Transfer Learning Decision Forests for Gesture Recognition

Autores
Goussies, Norberto Adrián; Ubalde, Sebastián; Mejail, Marta Estela
Año de publicación
2014
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
Decision forests are an increasingly popular tool in computer vision problems. Their advantages include high computational efficiency, state-of-the-art accuracy and multi-class support. In this paper, we present a novel method for transfer learning which uses decision forests, and we apply it to recognize gestures and characters. We introduce two mechanisms into the decision forest framework in order to transfer knowledge from the source tasks to a given target task. The first one is mixed information gain, which is a data-based regularizer. The second one is label propagation, which infers the manifold structure of the feature space. We show that both of them are important to achieve higher accuracy. Our experiments demonstrate improvements over traditional decision forests in the ChaLearn Gesture Challenge and MNIST data set. They also compare favorably against other state-of-the-art classifiers.
Fil: Goussies, Norberto Adrián. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Departamento de Computación; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina
Fil: Ubalde, Sebastián. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Departamento de Computación; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina
Fil: Mejail, Marta Estela. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Departamento de Computación; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina
Materia
Gesture Recognition
Nivel de accesibilidad
acceso abierto
Condiciones de uso
https://creativecommons.org/licenses/by-nc-nd/2.5/ar/
Repositorio
CONICET Digital (CONICET)
Institución
Consejo Nacional de Investigaciones Científicas y Técnicas
OAI Identificador
oai:ri.conicet.gov.ar:11336/33149
Acceder
id CONICETDig_5c8cfb8991e065e8b7a00b236aa0403d
oai_identifier_str oai:ri.conicet.gov.ar:11336/33149
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling Transfer Learning Decision Forests for Gesture RecognitionGoussies, Norberto AdriánUbalde, SebastiánMejail, Marta EstelaGesture Recognitionhttps://purl.org/becyt/ford/1.2https://purl.org/becyt/ford/1Decision forests are an increasingly popular tool in computer vision problems. Their advantages include high computational efficiency, state-of-the-art accuracy and multi-class support. In this paper, we present a novel method for transfer learning which uses decision forests, and we apply it to recognize gestures and characters. We introduce two mechanisms into the decision forest framework in order to transfer knowledge from the source tasks to a given target task. The first one is mixed information gain, which is a data-based regularizer. The second one is label propagation, which infers the manifold structure of the feature space. We show that both of them are important to achieve higher accuracy. Our experiments demonstrate improvements over traditional decision forests in the ChaLearn Gesture Challenge and MNIST data set. They also compare favorably against other state-of-the-art classifiers.Fil: Goussies, Norberto Adrián. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Departamento de Computación; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; ArgentinaFil: Ubalde, Sebastián. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Departamento de Computación; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; ArgentinaFil: Mejail, Marta Estela. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Departamento de Computación; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; ArgentinaMicrotome2014info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/33149Goussies, Norberto Adrián; Ubalde, Sebastián; Mejail, Marta Estela; Transfer Learning Decision Forests for Gesture Recognition ; Microtome; Journal of Machine Learning Research; 15; 2014; 3847−38701532-44351533-7928CONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/url/http://jmlr.org/papers/v15/goussies14a.htmlinfo:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by-nc-nd/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2025-09-10T13:14:11Zoai:ri.conicet.gov.ar:11336/33149instacron:CONICETInstitucionalhttp://ri.conicet.gov.ar/Organismo científico-tecnológicoNo correspondehttp://ri.conicet.gov.ar/oai/requestdasensio@conicet.gov.ar; lcarlino@conicet.gov.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:34982025-09-10 13:14:11.325CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv Transfer Learning Decision Forests for Gesture Recognition
title Transfer Learning Decision Forests for Gesture Recognition
spellingShingle Transfer Learning Decision Forests for Gesture Recognition
Goussies, Norberto Adrián
Gesture Recognition
title_short Transfer Learning Decision Forests for Gesture Recognition
title_full Transfer Learning Decision Forests for Gesture Recognition
title_fullStr Transfer Learning Decision Forests for Gesture Recognition
title_full_unstemmed Transfer Learning Decision Forests for Gesture Recognition
title_sort Transfer Learning Decision Forests for Gesture Recognition
dc.creator.none.fl_str_mv Goussies, Norberto Adrián
Ubalde, Sebastián
Mejail, Marta Estela
author Goussies, Norberto Adrián
author_facet Goussies, Norberto Adrián
Ubalde, Sebastián
Mejail, Marta Estela
author_role author
author2 Ubalde, Sebastián
Mejail, Marta Estela
author2_role author
author
dc.subject.none.fl_str_mv Gesture Recognition
topic Gesture Recognition
purl_subject.fl_str_mv https://purl.org/becyt/ford/1.2
https://purl.org/becyt/ford/1
dc.description.none.fl_txt_mv Decision forests are an increasingly popular tool in computer vision problems. Their advantages include high computational efficiency, state-of-the-art accuracy and multi-class support. In this paper, we present a novel method for transfer learning which uses decision forests, and we apply it to recognize gestures and characters. We introduce two mechanisms into the decision forest framework in order to transfer knowledge from the source tasks to a given target task. The first one is mixed information gain, which is a data-based regularizer. The second one is label propagation, which infers the manifold structure of the feature space. We show that both of them are important to achieve higher accuracy. Our experiments demonstrate improvements over traditional decision forests in the ChaLearn Gesture Challenge and MNIST data set. They also compare favorably against other state-of-the-art classifiers.
Fil: Goussies, Norberto Adrián. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Departamento de Computación; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina
Fil: Ubalde, Sebastián. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Departamento de Computación; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina
Fil: Mejail, Marta Estela. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Departamento de Computación; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina
description Decision forests are an increasingly popular tool in computer vision problems. Their advantages include high computational efficiency, state-of-the-art accuracy and multi-class support. In this paper, we present a novel method for transfer learning which uses decision forests, and we apply it to recognize gestures and characters. We introduce two mechanisms into the decision forest framework in order to transfer knowledge from the source tasks to a given target task. The first one is mixed information gain, which is a data-based regularizer. The second one is label propagation, which infers the manifold structure of the feature space. We show that both of them are important to achieve higher accuracy. Our experiments demonstrate improvements over traditional decision forests in the ChaLearn Gesture Challenge and MNIST data set. They also compare favorably against other state-of-the-art classifiers.
publishDate 2014
dc.date.none.fl_str_mv 2014
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_6501
info:ar-repo/semantics/articulo
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/11336/33149
Goussies, Norberto Adrián; Ubalde, Sebastián; Mejail, Marta Estela; Transfer Learning Decision Forests for Gesture Recognition ; Microtome; Journal of Machine Learning Research; 15; 2014; 3847−3870
1532-4435
1533-7928
CONICET Digital
CONICET
url http://hdl.handle.net/11336/33149
identifier_str_mv Goussies, Norberto Adrián; Ubalde, Sebastián; Mejail, Marta Estela; Transfer Learning Decision Forests for Gesture Recognition ; Microtome; Journal of Machine Learning Research; 15; 2014; 3847−3870
1532-4435
1533-7928
CONICET Digital
CONICET
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/url/http://jmlr.org/papers/v15/goussies14a.html
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
https://creativecommons.org/licenses/by-nc-nd/2.5/ar/
eu_rights_str_mv openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by-nc-nd/2.5/ar/
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Microtome
publisher.none.fl_str_mv Microtome
dc.source.none.fl_str_mv reponame:CONICET Digital (CONICET)
instname:Consejo Nacional de Investigaciones Científicas y Técnicas
reponame_str CONICET Digital (CONICET)
collection CONICET Digital (CONICET)
instname_str Consejo Nacional de Investigaciones Científicas y Técnicas
repository.name.fl_str_mv CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicas
repository.mail.fl_str_mv dasensio@conicet.gov.ar; lcarlino@conicet.gov.ar
_version_ 1842980756390936576
score 12.993085

Publicaciones similares