Navegar

Colección

Datos Estadísticas

Artículo

Ubalde, S.; Goussies, N.A. "Fast non-parametric action recognition" (2012) 17th Iberoamerican Congress on Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications, CIARP 2012. 7441 LNCS:268-275
Este artículo es de Acceso Abierto y puede ser descargado en su versión final desde nuestro repositorio
Consulte el artículo en la página del editor
Consulte la política de Acceso Abierto del editor

Abstract:

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.

Registro:

Documento: Artículo
Título:Fast non-parametric action recognition
Autor:Ubalde, S.; Goussies, N.A.
Ciudad:Buenos Aires
Filiación:Departamento de Computación, Facultad de Ciencias Exactas Y Naturales, Universidad de Buenos Aires, Buenos Aires, Argentina
Palabras clave: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
Año:2012
Volumen:7441 LNCS
Página de inicio:268
Página de fin:275
DOI: http://dx.doi.org/10.1007/978-3-642-33275-3_33
Título revista:17th Iberoamerican Congress on Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications, CIARP 2012
Título revista abreviado:Lect. Notes Comput. Sci.
ISSN:03029743
PDF:https://bibliotecadigital.exactas.uba.ar/download/paper/paper_03029743_v7441LNCS_n_p268_Ubalde.pdf
Registro:https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_03029743_v7441LNCS_n_p268_Ubalde

Referencias:

  • Davis, J., Bobick, A., The representation and recognition of action using temporal templates (1997) CVPR 1997, pp. 928-934
  • Weinland, D., Boyer, E., Ronfard, R., Action recognition from arbitrary views using 3d exemplars (2007) ICCV 2007, pp. 1-7
  • Yan, P., Khan, S., Shah, M., Learning 4d action feature models for arbitrary view action recognition (2008) CVPR 2008, pp. 1-7
  • Zelnik-manor, L., Irani, M., Event-based analysis of video (2001) Proc. CVPR, pp. 123-130
  • Laptev, I., Marszalek, M., Schmid, C., Rozenfeld, B., Learning realistic human actions from movies (2008) CVPR 2008, pp. 1-8
  • Dollar, P., Rabaud, V., Cottrell, G., Belongie, S., Behavior recognition via sparse spatiotemporal features (2005) PETS 2005, pp. 65-72
  • Zou, W., Yeung, S., Ng, A., Learning hierarchical invariant spatio-temporal features for action recognition with independent subspace analysis (2011) CVPR 2011, pp. 3361-3368
  • Goussies, N.A., Liu, Z., Yuan, J., Efficient search of top-k video subvolumes for multi-instance action detection (2010) ICME 2010, pp. 328-333
  • Yu, G., Goussies, N., Yuan, J., Liu, Z., Fast action detection via discriminative random forest voting and top-k subvolume search (2011) MultMed., 13 (3), pp. 507-517
  • Sivic, J., Zisserman, A., Video google: A text retrieval approach to object matching in videos (2003) ICCV 2003, pp. 1470-1477
  • Liu, J., Shah, M., Learning human actions via information maximization (2008) CVPR 2008, pp. 1-8
  • Bregonzio, M., Gong, S., Xiang, T., Recognising action as clouds of space-time interest points (2009) CVPR 2009, pp. 1948-1955
  • Boiman, O., Shechtman, E., Irani, M., In defense of nearest-neighbor based image classification (2008) CVPR 2008, pp. 1-8
  • Wang, Z., Hu, Y., Chia, L., Learning instance-to-class distance for human action recognition (2009) ICIP 2009, pp. 3545-3548
  • Yuan, J., Liu, Z., Wu, Y., Discriminative video pattern search for efficient action detection (2011) PAMI, 33, pp. 1728-1743
  • Laptev, I., On space-time interest points (2005) IJCV, 64, pp. 107-123
  • Muja, M., Lowe, D.G., Fast approximate nearest neighbors with automatic algorithm configuration (2009) International Conference on Computer Vision Theory and Application, VISSAPP 2009, pp. 331-340. , INSTICC Press
  • Zelnik Manor, L., Irani, M., Weinland, D., Ronfard, R., Boyer, E., Free viewpoint action recognition using motion history volumes (2006) CVIU, 103, pp. 249-257
  • Nowozin, S., Bakir, G., Tsuda, K., Discriminative subsequence mining for action classification (2007) ICCV 2007, pp. 1-8

Citas:

---------- APA ----------
Ubalde, S. & Goussies, N.A. (2012) . Fast non-parametric action recognition. 17th Iberoamerican Congress on Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications, CIARP 2012, 7441 LNCS, 268-275.
http://dx.doi.org/10.1007/978-3-642-33275-3_33
---------- CHICAGO ----------
Ubalde, S., Goussies, N.A. "Fast non-parametric action recognition" . 17th Iberoamerican Congress on Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications, CIARP 2012 7441 LNCS (2012) : 268-275.
http://dx.doi.org/10.1007/978-3-642-33275-3_33
---------- MLA ----------
Ubalde, S., Goussies, N.A. "Fast non-parametric action recognition" . 17th Iberoamerican Congress on Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications, CIARP 2012, vol. 7441 LNCS, 2012, pp. 268-275.
http://dx.doi.org/10.1007/978-3-642-33275-3_33
---------- VANCOUVER ----------
Ubalde, S., Goussies, N.A. Fast non-parametric action recognition. Lect. Notes Comput. Sci. 2012;7441 LNCS:268-275.
http://dx.doi.org/10.1007/978-3-642-33275-3_33