Efficient Learning to Label Images
dc.contributor.author | Jia, Ke | |
dc.contributor.author | Cheng, Li | |
dc.contributor.author | Liu, Nianjun | |
dc.contributor.author | Wang, Lei | |
dc.coverage.spatial | San Francisco USA | |
dc.date.accessioned | 2015-12-07T22:23:50Z | |
dc.date.created | June 13-18 2010 | |
dc.date.issued | 2010 | |
dc.date.updated | 2016-02-24T11:29:55Z | |
dc.description.abstract | Conditional random field methods (CRFs) have gained popularity for image labeling tasks in recent years. In this paper, we describe an alternative discriminative approach, by extending the large margin principle to incorporate spatial correlations among neighboring pixels. In particular, by explicitly enforcing the submodular condition, graph-cuts is conveniently integrated as the inference engine to attain the optimal label assignment efficiently. Our approach allows learning a model with thousands of parameters, and is shown to be capable of readily incorporating higher-order scene context. Empirical studies on a variety of image datasets suggest that our approach performs competitively compared to the state-of-the-art scene labeling methods. | |
dc.identifier.isbn | 9781424469857 | |
dc.identifier.uri | http://hdl.handle.net/1885/20889 | |
dc.publisher | Institute of Electrical and Electronics Engineers (IEEE Inc) | |
dc.relation.ispartofseries | Computer Vision and Pattern Recognition Conference (CVPR 2010) | |
dc.source | Proceedings of The 23rd IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2010) | |
dc.subject | Keywords: Conditional random field; Discriminative approach; Efficient learning; Empirical studies; Graph-cuts; Higher order; Image datasets; Image labeling; Label images; Labeling methods; Large margin principle; Spatial correlations; Submodular; Pattern recogniti | |
dc.title | Efficient Learning to Label Images | |
dc.type | Conference paper | |
local.bibliographicCitation.startpage | 4 | |
local.contributor.affiliation | Jia, Ke, College of Engineering and Computer Science, ANU | |
local.contributor.affiliation | Cheng, Li, Toyota Technological Institute at Chicago (TTI) | |
local.contributor.affiliation | Liu, Nianjun, College of Engineering and Computer Science, ANU | |
local.contributor.affiliation | Wang, Lei, College of Engineering and Computer Science, ANU | |
local.contributor.authoremail | repository.admin@anu.edu.au | |
local.contributor.authoruid | Jia, Ke, u4326094 | |
local.contributor.authoruid | Liu, Nianjun, u1814805 | |
local.contributor.authoruid | Wang, Lei, u4259382 | |
local.description.embargo | 2037-12-31 | |
local.description.notes | Imported from ARIES | |
local.description.refereed | Yes | |
local.identifier.absfor | 080104 - Computer Vision | |
local.identifier.absseo | 970109 - Expanding Knowledge in Engineering | |
local.identifier.ariespublication | u4963866xPUB14 | |
local.identifier.doi | 10.1109/ICPR.2010.236 | |
local.identifier.scopusID | 2-s2.0-78149491985 | |
local.identifier.uidSubmittedBy | u4963866 | |
local.type.status | Published Version |
Downloads
Original bundle
1 - 1 of 1
No Thumbnail Available
- Name:
- 01_Jia_Efficient_Learning_to_Label_2010.pdf
- Size:
- 362.72 KB
- Format:
- Adobe Portable Document Format