@InProceedings{RibeiroTeiFerJrNas:2016:CoAsLa,
author = "Ribeiro, Manoel Horta and Teixeira, Bruno and Fernandes,
Ant{\^o}nio Ot{\'a}vio and Jr. , Wagner Meira and Nascimento,
Erickson R.",
affiliation = "Computer Science Department, Universidade Federal de Minas Gerais
and Computer Science Department, Universidade Federal de Minas
Gerais and Computer Science Department, Universidade Federal de
Minas Gerais and Computer Science Department, Universidade Federal
de Minas Gerais and Computer Science Department, Universidade
Federal de Minas Gerais",
title = "Complexity-Aware Assignment of Latent Values in Discriminative
Models for Accurate Gesture Recognition",
booktitle = "Proceedings...",
year = "2016",
editor = "Aliaga, Daniel G. and Davis, Larry S. and Farias, Ricardo C. and
Fernandes, Leandro A. F. and Gibson, Stuart J. and Giraldi, Gilson
A. and Gois, Jo{\~a}o Paulo and Maciel, Anderson and Menotti,
David and Miranda, Paulo A. V. and Musse, Soraia and Namikawa,
Laercio and Pamplona, Mauricio and Papa, Jo{\~a}o Paulo and
Santos, Jefersson dos and Schwartz, William Robson and Thomaz,
Carlos E.",
organization = "Conference on Graphics, Patterns and Images, 29. (SIBGRAPI)",
publisher = "IEEE Computer Society´s Conference Publishing Services",
address = "Los Alamitos",
keywords = "discriminative models, conditional random fields, gesture
recognition, activity recognition.",
abstract = "Many of the state-of-the-art algorithms for gesture recognition
are based on Conditional Random Fields (CRFs). Successful
approaches, such as the Latent-Dynamic CRFs, extend the CRF by
incorporating latent variables, whose values are mapped to the
values of the labels. In this paper we propose a novel methodology
to set the latent values according to the gesture complexity. We
use an heuristic that iterates through the samples associated with
each label value, estimating their complexity. We then use it to
assign the latent values to the label values. We evaluate our
method on the task of recognizing human gestures from video
streams. The experiments were performed in binary datasets,
generated by grouping different labels. Our results demonstrate
that our approach outperforms the arbitrary one in many cases,
increasing the accuracy by up to 10\%.",
conference-location = "S{\~a}o Jos{\'e} dos Campos, SP, Brazil",
conference-year = "4-7 Oct. 2016",
doi = "10.1109/SIBGRAPI.2016.059",
url = "http://dx.doi.org/10.1109/SIBGRAPI.2016.059",
language = "en",
ibi = "8JMKD3MGPAW/3M4UNG2",
url = "http://urlib.net/ibi/8JMKD3MGPAW/3M4UNG2",
targetfile = "manoel_sibgrapi_final_version.pdf",
urlaccessdate = "2024, May 03"
}