Document Detail


State-of-the-art in Visual Attention Modeling.
MedLine Citation:
PMID:  22487985     Owner:  NLM     Status:  Publisher    
Abstract/OtherAbstract:
Modeling visual attention -- particularly stimulus-driven, saliency-based attention -- has been a very active research area over the past 25 years. Many different models of attention are now available, which aside from lending theoretical contributions to other fields, have demonstrated successful applications in computer vision, mobile robotics, and cognitive systems. Here we review, from a computational perspective, the basic concepts of attention implemented in these models. We present a taxonomy of nearly 65 models, which provides a critical comparison of approaches, their capabilities, and shortcomings. In particular, thirteen criteria derived from behavioral and computational studies are formulated for qualitative comparison of attention models. Furthermore, we address several challenging issues with models, including biological plausibility of the computations, correlation with eye movement datasets, bottom-up and top-down dissociation, and constructing meaningful performance measures. Finally, we highlight current research trends in attention modeling and provide insights for future.
Authors:
Ali Borji; Laurent Itti
Related Documents :
21995015 - Quantitative body dw-mri biomarkers uncertainty estimation using unscented wild-bootstrap.
22428425 - When violations of perfect duties do not cause strong trait attributions.
22420565 - A new technique for testing distribution of knowledge and to estimate sampling sufficie...
22445575 - Comparing evaluation activities across multiple theories of practice.
24163705 - Exploring structure-activity data using the landscape paradigm.
3839585 - Statistical software packages for physical therapists. statpak for the ibm pc.
Publication Detail:
Type:  JOURNAL ARTICLE     Date:  2012-4-5
Journal Detail:
Title:  IEEE transactions on pattern analysis and machine intelligence     Volume:  -     ISSN:  1939-3539     ISO Abbreviation:  -     Publication Date:  2012 Apr 
Date Detail:
Created Date:  2012-4-10     Completed Date:  -     Revised Date:  -    
Medline Journal Info:
Nlm Unique ID:  9885960     Medline TA:  IEEE Trans Pattern Anal Mach Intell     Country:  -    
Other Details:
Languages:  ENG     Pagination:  -     Citation Subset:  -    
Affiliation:
University of Southern California (USC), Los Angeles.
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine


Previous Document:  Robust Recovery of Subspace Structures by Low-Rank Representation.
Next Document:  Effects of heat acclimation on endurance capacity and prolactin response to exercise in the heat.