dc.date.accessioned2019-01-29T22:19:48Z
dc.date.accessioned2023-05-30T23:27:30Z
dc.date.available2019-01-29T22:19:48Z
dc.date.available2023-05-30T23:27:30Z
dc.date.created2019-01-29T22:19:48Z
dc.date.issued2018
dc.identifierurn:isbn:9781538634837
dc.identifier15224902
dc.identifierhttp://repositorio.ucsp.edu.pe/handle/UCSP/15753
dc.identifierhttps://doi.org/10.1109/SCCC.2017.8405126
dc.identifier.urihttps://repositorioslatinoamericanos.uchile.cl/handle/2250/6477566
dc.description.abstractPerson re-identificacion consists of reidentificating person through a set of images that is taken by different camera views. Despite recent advances in this field, this problem still remains a challenge due to partial occlusions, changes in illumination, variation in human body poses. In this paper, we present an enhanced Triplet CNN based on body-parts for person re-identification (AETCNN). We design a new model able to learn local body-part features and integrate them to produce the final feature representation of each input person. In addition, to avoid over-fitting due to the small size of the dataset, we propose an improvement in triplet assignment to speed up the convergence and improve performance. Experiments show that our approach achieves very promising results in (CUHK01) dataset and we advance state of the art, improving most of the results of the state of the art with a simpler architecture, achieving 76.50% in rank 1. © 2017 IEEE.
dc.languageeng
dc.publisherIEEE Computer Society
dc.relationhttps://www.scopus.com/inward/record.uri?eid=2-s2.0-85050964708&doi=10.1109%2fSCCC.2017.8405126&partnerID=40&md5=9e042531aae808dde5cdb698314f43ea
dc.rightsinfo:eu-repo/semantics/restrictedAccess
dc.sourceRepositorio Institucional - UCSP
dc.sourceUniversidad Católica San Pablo
dc.sourceScopus
dc.subjectComputers
dc.subjectCamera view
dc.subjectFeature representation
dc.subjectHuman bodies
dc.subjectImprove performance
dc.subjectOverfitting
dc.subjectPartial occlusions
dc.subjectPerson re identifications
dc.subjectState of the art
dc.subjectComputer science
dc.titleAn enhanced triplet CNN based on body parts for person re-identificacion
dc.typeinfo:eu-repo/semantics/conferenceObject


Este ítem pertenece a la siguiente institución