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...
Guardado en:
Publicado: |
2014
|
---|---|
Materias: | |
Acceso en línea: | https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_01678655_v36_n1_p213_Ubalde http://hdl.handle.net/20.500.12110/paper_01678655_v36_n1_p213_Ubalde |
Aporte de: |
id |
paper:paper_01678655_v36_n1_p213_Ubalde |
---|---|
record_format |
dspace |
spelling |
paper:paper_01678655_v36_n1_p213_Ubalde2023-06-08T15:17:00Z Efficient descriptor tree growing for fast action recognition 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. 2014 https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_01678655_v36_n1_p213_Ubalde 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) 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. |
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 |
publishDate |
2014 |
url |
https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_01678655_v36_n1_p213_Ubalde http://hdl.handle.net/20.500.12110/paper_01678655_v36_n1_p213_Ubalde |
_version_ |
1768542733876592640 |