573 0

Full metadata record

DC FieldValueLanguage
dc.contributor.authorYang, Ming-hsuan-
dc.date.accessioned2017-02-22T05:40:29Z-
dc.date.available2017-02-22T05:40:29Z-
dc.date.issued2015-06-
dc.identifier.citationComputer Vision and Pattern Recognition (CVPR), 2015 IEEE Conference on 2015 June, Page. 731-739en_US
dc.identifier.isbn978-1-4673-6964-0-
dc.identifier.issn1063-6919-
dc.identifier.urihttp://ieeexplore.ieee.org/document/7298673/?isnumber=7298593&arnumber=7298673-
dc.identifier.urihttp://hdl.handle.net/20.500.11754/25639-
dc.description.abstractLearning models for object detection is a challenging problem due to the large intra-class variability of objects in appearance, viewpoints, and rigidity. We address this variability by a novel feature pooling method that is adaptive to segmented regions. The proposed detection algorithm automatically discovers a diverse set of exemplars and their distinctive parts which are used to encode the region structure by the proposed feature pooling method. Based on each exemplar and its parts, a regression model is learned with samples selected by a coarse region matching scheme. The proposed algorithm performs favorably on the PASCAL VOC 2007 dataset against existing algorithms. We demonstrate the benefits of our feature pooling method when compared to conventional spatial pyramid pooling features. We also show that object information can be transferred through exemplars for detected objects.en_US
dc.description.sponsorshipThis work is supported in part by the NSF CAREER Grant #1149783 and NSF IIS Grant #1152576.en_US
dc.language.isoenen_US
dc.publisherIEEEen_US
dc.subjectFeature extractionen_US
dc.subjectProposalsen_US
dc.subjectTrainingen_US
dc.subjectAdaptation modelsen_US
dc.subjectTestingen_US
dc.subjectObject detectionen_US
dc.subjectImage segmentationen_US
dc.titleAdaptive Region Pooling for Object Detectionen_US
dc.typeArticleen_US
dc.identifier.doi10.1109/CVPR.2015.7298673-
dc.relation.page731-739-
dc.contributor.googleauthorTsai, Yi-Hsuan-
dc.contributor.googleauthorHamsici, Onur C.-
dc.contributor.googleauthorYang, Ming-Hsuan-
dc.relation.code20150012-
dc.sector.campusS-
dc.sector.daehakCOLLEGE OF ENGINEERING[S]-
dc.sector.departmentDEPARTMENT OF COMPUTER SCIENCE-
dc.identifier.pidmhyang-
Appears in Collections:
COLLEGE OF ENGINEERING[S](공과대학) > COMPUTER SCIENCE AND ENGINEERING(컴퓨터공학부) > Articles
Files in This Item:
There are no files associated with this item.
Export
RIS (EndNote)
XLS (Excel)
XML


qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE