doi:10.1109/TCYB.2016.2558447engRodríguez, MarioOrrite, CarlosMedrano, CarlosMakris, DimitriosOne-Shot Learning of Human Activity With an MAP Adapted GMM and Simplex-HMMART-2017-97394This 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.2017http://zaguan.unizar.es/record/6439610.1109/TCYB.2016.2558447http://zaguan.unizar.es/record/64396oai:zaguan.unizar.es:64396info:eu-repo/grantAgreement/ES/MINECO/BES-2011-043752info:eu-repo/grantAgreement/ES/MINECO/TIN2013-45312-RIEEE transactions on cybernetics 47, 7 (2017), 1769-1780All rights reservedhttp://www.europeana.eu/rights/rr-f/info:eu-repo/semantics/openAccess