Efficient descriptor tree growing for fast action recognition

Mostrar todas las versiones(2)

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
id todo:paper_01678655_v36_n1_p213_Ubalde
record_format dspace
spelling todo:paper_01678655_v36_n1_p213_Ubalde2023-10-03T15:05:27Z Efficient descriptor tree growing for fast action recognition Ubalde, S. Goussies, N.A. Mejail, M.E. Action recognition Instance-to-Class distance Nearest neighbor Pattern recognition Software engineering Action recognition Class-distance Classification performance Generalization capability Nearest neighbors Non-parametric classifiers State of the art Training database Classification (of information) 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. JOUR info:eu-repo/semantics/openAccess http://creativecommons.org/licenses/by/2.5/ar http://hdl.handle.net/20.500.12110/paper_01678655_v36_n1_p213_Ubalde
institution Universidad de Buenos Aires
institution_str I-28
repository_str R-134
collection Biblioteca Digital - Facultad de Ciencias Exactas y Naturales (UBA)
topic Action recognition
Instance-to-Class distance
Nearest neighbor
Pattern recognition
Software engineering
Action recognition
Class-distance
Classification performance
Generalization capability
Nearest neighbors
Non-parametric classifiers
State of the art
Training database
Classification (of information)
spellingShingle Action recognition
Instance-to-Class distance
Nearest neighbor
Pattern recognition
Software engineering
Action recognition
Class-distance
Classification performance
Generalization capability
Nearest neighbors
Non-parametric classifiers
State of the art
Training database
Classification (of information)
Ubalde, S.
Goussies, N.A.
Mejail, M.E.
Efficient descriptor tree growing for fast action recognition
topic_facet Action recognition
Instance-to-Class distance
Nearest neighbor
Pattern recognition
Software engineering
Action recognition
Class-distance
Classification performance
Generalization capability
Nearest neighbors
Non-parametric classifiers
State of the art
Training database
Classification (of information)
description 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.
format JOUR
author Ubalde, S.
Goussies, N.A.
Mejail, M.E.
author_facet Ubalde, S.
Goussies, N.A.
Mejail, M.E.
author_sort Ubalde, S.
title Efficient descriptor tree growing for fast action recognition
title_short Efficient descriptor tree growing for fast action recognition
title_full Efficient descriptor tree growing for fast action recognition
title_fullStr Efficient descriptor tree growing for fast action recognition
title_full_unstemmed Efficient descriptor tree growing for fast action recognition
title_sort efficient descriptor tree growing for fast action recognition
url http://hdl.handle.net/20.500.12110/paper_01678655_v36_n1_p213_Ubalde
work_keys_str_mv AT ubaldes efficientdescriptortreegrowingforfastactionrecognition
AT goussiesna efficientdescriptortreegrowingforfastactionrecognition
AT mejailme efficientdescriptortreegrowingforfastactionrecognition
_version_ 1807321411953360896

Ejemplares similares