DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kim, Sung-Woong | ko |
dc.contributor.author | Nowozin, Sebastian | ko |
dc.contributor.author | Kohli, Pushmeet | ko |
dc.contributor.author | Yoo, Chang-Dong | ko |
dc.date.accessioned | 2013-08-08T06:05:01Z | - |
dc.date.available | 2013-08-08T06:05:01Z | - |
dc.date.created | 2013-03-18 | - |
dc.date.created | 2013-03-18 | - |
dc.date.issued | 2013-02 | - |
dc.identifier.citation | IEEE TRANSACTIONS ON IMAGE PROCESSING, v.22, no.2, pp.488 - 500 | - |
dc.identifier.issn | 1057-7149 | - |
dc.identifier.uri | http://hdl.handle.net/10203/174873 | - |
dc.description.abstract | Image partitioning is an important preprocessing step for many of the state-of-the-art algorithms used for performing high-level computer vision tasks. Typically, partitioning is conducted without regard to the task in hand. We propose a task-specific image partitioning framework to produce a region-based image representation that will lead to a higher task performance than that reached using any task-oblivious partitioning framework and existing supervised partitioning framework, albeit few in number. The proposed method partitions the image by means of correlation clustering, maximizing a linear discriminant function defined over a superpixel graph. The parameters of the discriminant function that define task-specific similarity/dissimilarity among superpixels are estimated based on structured support vector machine (S-SVM) using task-specific training data. The S-SVM learning leads to a better generalization ability while the construction of the superpixel graph used to define the discriminant function allows a rich set of features to be incorporated to improve discriminability and robustness. We evaluate the learned task-aware partitioning algorithms on three benchmark datasets. Results show that task-aware partitioning leads to better labeling performance than the partitioning computed by the state-of-the-art general-purpose and supervised partitioning algorithms. We believe that the task-specific image partitioning paradigm is widely applicable to improving performance in high-level image understanding tasks. | - |
dc.language | English | - |
dc.publisher | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC | - |
dc.subject | SEGMENTATION | - |
dc.subject | APPEARANCE | - |
dc.title | Task-Specific Image Partitioning | - |
dc.type | Article | - |
dc.identifier.wosid | 000314717800006 | - |
dc.identifier.scopusid | 2-s2.0-84872306546 | - |
dc.type.rims | ART | - |
dc.citation.volume | 22 | - |
dc.citation.issue | 2 | - |
dc.citation.beginningpage | 488 | - |
dc.citation.endingpage | 500 | - |
dc.citation.publicationname | IEEE TRANSACTIONS ON IMAGE PROCESSING | - |
dc.identifier.doi | 10.1109/TIP.2012.2218822 | - |
dc.embargo.liftdate | 9999-12-31 | - |
dc.embargo.terms | 9999-12-31 | - |
dc.contributor.localauthor | Yoo, Chang-Dong | - |
dc.contributor.nonIdAuthor | Nowozin, Sebastian | - |
dc.contributor.nonIdAuthor | Kohli, Pushmeet | - |
dc.type.journalArticle | Article | - |
dc.subject.keywordAuthor | Correlation clustering | - |
dc.subject.keywordAuthor | image partitioning | - |
dc.subject.keywordAuthor | linear programming relaxation | - |
dc.subject.keywordAuthor | structured support vector machine | - |
dc.subject.keywordPlus | SEGMENTATION | - |
dc.subject.keywordPlus | APPEARANCE | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.