Improving the Accuracy of Action Classification Using View-Dependent Context Information

e-Archivo Repository

Improving the Accuracy of Action Classification Using View-Dependent Context Information

Author(s): Cilla, Rodrigo; Patricio Guisado, Miguel Ángel; Berlanga de Jesús, Antonio; Molina López, José Manuel
Publisher: Springer
Issued date: 2011
Citation: Corchado, E. et al. (eds.) (2011) Hybrid Artificial Intelligent Systems: 6th International Conference, HAIS 2011, Wroclaw, Poland, May 23-25, 2011, Proceedings, Part II. (Lecture Notes in Computer Science, 6679). Springer, pp. 136- 143.
ISBN: 978-3-642-21222-2 (online)
978-3-642-21221-5 (print)
ISSN: 0302-9743
DOI: 10.1007/978-3-642-21222-2_17
Sponsor: This work was supported in part by Projects CICYT TIN2008-06742-C02-02/ TSI, CICYT TEC2008-06732-C02-02/TEC, CAM CONTEXTS (S2009/ TIC-1485) and DPS2008-07029-C02-02.
Serie/No.: Lecture Notes in Computer Science
6679
Project: Comunidad de Madrid. S2009/TIC-1485/CONTEXTS
Keywords: Human Action Recognition
URI: http://hdl.handle.net/10016/18332
Rights: © 2011 Springer-Verlag Berlin Heidelberg

Abstract:

This paper presents a human action recognition system that decomposes the task in two subtasks. First, a view-independent classifier, shared between the multiple views to analyze, is applied to obtain an initial guess of the posterior distribution of the perfo [+]

Description:

Proceedings of: 6th International Conference, HAIS 2011, Wroclaw, Poland, May 23-25, 2011

Show full item record

Impact:

 

Files in this item

ADOBE PDF PREVIEW
Name: improving_HAIS_LN ...
Size: 593.1Kb
Format: PDF
OPENACCESS
*Click on file's image for preview. (Embargoed files's preview is not supported)


Find Full text

This item appears in the following Collection(s)