Personalized Visual Saliency: Individuality Affects Image Perception
Open Access
- 31 January 2018
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 6, 16099-16109
- https://doi.org/10.1109/access.2018.2800294
Abstract
Due to the limited capability for information processing, humans only choose a small amount of input data received from visual field to better understand their environment. The selection of visual input implies the nonuniform distribution of visual attention, which is influenced by environmental visual stimuli and endogenous subject interest. Traditional saliency models do not differentiate individuals, exploring the common trend in attention deployment. The present study investigates individual nuance and association in both saccadic movements and attention distribution, and then discusses how individuality plays a role in predicting attention with low-level and deep features, respectively. It turns out that individual differences indeed exist and can be better discriminated by deep features. In conclusion, individuality not only contributes to improving the accuracy of attention prediction models but also gives us hint about some interesting viewing behavior that stands out from the crowd pattern.Funding Information
- National Natural Science Foundation of China (61771348, 61471273)
- Wuhan Morning Light Plan of Youth Science and Technology (2017050304010302)
This publication has 25 references indexed in Scilit:
- Saccadic model of eye movements for free-viewing conditionVision Research, 2015
- A comparison of scanpath comparison methodsBehavior Research Methods, 2014
- Curious eyes: Individual differences in personality predict eye movement behavior in scene-viewingCognition, 2012
- Scene and screen center bias early eye movements in scene viewingVision Research, 2010
- SUN: Top-down saliency using natural statisticsVisual Cognition, 2009
- Predicting visual fixations on video based on low-level visual featuresVision Research, 2007
- Components of bottom-up gaze allocation in natural imagesVision Research, 2005
- A model of saliency-based visual attention for rapid scene analysisIEEE Transactions on Pattern Analysis and Machine Intelligence, 1998
- Gabor filter-based edge detectionPattern Recognition, 1992
- The color-opponent and broad-band channels of the primate visual systemTrends in Neurosciences, 1990