Please use this identifier to cite or link to this item:
https://doi.org/10.1109/ICIP.2010.5652300
DC Field | Value | |
---|---|---|
dc.title | Video categorization using Object of Interest detection | |
dc.contributor.author | Kowdle A. | |
dc.contributor.author | Chang K.-W. | |
dc.contributor.author | Chen T. | |
dc.date.accessioned | 2018-08-21T04:59:58Z | |
dc.date.available | 2018-08-21T04:59:58Z | |
dc.date.issued | 2010 | |
dc.identifier.citation | Kowdle A., Chang K.-W., Chen T. (2010). Video categorization using Object of Interest detection. Proceedings - International Conference on Image Processing, ICIP : 4569-4572. ScholarBank@NUS Repository. https://doi.org/10.1109/ICIP.2010.5652300 | |
dc.identifier.isbn | 9781424479948 | |
dc.identifier.issn | 15224880 | |
dc.identifier.uri | http://scholarbank.nus.edu.sg/handle/10635/146162 | |
dc.description.abstract | Object of Interest (OOI) detection has been widely used in many recent works in video analysis, especially in video similarity and video retrieval. In this paper, we describe a generic video classification algorithm using object of interest dectection. We use online user-submitted videos and aim to categorize the videos into six broad categories hot star, news, anime, pets, sports and commercials. We show through our experiments that, detecting and describing the object of interest improves the video classification accuracy by about 10 percentage points. | |
dc.source | Scopus | |
dc.subject | Object of interest detection | |
dc.subject | Video classification | |
dc.type | Conference Paper | |
dc.contributor.department | OFFICE OF THE PROVOST | |
dc.contributor.department | DEPARTMENT OF COMPUTER SCIENCE | |
dc.description.doi | 10.1109/ICIP.2010.5652300 | |
dc.description.sourcetitle | Proceedings - International Conference on Image Processing, ICIP | |
dc.description.page | 4569-4572 | |
dc.published.state | published | |
Appears in Collections: | Staff Publications |
Show simple item record
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.