File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Person Re-Identification Using Multiple Experts with Random Subspaces

TitlePerson Re-Identification Using Multiple Experts with Random Subspaces
Authors
Issue Date2014
PublisherJournal of Image and Graphics. The Journal's web site is located at http://www.joig.org/
Citation
Journal of Image and Graphics, 2014, v. 2 n. 2, p. 151-157 How to Cite?
AbstractThis paper presents a simple and effective multi-expert approach based on random subspaces for person re-identification across non-overlapping camera views. This approach applies to supervised learning methods that learn a continuous decision function. Our proposed method trains a group of expert functions, each of which is only exposed to a random subset of the input features. Each expert function produces an opinion according to the partial features it has. We also introduce weighted fusion schemes to effectively combine the opinions of multiple expert functions together to form a global view. Thus our method overall still makes use of all features without losing much information they carry. Yet each individual expert function can be trained efficiently without overfitting. We have tested our method on the VIPeR, ETHZ, and CAVIAR4REID datasets, and the results demonstrate that our method is able to significantly improve the performance of existing state-of-the-art techniques.
Persistent Identifierhttp://hdl.handle.net/10722/215523
ISSN

 

DC FieldValueLanguage
dc.contributor.authorBi, S-
dc.contributor.authorLi, G-
dc.contributor.authorYu, Y-
dc.date.accessioned2015-08-21T13:28:53Z-
dc.date.available2015-08-21T13:28:53Z-
dc.date.issued2014-
dc.identifier.citationJournal of Image and Graphics, 2014, v. 2 n. 2, p. 151-157-
dc.identifier.issn2301-3699-
dc.identifier.urihttp://hdl.handle.net/10722/215523-
dc.description.abstractThis paper presents a simple and effective multi-expert approach based on random subspaces for person re-identification across non-overlapping camera views. This approach applies to supervised learning methods that learn a continuous decision function. Our proposed method trains a group of expert functions, each of which is only exposed to a random subset of the input features. Each expert function produces an opinion according to the partial features it has. We also introduce weighted fusion schemes to effectively combine the opinions of multiple expert functions together to form a global view. Thus our method overall still makes use of all features without losing much information they carry. Yet each individual expert function can be trained efficiently without overfitting. We have tested our method on the VIPeR, ETHZ, and CAVIAR4REID datasets, and the results demonstrate that our method is able to significantly improve the performance of existing state-of-the-art techniques.-
dc.languageeng-
dc.publisherJournal of Image and Graphics. The Journal's web site is located at http://www.joig.org/-
dc.relation.ispartofJournal of Image and Graphics-
dc.titlePerson Re-Identification Using Multiple Experts with Random Subspaces-
dc.typeArticle-
dc.identifier.emailBi, S: bisai@hku.hk-
dc.identifier.emailYu, Y: yzyu@cs.hku.hk-
dc.identifier.authorityYu, Y=rp01415-
dc.identifier.doi10.12720/joig.2.2.151-157-
dc.identifier.hkuros249511-
dc.identifier.volume2-
dc.identifier.issue2-
dc.identifier.spage151-
dc.identifier.epage157-
dc.publisher.placeUnited States-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats