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: SER
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
Aporte de:
Biblioteca Digital - Facultad de Ciencias Exactas y Naturales (UBA) de Universidad de Buenos Aires
Descripción
Sumario: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.

Ejemplares similares