Efficient descriptor tree growing for fast action recognition

Video and image classification based on Instance-to-Class (I2C) distance attracted many recent studies, due to the good generalization capabilities it provides for non-parametric classifiers. In this work we propose a method for action recognition. Our approach needs no intensive learning stage, and...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Ubalde, S., Goussies, N.A., Mejail, M.E.
Formato: JOUR
Materias:
Action recognition
Instance-to-Class distance
Nearest neighbor
Pattern recognition
Software engineering
Class-distance
Classification performance
Generalization capability
Nearest neighbors
Non-parametric classifiers
State of the art
Training database
Classification (of information)
Acceso en línea:http://hdl.handle.net/20.500.12110/paper_01678655_v36_n1_p213_Ubalde
Aporte de:
Biblioteca Digital - Facultad de Ciencias Exactas y Naturales (UBA) de Universidad de Buenos Aires
Descripción
Sumario:Video and image classification based on Instance-to-Class (I2C) distance attracted many recent studies, due to the good generalization capabilities it provides for non-parametric classifiers. In this work we propose a method for action recognition. Our approach needs no intensive learning stage, and its classification performance is comparable to the state-of-the-art. A smart organization of training data allows the classifier to achieve reasonable computation times when working with large training databases. An efficient method for organizing training data in such a way is proposed. We perform thorough experiments on two popular action recognition datasets: the KTH dataset and the IXMAS dataset, and we study the influence of one of the key parameters of the method on classification performance. © 2013 Elsevier B.V. All rights reserved.

Ejemplares similares