One-Shot Learning of Human Activity With an MAP Adapted GMM and Simplex-HMM

Rodríguez, Mario (Universidad de Zaragoza) ; Orrite, Carlos (Universidad de Zaragoza) ; Medrano, Carlos (Universidad de Zaragoza) ; Makris, Dimitrios

Resumen: This 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.

Idioma: Inglés

DOI: 10.1109/TCYB.2016.2558447

Año: 2017

Publicado en: IEEE transactions on cybernetics 47, 7 (2017), 1769-1780
ISSN: 2168-2267

Factor impacto JCR: 8.803 (2017)

Categ. JCR: AUTOMATION & CONTROL SYSTEMS rank: 1 / 61 = 0.016 (2017) - Q1 - T1
Categ. JCR: COMPUTER SCIENCE, CYBERNETICS rank: 1 / 22 = 0.045 (2017) - Q1 - T1
Categ. JCR: COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE rank: 3 / 132 = 0.023 (2017) - Q1 - T1

Factor impacto SCIMAGO: 3.274 - Computer Science Applications (Q1) - Control and Systems Engineering (Q1) - Software (Q1) - Human-Computer Interaction (Q1) - Information Systems (Q1) - Electrical and Electronic Engineering (Q1)

Financiación: info:eu-repo/grantAgreement/ES/MINECO/BES-2011-043752
Financiación: info:eu-repo/grantAgreement/ES/MINECO/TIN2013-45312-R

Tipo y forma: Artículo (PostPrint)

Área (Departamento): Área Tecnología Electrónica (Dpto. Ingeniería Electrón.Com.)
Área (Departamento): Proy. investigación JBA (Dpto. Ingeniería Electrón.Com.)