Prediction of human looking behavior using interest-based image representations

機構典藏 > College of Sciences > Department of Applied Mathematics and Data Science > Journal Article > Item 987654321/125141

Please use this identifier to cite or link to this item: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/125141

Title:	Prediction of human looking behavior using interest-based image representations
Authors:	Guo, Jong-shenq
Date:	2023-10-12
Issue Date:	2024-03-05 12:05:20 (UTC+8)
Abstract:	Looking behavior allows human to understand and interact with an enormous amount of information, a capacity challenging to replicate in AI systems. One of the core elements of this work is an effort to predict scan-paths from a combination of image information and past looking behavior. The success of this scan-path predication relies heavily on whether this image information can provide a sufficiently rich representation for prediction. In this paper, we show that changing representations dramatically simplifies and improves predictions of looking behavior. We introduce a representation of looking behavior that centers around interest-regions in images, defined by natural and collective looking behavior. These regions (called interest-based regions) can be used to partition images for semantic labeling and to provide a basis for shared representation across observers. Without any additional label or image information, we achieve highly accurate sequence prediction using this interest-based image representation.
Relation:	Communications in Information and Systems 23,　p.245-262
DOI:	10.4310/CIS.2023.v23.n3.a2
Appears in Collections:	[Department of Applied Mathematics and Data Science] Journal Article

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	61	View/Open