Saliency Integration: An Arbitrator Model
Download (2.59 MB)
-
Altmetric Citations
Xu, Yingyue; Hong, Xiaopeng; Porikli, Fatih; Liu, Xin; Chen, Jie; Zhao, Guoying
Description
Saliency integration has aroused general concern on unifying saliency maps from multiple saliency models. Previous offline integration methods usually face two challenges: 1. if most of the candidate saliency models misjudge the saliency on an image, the integration result will lean heavily on those inferior candidate models; 2. an unawareness of the ground truth saliency labels brings difficulty in estimating the expertise of each candidate model. To address these problems, in this paper, we...[Show more]
dc.contributor.author | Xu, Yingyue | |
---|---|---|
dc.contributor.author | Hong, Xiaopeng | |
dc.contributor.author | Porikli, Fatih | |
dc.contributor.author | Liu, Xin | |
dc.contributor.author | Chen, Jie | |
dc.contributor.author | Zhao, Guoying | |
dc.date.accessioned | 2020-09-11T04:57:47Z | |
dc.identifier.issn | 1520-9210 | |
dc.identifier.uri | http://hdl.handle.net/1885/209986 | |
dc.description.abstract | Saliency integration has aroused general concern on unifying saliency maps from multiple saliency models. Previous offline integration methods usually face two challenges: 1. if most of the candidate saliency models misjudge the saliency on an image, the integration result will lean heavily on those inferior candidate models; 2. an unawareness of the ground truth saliency labels brings difficulty in estimating the expertise of each candidate model. To address these problems, in this paper, we propose an arbitrator model (AM) for saliency integration. Firstly, we incorporate the consensus of multiple saliency models and the external knowledge into a reference map to effectively rectify the misleading by candidate models. Secondly, our quest for ways of estimating the expertise of the saliency models without ground truth labels gives rise to two distinct online model-expertise estimation methods. Finally, we derive a Bayesian integration framework to reconcile the saliency models of varying expertise and the reference map. To extensively evaluate the proposed AM model, we test twenty-seven state-of-the-art saliency models, covering both traditional and deep learning ones, on various combinations over four datasets. The evaluation results show that the AM model improves the performance substantially compared to the existing state-of-the-art integration methods, regardless of the chosen candidate saliency models. | |
dc.format.mimetype | application/pdf | |
dc.language.iso | en_AU | |
dc.publisher | Institute of Electrical and Electronics Engineers (IEEE Inc) | |
dc.rights | © 2018 IEEE | |
dc.source | IEEE Transactions on Multimedia | |
dc.title | Saliency Integration: An Arbitrator Model | |
dc.type | Journal article | |
local.description.notes | Imported from ARIES | |
dc.date.issued | 2018 | |
local.identifier.absfor | 080104 - Computer Vision | |
local.identifier.ariespublication | a383154xPUB10436 | |
local.publisher.url | http://ieeexplore.ieee.org/xpl/RecentIssue.jsp/?punumber=6046 | |
local.type.status | Published Version | |
local.contributor.affiliation | Xu, Yingyue, University of Oulu | |
local.contributor.affiliation | Hong, Xiaopeng, University of Oulu | |
local.contributor.affiliation | Porikli, Fatih, College of Engineering and Computer Science, ANU | |
local.contributor.affiliation | Liu, Xin, University of Oulu | |
local.contributor.affiliation | Chen, Jie, University of Oulu | |
local.contributor.affiliation | Zhao, Guoying , University of Oulu | |
local.description.embargo | 2037-12-31 | |
local.bibliographicCitation.startpage | 1 | |
local.bibliographicCitation.lastpage | 16 | |
local.identifier.doi | 10.1109/TMM.2018.2856126 | |
local.identifier.absseo | 900201 - Administration and Business Support Services | |
local.identifier.absseo | 899999 - Information and Communication Services not elsewhere classified | |
dc.date.updated | 2020-06-23T00:52:18Z | |
local.identifier.scopusID | 2-s2.0-85049931257 | |
Collections | ANU Research Publications |
Download
File | Description | Size | Format | Image |
---|---|---|---|---|
01_Xu_Saliency_Integration%3A_An_2018.pdf | 2.59 MB | Adobe PDF |
Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.
Updated: 17 November 2022/ Responsible Officer: University Librarian/ Page Contact: Library Systems & Web Coordinator