Fast non-parametric action recognition

Mostrar todas las versiones(3)

In this work we propose a method for action recognition which needs no intensive learning stage, and achieves state-of-the-art classification performance. Our work is based on a method presented in the context of image classification. Unlike that method, our approach is well-suited for working with...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Ubalde, S., Goussies, N.A.
Formato:	Artículo publishedVersion
Publicado:	2012
Materias:	action recognition image-to-class distance nearest neighbor Action recognition Average running time Classification performance Data sets Nearest neighbors Non-parametric Real-world problem Training data Image analysis Computer vision
Acceso en línea:	http://hdl.handle.net/20.500.12110/paper_03029743_v7441LNCS_n_p268_Ubalde https://repositoriouba.sisbi.uba.ar/gsdl/cgi-bin/library.cgi?a=d&c=artiaex&d=paper_03029743_v7441LNCS_n_p268_Ubalde_oai
Aporte de:	Repositorio Digital de la Universidad de Buenos Aires (UBA) de Universidad de Buenos Aires

id	I28-R145-paper_03029743_v7441LNCS_n_p268_Ubalde_oai
record_format	dspace
spelling	I28-R145-paper_03029743_v7441LNCS_n_p268_Ubalde_oai2024-08-16 Ubalde, S. Goussies, N.A. 2012 In this work we propose a method for action recognition which needs no intensive learning stage, and achieves state-of-the-art classification performance. Our work is based on a method presented in the context of image classification. Unlike that method, our approach is well-suited for working with large real-world problems, thanks to an efficient organization of the training data. We show results on the KTH and IXMAS datasets. On the challenging IXMAS dataset, the average running time is reduced by 50% when using our method. © 2012 Springer-Verlag. application/pdf http://hdl.handle.net/20.500.12110/paper_03029743_v7441LNCS_n_p268_Ubalde info:eu-repo/semantics/openAccess http://creativecommons.org/licenses/by/2.5/ar Lect. Notes Comput. Sci. 2012;7441 LNCS:268-275 action recognition image-to-class distance nearest neighbor Action recognition Average running time Classification performance Data sets image-to-class distance Nearest neighbors Non-parametric Real-world problem Training data Image analysis Computer vision Fast non-parametric action recognition info:eu-repo/semantics/article info:ar-repo/semantics/artículo info:eu-repo/semantics/publishedVersion https://repositoriouba.sisbi.uba.ar/gsdl/cgi-bin/library.cgi?a=d&c=artiaex&d=paper_03029743_v7441LNCS_n_p268_Ubalde_oai
institution	Universidad de Buenos Aires
institution_str	I-28
repository_str	R-145
collection	Repositorio Digital de la Universidad de Buenos Aires (UBA)
topic	action recognition image-to-class distance nearest neighbor Action recognition Average running time Classification performance Data sets image-to-class distance Nearest neighbors Non-parametric Real-world problem Training data Image analysis Computer vision
spellingShingle	action recognition image-to-class distance nearest neighbor Action recognition Average running time Classification performance Data sets image-to-class distance Nearest neighbors Non-parametric Real-world problem Training data Image analysis Computer vision Ubalde, S. Goussies, N.A. Fast non-parametric action recognition
topic_facet	action recognition image-to-class distance nearest neighbor Action recognition Average running time Classification performance Data sets image-to-class distance Nearest neighbors Non-parametric Real-world problem Training data Image analysis Computer vision
description	In this work we propose a method for action recognition which needs no intensive learning stage, and achieves state-of-the-art classification performance. Our work is based on a method presented in the context of image classification. Unlike that method, our approach is well-suited for working with large real-world problems, thanks to an efficient organization of the training data. We show results on the KTH and IXMAS datasets. On the challenging IXMAS dataset, the average running time is reduced by 50% when using our method. © 2012 Springer-Verlag.
format	Artículo Artículo publishedVersion
author	Ubalde, S. Goussies, N.A.
author_facet	Ubalde, S. Goussies, N.A.
author_sort	Ubalde, S.
title	Fast non-parametric action recognition
title_short	Fast non-parametric action recognition
title_full	Fast non-parametric action recognition
title_fullStr	Fast non-parametric action recognition
title_full_unstemmed	Fast non-parametric action recognition
title_sort	fast non-parametric action recognition
publishDate	2012
url	http://hdl.handle.net/20.500.12110/paper_03029743_v7441LNCS_n_p268_Ubalde https://repositoriouba.sisbi.uba.ar/gsdl/cgi-bin/library.cgi?a=d&c=artiaex&d=paper_03029743_v7441LNCS_n_p268_Ubalde_oai
work_keys_str_mv	AT ubaldes fastnonparametricactionrecognition AT goussiesna fastnonparametricactionrecognition
_version_	1809357001953640448

Fast non-parametric action recognition

Ejemplares similares