Glimpse: A gaze-based measure of temporal salience
Visualitza/
Impacte
Scholar |
Altres documents de l'autoria: Traver Roig, Vicente Javier; Zorío Ventura, Judith; Leiva, Luis A.
Metadades
Mostra el registre complet de l'elementcomunitat-uji-handle:10234/9
comunitat-uji-handle2:10234/43662
comunitat-uji-handle3:10234/43643
comunitat-uji-handle4:
INVESTIGACIONMetadades
Títol
Glimpse: A gaze-based measure of temporal salienceData de publicació
2021-04-29Editor
Multidisciplinary Digital Publishing InstituteISSN
1424-8220Cita bibliogràfica
Traver, V.J.; Zorío, J.; Leiva, L.A. GLIMPSE: A Gaze-Based Measure of Temporal Salience. Sensors 2021, 21, 3099. https://doi.org/10.3390/s21093099Tipus de document
info:eu-repo/semantics/articleVersió de l'editorial
https://www.mdpi.com/1424-8220/21/9/3099/htmVersió
info:eu-repo/semantics/publishedVersionParaules clau / Matèries
Resum
Temporal salience considers how visual attention varies over time. Although visual salience
has been widely studied from a spatial perspective, its temporal dimension has been mostly ignored,
despite arguably being ... [+]
Temporal salience considers how visual attention varies over time. Although visual salience
has been widely studied from a spatial perspective, its temporal dimension has been mostly ignored,
despite arguably being of utmost importance to understand the temporal evolution of attention
on dynamic contents. To address this gap, we proposed GLIMPSE, a novel measure to compute
temporal salience based on the observer-spatio-temporal consistency of raw gaze data. The measure
is conceptually simple, training free, and provides a semantically meaningful quantification of
visual attention over time. As an extension, we explored scoring algorithms to estimate temporal
salience from spatial salience maps predicted with existing computational models. However, these
approaches generally fall short when compared with our proposed gaze-based measure. GLIMPSE
could serve as the basis for several downstream tasks such as segmentation or summarization of
videos. GLIMPSE’s software and data are publicly available. [-]
Publicat a
Sensors, 21, 2021.Codi del projecte o subvenció
UJI-B2018-44 | RED2018-102511-T
Títol del projecte o subvenció
Generación automática de resumenes de datos visuales egocéntricos | Red española de aprendizaje automático y visión artificial para el análisis de personas y la percepción robótica
Drets d'accés
info:eu-repo/semantics/openAccess
Apareix a les col.leccions
- INIT_Articles [749]