Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/67359
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Wang, L. | - |
dc.contributor.author | Zhou, L. | - |
dc.contributor.author | Shen, C. | - |
dc.date.issued | 2008 | - |
dc.identifier.citation | Proceedings of 10th European Conference on Computer Vision (ECCV), 12-18 October, 2008 / D. Forsyth, P. Torr and A. Zisserman (eds.); Part IV, pp.719-732 | - |
dc.identifier.isbn | 3540886923 | - |
dc.identifier.isbn | 9783540886921 | - |
dc.identifier.issn | 0302-9743 | - |
dc.identifier.issn | 1611-3349 | - |
dc.identifier.uri | http://hdl.handle.net/2440/67359 | - |
dc.description.abstract | In patch-based object recognition, using a compact visual codebook can boost computational efficiency and reduce memory cost. Nevertheless, compared with a large-sized codebook, it also risks the loss of discriminative power. Moreover, creating a compact visual codebook can be very time-consuming, especially when the number of initial visual words is large. In this paper, to minimize its loss of discriminative power, we propose an approach to build a compact visual codebook by maximally preserving the separability of the object classes. Furthermore, a fast algorithm is designed to accomplish this task effortlessly, which can hierarchically merge 10,000 visual words down to 2 in ninety seconds. Experimental study shows that the compact visual codebook created in this way can achieve excellent classification performance even after a considerable reduction in size. © 2008 Springer Berlin Heidelberg. | - |
dc.description.statementofresponsibility | Lei Wang, Luping Zhou and Chunhua Shen | - |
dc.language.iso | en | - |
dc.publisher | Springer | - |
dc.relation.ispartofseries | Lecture Notes in Computer Science; Vol. 5305 | - |
dc.rights | © Springer, Part of Springer Science+Business Media | - |
dc.source.uri | http://dx.doi.org/10.1007/978-3-540-88693-8_53 | - |
dc.title | A fast algorithm for creating a compact and discriminative visual codebook | - |
dc.type | Conference paper | - |
dc.contributor.conference | European Conference on Computer Vision (ECCV) (10th : 2008 : Marseille, France) | - |
dc.identifier.doi | 10.1007/978-3-540-88693-8_53 | - |
dc.publisher.place | New York | - |
pubs.publication-status | Published | - |
dc.identifier.orcid | Shen, C. [0000-0002-8648-8718] | - |
Appears in Collections: | Aurora harvest 5 Computer Science publications |
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.