Share Email Print

Proceedings Paper

Weighting video information into a multikernel SVM for human action recognition
Author(s): Jordi Bautista-Ballester; Jaume Vergés-Llahí; Domenec Puig
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Action classification using a Bag of Words (BoW) representation has shown computational simplicity and good performance, but the increasing number of categories, including actions with high confusion, and the addition of significant contextual information has led most authors to focus their efforts on the combination of image descriptors. In this approach we code the action videos using a BoW representation with diverse image descriptors and introduce them to the optimal SVM kernel as a linear combination of learning weighted single kernels. Experiments have been carried out on the action database HMDB and the upturn achieved with our approach is much better than the state of the art, reaching an improvement of 14.63% of accuracy.

Paper Details

Date Published: 8 December 2015
PDF: 5 pages
Proc. SPIE 9875, Eighth International Conference on Machine Vision (ICMV 2015), 98750J (8 December 2015); doi: 10.1117/12.2228527
Show Author Affiliations
Jordi Bautista-Ballester, ATEKNEA Solutions (Spain)
Univ. Rovira i Virgili (Spain)
Jaume Vergés-Llahí, ATEKNEA Solutions (Spain)
Domenec Puig, Univ. Rovira i Virgili (Spain)

Published in SPIE Proceedings Vol. 9875:
Eighth International Conference on Machine Vision (ICMV 2015)
Antanas Verikas; Petia Radeva; Dmitry Nikolaev, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?