Unsupervised local regressive attributes for pedestrian re-identification

Simple item page
datacite.alternateIdentifier.citationLecture Notes in Computer Science, Vol. 10657 LNCS, 517-524, 2018en_US
datacite.alternateIdentifier.doi10.1007/978-3-319-75193-1_62en_US
datacite.creatorPeralta Márquez, Billy
datacite.creatorCaro Saldivia, Luis
datacite.creatorSoto, Alvaro
datacite.date2018
datacite.subjectDescubrimiento de atributosen_US
datacite.subjectRe identificación pedestreen_US
datacite.subjectAprendizaje no supervisadoen_US
datacite.titleUnsupervised local regressive attributes for pedestrian re-identificationen_US
dc.date.accessioned2020-04-15T00:26:44Z
dc.date.available2020-04-15T00:26:44Z
dc.description.abstractDiscovering of attributes is a challenging task in computer vision due to uncertainty about the attributes, which is caused mainly by the lack of semantic meaning in image parts. A usual scheme for facing attribute discovering is to divide the feature space using binary variables. Moreover, we can assume to know the attributes and by using expert information we can give a degree of attribute beyond only two values. Nonetheless, a binary variable could not be very informative, and we could not have access to expert information. In this work, we propose to discover linear regressive codes using image regions guided by a supervised criteria where the obtained codes obtain better generalization properties. We found that the discovered regressive codes can be successfully re-used in other visual datasets. As a future work, we plan to explore richer codification structures than lineal mapping considering efficient computationen_US
dc.formatPDFen_US
dc.identifier.urihttp://repositoriodigital.uct.cl/handle/10925/2162
dc.language.isoenen_US
dc.sourceLecture Notes in Computer Scienceen_US
oaire.resourceTypeArtículo de Revistaen_US
uct.catalogadorpopen_US
uct.comunidadIngenieríaen_US
uct.indizacionSCOPUSen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Peralta_Caro_Soto_Unsuperviced_2018.pdf
Size:
434.93 KB
Format:
Adobe Portable Document Format
Description:
Lectura de los datos del documento
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
803 B
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Ciencias de la Ingeniería