CaltechAUTHORS
  A Caltech Library Service

The Secrets of Salient Object Segmentation

Li, Yin and Hou, Xiaodi and Koch, Christof and Rehg, James M. and Yuille, Alan L. (2014) The Secrets of Salient Object Segmentation. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE , Piscataway, NJ, pp. 280-287. ISBN 978-1-4799-5117-8 http://resolver.caltech.edu/CaltechAUTHORS:20151023-153719789

Full text is not posted in this repository. Consult Related URLs below.

Use this Persistent URL to link to this item: http://resolver.caltech.edu/CaltechAUTHORS:20151023-153719789

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 benchmarks, 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.


Item Type:Book Section
Related URLs:
URLURL TypeDescription
http://dx.doi.org/10.1109/CVPR.2014.43 DOIArticle
http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6909437PublisherArticle
Additional Information:© 2014 IEEE. The research was supported by the ONR via an award made through Johns Hopkins University, by the G. Harold and Leila Y. Mathers Charitable Foundation, by ONR N00014-12-1-0883 and the Center for Minds, Brains and Machines (CBMM), funded by NSF STC award CCF-1231216. This research is also supported by NSF Awards 0916687 and 1029679, ARO MURI award 58144-NS-MUR, and by the Intel Science and Technology Center in Pervasive Computing.
Group:Koch Laboratory, KLAB
Funders:
Funding AgencyGrant Number
Johns Hopkins UniversityUNSPECIFIED
Harold and Leila Y. Mathers Charitable FoundationUNSPECIFIED
Office of Naval Research (ONR)N00014-12-1-0883
NSFCCF-1231216
NSF0916687
NSF1029679
Army Research Office (ARO)58144-NS-MUR
Intel Science and Technology Center in Pervasive ComputingUNSPECIFIED
Record Number:CaltechAUTHORS:20151023-153719789
Persistent URL:http://resolver.caltech.edu/CaltechAUTHORS:20151023-153719789
Official Citation:Yin Li; Xiaodi Hou; Koch, C.; Rehg, J.M.; Yuille, A.L., "The Secrets of Salient Object Segmentation," in Computer Vision and Pattern Recognition (CVPR), 2014 IEEE Conference on , vol., no., pp.280-287, 23-28 June 2014 doi: 10.1109/CVPR.2014.43
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:61513
Collection:CaltechAUTHORS
Deposited By: Tony Diaz
Deposited On:26 Oct 2015 20:44
Last Modified:26 Oct 2015 20:44

Repository Staff Only: item control page