DC Field | Value | Language |
---|---|---|
dc.contributor.author | Yoo, Dong Geun | ko |
dc.contributor.author | Park, Sung Gyun | ko |
dc.contributor.author | Lee, Joon Young | ko |
dc.contributor.author | Kweon, In So | ko |
dc.date.accessioned | 2016-04-18T05:13:25Z | - |
dc.date.available | 2016-04-18T05:13:25Z | - |
dc.date.created | 2015-11-24 | - |
dc.date.created | 2015-11-24 | - |
dc.date.created | 2015-11-24 | - |
dc.date.issued | 2015-06-10 | - |
dc.identifier.citation | CVPR2015 IEEE Conference on Computer Vision and Pattern Recognition | - |
dc.identifier.uri | http://hdl.handle.net/10203/204481 | - |
dc.description.abstract | Compared to image representation based on low-level local descriptors, deep neural activations of Convolutional Neural Networks (CNNs) are richer in mid-level representation, but poorer in geometric invariance properties. In this paper, we present a straightforward framework for better image representation by combining the two approaches. To take advantages of both representations, we extract a fair amount of multi-scale dense local activations from a pre-trained CNN. We then aggregate the activations by Fisher kernel framework, which has been modified with a simple scale-wise normalization essential to make it suitable for CNN activations. Our representation demonstrates new state-of-the-art performances on three public datasets: 80.78% (Acc.) on MIT Indoor 67, 83.20% (mAP) on PASCAL VOC 2007 and 91.28% (Acc.) on Oxford 102 Flowers. The results suggest that our proposal can be used as a primary image representation for better performances in wide visual recognition tasks. | - |
dc.language | English | - |
dc.publisher | IEEE Computer Society and the Computer Vision Foundation (CVF) | - |
dc.title | Multi-scale Pyramid Pooling for Deep Convolutional Representation | - |
dc.type | Conference | - |
dc.identifier.wosid | 000378887900009 | - |
dc.identifier.scopusid | 2-s2.0-84952053193 | - |
dc.type.rims | CONF | - |
dc.citation.publicationname | CVPR2015 IEEE Conference on Computer Vision and Pattern Recognition | - |
dc.identifier.conferencecountry | US | - |
dc.identifier.conferencelocation | Hynes Convention Center, Boston | - |
dc.embargo.liftdate | 9999-12-31 | - |
dc.embargo.terms | 9999-12-31 | - |
dc.contributor.localauthor | Kweon, In So | - |
dc.contributor.nonIdAuthor | Park, Sung Gyun | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.