Can Visual Scanpath Reveal Personal Image Memorability? Investigation of HMM Tools for Gaze Patterns Analysis

Waqas Ellahi (1, 2) , Toinon Vigier (1, 2) , Patrick Le Callet (2, 1, 3)

1 LS2N - équipe IPI - Image Perception Interaction
2 LS2N - Laboratoire des Sciences du Numérique de Nantes
3 EPUN - Ecole Polytechnique de l'Université de Nantes

Visual attention has been shown as a good proxy for QoE, revealing specific visual patterns considering content, system and contextual aspects of a multimedia applications. In this paper, we propose a novel approach based on hidden markov models to analyze visual scanpaths in an image memorability task. This new method ensures the consideration of both temporal and idiosyncrasic aspects of visual behavior. The study shows promising results for the use of indirect measures for the personalization of QoE assessment and prediction.

Mots clés: scanpath; eye movements; visual attention; hidden Markov model; memorability

Domaines: Multimédia [cs.MM]; Apprentissage [cs.LG]; Psychologie

Waqas Ellahi, Toinon Vigier, Patrick Le Callet. Can Visual Scanpath Reveal Personal Image Memorability? Investigation of HMM Tools for Gaze Patterns Analysis. 2020 Twelfth International Conference on Quality of Multimedia Experience (QoMEX 2020), May 2020, Athlone, Ireland. ⟨hal-02611803⟩