Fast non-parametric action recognition
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...
Guardado en:
Publicado: |
2012
|
---|---|
Materias: | |
Acceso en línea: | https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_03029743_v7441LNCS_n_p268_Ubalde http://hdl.handle.net/20.500.12110/paper_03029743_v7441LNCS_n_p268_Ubalde |
Aporte de: |
id |
paper:paper_03029743_v7441LNCS_n_p268_Ubalde |
---|---|
record_format |
dspace |
spelling |
paper:paper_03029743_v7441LNCS_n_p268_Ubalde2023-06-08T15:28:45Z Fast non-parametric action recognition 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 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. 2012 https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_03029743_v7441LNCS_n_p268_Ubalde http://hdl.handle.net/20.500.12110/paper_03029743_v7441LNCS_n_p268_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 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 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. |
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 |
https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_03029743_v7441LNCS_n_p268_Ubalde http://hdl.handle.net/20.500.12110/paper_03029743_v7441LNCS_n_p268_Ubalde |
_version_ |
1768545141935570944 |