Online Action Recognition via Nonparametric Incremental Learning
In Proceedings British Machine Vision Conference 2014
http://dx.doi.org/10.5244/C.28.113
Abstract
We introduce an online action recognition system that can be combined with any set of frame-by-frame feature descriptors. Our system covers the frame feature space with classifiers whose distribution adapts to the hardness of locally approximating the Bayes optimal classifier. An efficient nearest neighbour search is used to find and combine the local classifiers that are closest to the frames of a new video to be classified. The advantages of our approach are: incremental training, frame by frame real-time prediction, nonparametric predictive modelling, video segmentation for continuous action recognition, no need to trim videos to equal lengths and only one tuning parameter (which, for large datasets, can be safely set to the diameter of the feature space). Experiments on standard benchmarks show that our system is competitive with state-of-the-art non-incremental and incremental baselines. keywords: action recognition, incremental learning, continuous action recognition, nonparametric model, real time, multivariate time series classification, temporal classification
Session
Poster Session
Files
Citation
Rocco De Rosa, Nicolò Cesa-Bianchi, Ilaria Gori, and Fabio Cuzzolin. Online Action Recognition via Nonparametric Incremental Learning. Proceedings of the British Machine Vision Conference. BMVA Press, September 2014.
BibTex
@inproceedings{BMVC.28.113
title = {Online Action Recognition via Nonparametric Incremental Learning},
author = {De Rosa, Rocco and Cesa-Bianchi, Nicolò and Gori, Ilaria and Cuzzolin, Fabio},
year = {2014},
booktitle = {Proceedings of the British Machine Vision Conference},
publisher = {BMVA Press},
editors = {Valstar, Michel and French, Andrew and Pridmore, Tony}
doi = { http://dx.doi.org/10.5244/C.28.113 }
}