Fast action detection via discriminative random forest voting and top-K subvolume search

Autores
Yu, Gang; Goussies, Norberto Adrián; Yuan, Junsong; Liu, Zicheng
Año de publicación
2011
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
Multiclass action detection in complex scenes is a challenging problem because of cluttered backgrounds and the large intra-class variations in each type of actions. To achieve efficient and robust action detection, we characterize a video as a collection of spatio-temporal interest points, and locate actions via finding spatio-temporal video subvolumes of the highest mutual information score towards each action class. A random forest is constructed to efficiently generate discriminative votes from individual interest points, and a fast top-K subvolume search algorithm is developed to find all action instances in a single round of search. Without significantly degrading the performance, such a top-K search can be performed on down-sampled score volumes for more efficient localization. Experiments on a challenging MSR Action Dataset II validate the effectiveness of our proposed multiclass action detection method. The detection speed is several orders of magnitude faster than existing methods.
Fil: Yu, Gang. Nanyang Technological University; Singapur
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. Oficina de Coordinación Administrativa Ciudad Universitaria; Argentina
Fil: Yuan, Junsong. Nanyang Technological University; Singapur
Fil: Liu, Zicheng. Microsoft Research; Estados Unidos
Materia
ACTION DETECTION
BRANCH AND BOUND
RANDOM FOREST
TOP-K SEARCH
Nivel de accesibilidad
acceso abierto
Condiciones de uso
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
Repositorio
CONICET Digital (CONICET)
Institución
Consejo Nacional de Investigaciones Científicas y Técnicas
OAI Identificador
oai:ri.conicet.gov.ar:11336/117819

id CONICETDig_53f8ff6fd73891171927affd4b5c5af9
oai_identifier_str oai:ri.conicet.gov.ar:11336/117819
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling Fast action detection via discriminative random forest voting and top-K subvolume searchYu, GangGoussies, Norberto AdriánYuan, JunsongLiu, ZichengACTION DETECTIONBRANCH AND BOUNDRANDOM FORESTTOP-K SEARCHhttps://purl.org/becyt/ford/1.2https://purl.org/becyt/ford/1Multiclass action detection in complex scenes is a challenging problem because of cluttered backgrounds and the large intra-class variations in each type of actions. To achieve efficient and robust action detection, we characterize a video as a collection of spatio-temporal interest points, and locate actions via finding spatio-temporal video subvolumes of the highest mutual information score towards each action class. A random forest is constructed to efficiently generate discriminative votes from individual interest points, and a fast top-K subvolume search algorithm is developed to find all action instances in a single round of search. Without significantly degrading the performance, such a top-K search can be performed on down-sampled score volumes for more efficient localization. Experiments on a challenging MSR Action Dataset II validate the effectiveness of our proposed multiclass action detection method. The detection speed is several orders of magnitude faster than existing methods.Fil: Yu, Gang. Nanyang Technological University; SingapurFil: Goussies, Norberto Adrián. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Departamento de Computación; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria; ArgentinaFil: Yuan, Junsong. Nanyang Technological University; SingapurFil: Liu, Zicheng. Microsoft Research; Estados UnidosInstitute of Electrical and Electronics Engineers2011-06info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/117819Yu, Gang; Goussies, Norberto Adrián; Yuan, Junsong; Liu, Zicheng; Fast action detection via discriminative random forest voting and top-K subvolume search; Institute of Electrical and Electronics Engineers; Ieee Transactions On Multimedia; 13; 3; 6-2011; 507-5171520-9210CONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/url/http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=5730498info:eu-repo/semantics/altIdentifier/doi/10.1109/TMM.2011.2128301info:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by-nc-sa/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2025-09-29T10:10:03Zoai:ri.conicet.gov.ar:11336/117819instacron: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:34982025-09-29 10:10:03.423CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv Fast action detection via discriminative random forest voting and top-K subvolume search
title Fast action detection via discriminative random forest voting and top-K subvolume search
spellingShingle Fast action detection via discriminative random forest voting and top-K subvolume search
Yu, Gang
ACTION DETECTION
BRANCH AND BOUND
RANDOM FOREST
TOP-K SEARCH
title_short Fast action detection via discriminative random forest voting and top-K subvolume search
title_full Fast action detection via discriminative random forest voting and top-K subvolume search
title_fullStr Fast action detection via discriminative random forest voting and top-K subvolume search
title_full_unstemmed Fast action detection via discriminative random forest voting and top-K subvolume search
title_sort Fast action detection via discriminative random forest voting and top-K subvolume search
dc.creator.none.fl_str_mv Yu, Gang
Goussies, Norberto Adrián
Yuan, Junsong
Liu, Zicheng
author Yu, Gang
author_facet Yu, Gang
Goussies, Norberto Adrián
Yuan, Junsong
Liu, Zicheng
author_role author
author2 Goussies, Norberto Adrián
Yuan, Junsong
Liu, Zicheng
author2_role author
author
author
dc.subject.none.fl_str_mv ACTION DETECTION
BRANCH AND BOUND
RANDOM FOREST
TOP-K SEARCH
topic ACTION DETECTION
BRANCH AND BOUND
RANDOM FOREST
TOP-K SEARCH
purl_subject.fl_str_mv https://purl.org/becyt/ford/1.2
https://purl.org/becyt/ford/1
dc.description.none.fl_txt_mv Multiclass action detection in complex scenes is a challenging problem because of cluttered backgrounds and the large intra-class variations in each type of actions. To achieve efficient and robust action detection, we characterize a video as a collection of spatio-temporal interest points, and locate actions via finding spatio-temporal video subvolumes of the highest mutual information score towards each action class. A random forest is constructed to efficiently generate discriminative votes from individual interest points, and a fast top-K subvolume search algorithm is developed to find all action instances in a single round of search. Without significantly degrading the performance, such a top-K search can be performed on down-sampled score volumes for more efficient localization. Experiments on a challenging MSR Action Dataset II validate the effectiveness of our proposed multiclass action detection method. The detection speed is several orders of magnitude faster than existing methods.
Fil: Yu, Gang. Nanyang Technological University; Singapur
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. Oficina de Coordinación Administrativa Ciudad Universitaria; Argentina
Fil: Yuan, Junsong. Nanyang Technological University; Singapur
Fil: Liu, Zicheng. Microsoft Research; Estados Unidos
description Multiclass action detection in complex scenes is a challenging problem because of cluttered backgrounds and the large intra-class variations in each type of actions. To achieve efficient and robust action detection, we characterize a video as a collection of spatio-temporal interest points, and locate actions via finding spatio-temporal video subvolumes of the highest mutual information score towards each action class. A random forest is constructed to efficiently generate discriminative votes from individual interest points, and a fast top-K subvolume search algorithm is developed to find all action instances in a single round of search. Without significantly degrading the performance, such a top-K search can be performed on down-sampled score volumes for more efficient localization. Experiments on a challenging MSR Action Dataset II validate the effectiveness of our proposed multiclass action detection method. The detection speed is several orders of magnitude faster than existing methods.
publishDate 2011
dc.date.none.fl_str_mv 2011-06
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/11336/117819
Yu, Gang; Goussies, Norberto Adrián; Yuan, Junsong; Liu, Zicheng; Fast action detection via discriminative random forest voting and top-K subvolume search; Institute of Electrical and Electronics Engineers; Ieee Transactions On Multimedia; 13; 3; 6-2011; 507-517
1520-9210
CONICET Digital
CONICET
url http://hdl.handle.net/11336/117819
identifier_str_mv Yu, Gang; Goussies, Norberto Adrián; Yuan, Junsong; Liu, Zicheng; Fast action detection via discriminative random forest voting and top-K subvolume search; Institute of Electrical and Electronics Engineers; Ieee Transactions On Multimedia; 13; 3; 6-2011; 507-517
1520-9210
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://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=5730498
info:eu-repo/semantics/altIdentifier/doi/10.1109/TMM.2011.2128301
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
eu_rights_str_mv openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Institute of Electrical and Electronics Engineers
publisher.none.fl_str_mv Institute of Electrical and Electronics Engineers
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_ 1844613985413890048
score 13.070432