, semantic and memory maps
Anne Guérin-Dugué
- Fonction : Auteur
- PersonId : 5486
- IdHAL : anne-guerin-dugue
- ORCID : 0000-0002-4615-9215
- IdRef : 079208797
Thierry Baccino
- Fonction : Auteur
- PersonId : 859366
Résumé
This paper presents a threefold model of information seeking. A visual, a semantic and a memory map are dynamically computed in order to predict the location of the next fixation. This model is applied to a task in which the goal is to find among 40 words the one which best corresponds to a definition. Words have visual features and they are semantically organized. The model predicts scanpaths which are compared to human scanpaths on 3 high-level variables (number of fixations, average angle between saccades, rate of progression saccades). The best fit to human data is obtained when the memory map is given a strong weight and the semantic component a low weight.
Format du dépôt | Notice |
---|---|
Type de dépôt | Chapitre d'ouvrage |
Titre |
en
Towards a model of information seek-ing by integrating visual, semantic and memory maps
|
Résumé |
en
This paper presents a threefold model of information seeking. A visual, a semantic and a memory map are dynamically computed in order to predict the location of the next fixation. This model is applied to a task in which the goal is to find among 40 words the one which best corresponds to a definition. Words have visual features and they are semantically organized. The model predicts scanpaths which are compared to human scanpaths on 3 high-level variables (number of fixations, average angle between saccades, rate of progression saccades). The best fit to human data is obtained when the memory map is given a strong weight and the semantic component a low weight.
|
Auteur(s) |
Myriam Chanceaux
1
, Anne Guérin-Dugué
2
, Benoît Lemaire
3
, Thierry Baccino
4
1
AMA -
Analyse de données, Modélisation et Apprentissage automatique [Grenoble]
( 405357 )
- Laboratoire LIG - Bâtiment IMAG - 700 avenue Centrale, CS 40700 - 38058 Grenoble cedex 9
- France
2
GIPSA-GPIG -
GIPSA - Géométrie, Perception, Images, Geste
( 388966 )
- GIPSA-lab, 11 rue des Mathématiques, Grenoble Campus BP46, F-38402 SAINT MARTIN D'HERES CEDEX
- France
3
LPNC -
Laboratoire de Psychologie et NeuroCognition
( 596 )
- LPNC - Laboratoire de Psychologie et NeuroCognition
CNRS UMR 5105 - UGA
BSHM - 1251 Av Centrale
CS40700
38058 Grenoble Cedex 9
- France
4
LUTIN -
Laboratoire des Usages en Technologies d'Information Numériques
( 542056 )
- Cité des Sciences et de l'Industrie (Niveau -2), 30 avenue Corentin Cariou, 75019 Paris
- France
|
Vulgarisation |
Non
|
Langue du document |
Anglais
|
Audience |
Internationale
|
Date de publication |
2008
|
Page/Identifiant |
65-78
|
Titre de la collection |
Lecture Notes in Computer Science
|
Volume |
5329
|
Lieu de publication |
Berlin, Heidelberg
|
Titre de l'ouvrage |
Cognitive Vision. ICVW 2008
|
ISBN |
978-3-540-92780-8
|
URL éditeur |
https://link.springer.com/chapter/10.1007/978-3-540-92781-5_6
|
Domaine(s) |
|
Éditeur commercial |
|
Éditeur scientifique |
|
Mots-clés |
en
computational model, information seeking, visual saliency, semantic knowledge, memory
|
DOI | 10.1007/978-3-540-92781-5_6 |
Loading...