8 December 2015 Weighting video information into a multikernel SVM for human action recognition
Author Affiliations +
Proceedings Volume 9875, Eighth International Conference on Machine Vision (ICMV 2015); 98750J (2015) https://doi.org/10.1117/12.2228527
Event: Eighth International Conference on Machine Vision, 2015, Barcelona, Spain
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.
© (2015) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Jordi Bautista-Ballester, Jaume Vergés-Llahí, Domenec Puig, "Weighting video information into a multikernel SVM for human action recognition ", Proc. SPIE 9875, Eighth International Conference on Machine Vision (ICMV 2015), 98750J (8 December 2015); doi: 10.1117/12.2228527; https://doi.org/10.1117/12.2228527
PROCEEDINGS
5 PAGES


SHARE
RELATED CONTENT

A robust SIFT-based descriptor for video classification
Proceedings of SPIE (February 14 2015)
Psychophysical evaluation of document visual similarity
Proceedings of SPIE (February 21 2012)
Detection of camera operations in compressed video sequences
Proceedings of SPIE (January 15 1997)
Feature management for large video databases
Proceedings of SPIE (April 14 1993)
Video genre classification using multimodal features
Proceedings of SPIE (December 18 2003)
Using a CBIR scheme based on expert knowledge for a...
Proceedings of SPIE (May 01 2003)

Back to Top