Please use this identifier to cite or link to this item:
https://scholarbank.nus.edu.sg/handle/10635/121113
DC Field | Value | |
---|---|---|
dc.title | CONTENT EXTRACTION BASED ON VIDEO CO-SEGMENTATION | |
dc.contributor.author | GUO JIAMING | |
dc.date.accessioned | 2015-09-30T18:01:20Z | |
dc.date.available | 2015-09-30T18:01:20Z | |
dc.date.issued | 2014-12-24 | |
dc.identifier.citation | GUO JIAMING (2014-12-24). CONTENT EXTRACTION BASED ON VIDEO CO-SEGMENTATION. ScholarBank@NUS Repository. | |
dc.identifier.uri | http://scholarbank.nus.edu.sg/handle/10635/121113 | |
dc.description.abstract | Given a set of images or videos having common content, the objective of co-segmentation is to simultaneously segment the set of images or videos to extract this common content. The term ?common content? here refers to the image or video regions that depict the same thing, which, in most of the cases, is the theme of the input images or videos acknowledged by the user. Most previous approaches focus on image co-segmentation, while recently, more and more attempts have been made on the problem of video co-segmentation, which presents much more complexity and di?culty than image segmentation. In this thesis, we address the challenge of video co-segmentation and develop techniques for common content extraction. | |
dc.language.iso | en | |
dc.subject | content extraction, video segmentation, video action co-segmentation, video object co-segmentation, co-saliency, constraint clustering | |
dc.type | Thesis | |
dc.contributor.department | ELECTRICAL & COMPUTER ENGINEERING | |
dc.contributor.supervisor | ZHOU ZHIYING | |
dc.contributor.supervisor | CHEONG LOONG FAH | |
dc.description.degree | Ph.D | |
dc.description.degreeconferred | DOCTOR OF PHILOSOPHY | |
dc.identifier.isiut | NOT_IN_WOS | |
Appears in Collections: | Ph.D Theses (Open) |
Show simple item record
Files in This Item:
File | Description | Size | Format | Access Settings | Version | |
---|---|---|---|---|---|---|
GuoJM.pdf | 3.17 MB | Adobe PDF | OPEN | None | View/Download |
Google ScholarTM
Check
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.