Title:
The Secrets of Salient Object Segmentation

dc.contributor.author Li, Yin
dc.contributor.author Hou, Xiaodi
dc.contributor.author Koch, Christof
dc.contributor.author Rehg, James M.
dc.contributor.author Yuille, Alan L.
dc.contributor.corporatename Georgia Institute of Technology. Institute for Robotics and Intelligent Machines en_US
dc.contributor.corporatename Georgia Institute of Technology. College of Computing en_US
dc.contributor.corporatename Georgia Institute of Technology. School of Interactive Computing en_US
dc.contributor.corporatename California Institute of Technology en_US
dc.contributor.corporatename Allen Institute for Brain Science en_US
dc.contributor.corporatename University of California, Los Angeles en_US
dc.date.accessioned 2015-07-13T17:38:53Z
dc.date.available 2015-07-13T17:38:53Z
dc.date.issued 2014-06
dc.description © 2014 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works. en_US
dc.description This CVPR2014 paper is the Open Access version, provided by the Computer Vision Foundation. The authoritative version of this paper is available in IEEE Xplore.
dc.description DOI: 10.1109/CVPR.2014.43
dc.description.abstract In this paper we provide an extensive evaluation of fixation prediction and salient object segmentation algorithms as well as statistics of major datasets. Our analysis identifies serious design flaws of existing salient object bench- marks, called the dataset design bias, by over emphasising the stereotypical concepts of saliency. The dataset design bias does not only create the discomforting disconnection between fixations and salient object segmentation, but also misleads the algorithm designing. Based on our analysis, we propose a new high quality dataset that offers both fixation and salient object segmentation ground-truth. With fixations and salient object being presented simultaneously, we are able to bridge the gap between fixations and salient objects, and propose a novel method for salient object segmentation. Finally, we report significant benchmark progress on 3 existing datasets of segmenting salient objects. en_US
dc.embargo.terms null en_US
dc.identifier.citation Li, Y.; Hou, X.; Koch, C.; Rehg, J.M.; & Yuille, A.L. (2014). "The Secrets of Salient Object Segmentation". Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2014), 23-28 June 2014, pp.280-287. en_US
dc.identifier.doi 10.1109/CVPR.2014.43
dc.identifier.uri http://hdl.handle.net/1853/53677
dc.language.iso en_US en_US
dc.publisher Georgia Institute of Technology en_US
dc.publisher.original Institute of Electrical and Electronics Engineers
dc.subject Dataset analysis en_US
dc.subject Eye fixation en_US
dc.subject Saliency en_US
dc.subject Salient object segmentation en_US
dc.title The Secrets of Salient Object Segmentation en_US
dc.type Text
dc.type.genre Proceedings
dspace.entity.type Publication
local.contributor.author Rehg, James M.
local.contributor.corporatename Institute for Robotics and Intelligent Machines (IRIM)
relation.isAuthorOfPublication af5b46ec-ffe2-4ce4-8722-1373c9b74a37
relation.isOrgUnitOfPublication 66259949-abfd-45c2-9dcc-5a6f2c013bcf
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Li_The_Secrets_of_2014_CVPR_paper.pdf
Size:
2.2 MB
Format:
Adobe Portable Document Format
Description:
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
3.13 KB
Format:
Item-specific license agreed upon to submission
Description: