Please use this identifier to cite or link to this item: https://open.uns.ac.rs/handle/123456789/13416
Title: Data-driven approach to dynamic visual attention modelling
Authors: Ćulibrk, Dubravko 
Sladojević, Srđan 
Riche N.
Mancas M.
Crnojević V.
Issue Date: 12-Jun-2012
Journal: Proceedings of SPIE - The International Society for Optical Engineering
Abstract: Visual attention deployment mechanisms allow the Human Visual System to cope with an overwhelming amount of visual data by dedicating most of the processing power to objects of interest. The ability to automatically detect areas of the visual scene that will be attended to by humans is of interest for a large number of applications, from video coding, video quality assessment to scene understanding. Due to this fact, visual saliency (bottom-up attention) models have generated significant scientific interest in recent years. Most recent work in this area deals with dynamic models of attention that deal with moving stimuli (videos) instead of traditionally used still images. Visual saliency models are usually evaluated against ground-truth eye-tracking data collected from human subjects. However, there are precious few recently published approaches that try to learn saliency from eye-tracking data and, to the best of our knowledge, no approaches that try to do so when dynamic saliency is concerned. The paper attempts to fill this gap and describes an approach to data-driven dynamic saliency model learning. A framework is proposed that enables the use of eye-tracking data to train an arbitrary machine learning algorithm, using arbitrary features derived from the scene. We evaluate the methodology using features from a state-of-the art dynamic saliency model and show how simple machine learning algorithms can be trained to distinguish between visually salient and non-salient parts of the scene. © 2012 SPIE.
URI: https://open.uns.ac.rs/handle/123456789/13416
ISBN: 9780819491282
ISSN: 0277786X
DOI: 10.1117/12.923559
Appears in Collections:FTN Publikacije/Publications

Show full item record

SCOPUSTM   
Citations

1
checked on May 10, 2024

Page view(s)

50
Last Week
19
Last month
0
checked on May 10, 2024

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.