000064396 001__ 64396
000064396 005__ 20190709135424.0
000064396 0247_ $$2doi$$a10.1109/TCYB.2016.2558447
000064396 0248_ $$2sideral$$a97394
000064396 037__ $$aART-2017-97394
000064396 041__ $$aeng
000064396 100__ $$0(orcid)0000-0001-6324-940X$$aRodríguez, Mario$$uUniversidad de Zaragoza
000064396 245__ $$aOne-Shot Learning of Human Activity With an MAP Adapted GMM and Simplex-HMM
000064396 260__ $$c2017
000064396 5060_ $$aAccess copy available to the general public$$fUnrestricted
000064396 5203_ $$aThis paper presents a novel activity class representation using a single sequence for training. The contribution of this representation lays on the ability to train an one-shot learning recognition system, useful in new scenarios where capturing and labeling sequences is expensive or impractical. The method uses a universal background model of local descriptors obtained from source databases available on-line and adapts it to a new sequence in the target scenario through a maximum a posteriori adaptation. Each activity sample is encoded in a sequence of normalized bag of features and modeled by a new hidden Markov model formulation, where the expectation-maximization algorithm for training is modified to deal with observations consisting in vectors in a unit simplex. Extensive experiments in recognition have been performed using one-shot learning over the public datasets Weizmann, KTH, and IXMAS. These experiments demonstrate the discriminative properties of the representation and the validity of application in recognition systems, achieving state-of-the-art results.
000064396 536__ $$9info:eu-repo/grantAgreement/ES/MINECO/BES-2011-043752$$9info:eu-repo/grantAgreement/ES/MINECO/TIN2013-45312-R
000064396 540__ $$9info:eu-repo/semantics/openAccess$$aAll rights reserved$$uhttp://www.europeana.eu/rights/rr-f/
000064396 590__ $$a8.803$$b2017
000064396 591__ $$aAUTOMATION & CONTROL SYSTEMS$$b1 / 61 = 0.016$$c2017$$dQ1$$eT1
000064396 591__ $$aCOMPUTER SCIENCE, CYBERNETICS$$b1 / 22 = 0.045$$c2017$$dQ1$$eT1
000064396 591__ $$aCOMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE$$b3 / 132 = 0.023$$c2017$$dQ1$$eT1
000064396 592__ $$a3.274$$b2017
000064396 593__ $$aComputer Science Applications$$c2017$$dQ1
000064396 593__ $$aControl and Systems Engineering$$c2017$$dQ1
000064396 593__ $$aSoftware$$c2017$$dQ1
000064396 593__ $$aHuman-Computer Interaction$$c2017$$dQ1
000064396 593__ $$aInformation Systems$$c2017$$dQ1
000064396 593__ $$aElectrical and Electronic Engineering$$c2017$$dQ1
000064396 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/acceptedVersion
000064396 700__ $$0(orcid)0000-0002-0903-5520$$aOrrite, Carlos$$uUniversidad de Zaragoza
000064396 700__ $$0(orcid)0000-0001-7671-7540$$aMedrano, Carlos$$uUniversidad de Zaragoza
000064396 700__ $$aMakris, Dimitrios
000064396 7102_ $$15008$$2785$$aUniversidad de Zaragoza$$bDpto. Ingeniería Electrón.Com.$$cÁrea Tecnología Electrónica
000064396 7102_ $$15008$$2X$$aUniversidad de Zaragoza$$bDpto. Ingeniería Electrón.Com.$$cProy. investigación JBA
000064396 773__ $$g47, 7 (2017), 1769-1780$$pIEEE trans. cybern. (Print)$$tIEEE transactions on cybernetics$$x2168-2267
000064396 8564_ $$s670965$$uhttps://zaguan.unizar.es/record/64396/files/texto_completo.pdf$$yPostprint
000064396 8564_ $$s139680$$uhttps://zaguan.unizar.es/record/64396/files/texto_completo.jpg?subformat=icon$$xicon$$yPostprint
000064396 909CO $$ooai:zaguan.unizar.es:64396$$particulos$$pdriver
000064396 951__ $$a2019-07-09-11:28:16
000064396 980__ $$aARTICLE