Unsupervised local regressive attributes for pedestrian re-identification

Peralta Márquez, Billy; Caro Saldivia, Luis; Soto, Alvaro

Unsupervised local regressive attributes for pedestrian re-identification

dc.contributor.author	Peralta Márquez, Billy
dc.contributor.author	Caro Saldivia, Luis
dc.contributor.author	Soto, Alvaro
dc.date	2018
dc.date.accessioned	2020-04-15T00:26:44Z
dc.date.available	2020-04-15T00:26:44Z
dc.description.abstract	Discovering 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 computation	en_US
dc.format	PDF	en_US
dc.identifier.citation	Lecture Notes in Computer Science, Vol. 10657 LNCS, 517-524, 2018	en_US
dc.identifier.doi	10.1007/978-3-319-75193-1_62	en_US
dc.identifier.uri	http://repositoriodigital.uct.cl/handle/10925/2162
dc.language.iso	en	en_US
dc.source	Lecture Notes in Computer Science	en_US
dc.subject	Descubrimiento de atributos	en_US
dc.subject	Re identificación pedestre	en_US
dc.subject	Aprendizaje no supervisado	en_US
dc.title	Unsupervised local regressive attributes for pedestrian re-identification	en_US
dc.type	Artículo de Revista	en_US
uct.catalogador	pop	en_US
uct.comunidad	Ingeniería	en_US
uct.indizacion	SCOPUS	en_US