Unsupervised action proposals using support vector classifiers for online video processing

In this work, we introduce an intelligent video sensor for the problem of Action Proposals (AP). AP consists of localizing temporal segments in untrimmed videos that are likely to contain actions. Solving this problem can accelerate several video action understanding tasks, such as detection, retrie...

Descripción completa

Detalles Bibliográficos
Autores: Baptista Ríos, Marcos, López Sastre, Roberto Javier|||0000-0002-2477-0152, Acevedo Rodríguez, Francisco Javier|||0000-0002-4727-1575, Martín Martín, María del Pilar|||0000-0002-9793-7371, Maldonado Bascón, Saturnino|||0000-0001-6472-5359
Tipo de recurso: artículo
Fecha de publicación:2020
País:España
Institución:Universidad de Alcalá (UAH)
Repositorio:e_Buah Biblioteca Digital Universidad de Alcalá
Idioma:inglés
OAI Identifier:oai:ebuah.uah.es:10017/67458
Acceso en línea:http://hdl.handle.net/10017/67458
https://dx.doi.org/10.3390/s20102953
Access Level:acceso abierto
Palabra clave:Action proposals
Action recognition
Computer vision
Unsupervised learning
Intelligent video sensor
Electrónica
Electronics
id ES_2f090f90accce1bf5f2ae7b56f82d6ee
oai_identifier_str oai:ebuah.uah.es:10017/67458
network_acronym_str ES
network_name_str España
repository_id_str
spelling Unsupervised action proposals using support vector classifiers for online video processingBaptista Ríos, MarcosLópez Sastre, Roberto Javier|||0000-0002-2477-0152Acevedo Rodríguez, Francisco Javier|||0000-0002-4727-1575Martín Martín, María del Pilar|||0000-0002-9793-7371Maldonado Bascón, Saturnino|||0000-0001-6472-5359Action proposalsAction recognitionComputer visionUnsupervised learningIntelligent video sensorElectrónicaElectronicsIn this work, we introduce an intelligent video sensor for the problem of Action Proposals (AP). AP consists of localizing temporal segments in untrimmed videos that are likely to contain actions. Solving this problem can accelerate several video action understanding tasks, such as detection, retrieval, or indexing. All previous AP approaches are supervised and offline, i.e., they need both the temporal annotations of the datasets during training and access to the whole video to effectively cast the proposals. We propose here a new approach which, unlike the rest of the state-of-the-art models, is unsupervised. This implies that we do not allow it to see any labeled data during learning nor to work with any pre-trained feature on the used dataset. Moreover, our approach also operates in an online manner, which can be beneficial for many real-world applications where the video has to be processed as soon as it arrives at the sensor, e.g., robotics or video monitoring. The core of our method is based on a Support Vector Classifier (SVC) module which produces candidate segments for AP by distinguishing between sets of contiguous video frames. We further propose a mechanism to refine and filter those candidate segments. This filter optimizes a learning-to-rank formulation over the dynamics of the segments. An extensive experimental evaluation is conducted on Thumos?14 and ActivityNet datasets, and, to the best of our knowledge, this work supposes the first unsupervised approach on these main AP benchmarks. Finally, we also provide a thorough comparison to the current state-of-the-art supervised AP approaches. We achieve 41% and 59% of the performance of the best-supervised model on ActivityNet and Thumos?14, respectively, confirming our unsupervised solution as a correct option to tackle the AP problem. The code to reproduce all our results will be publicly released upon acceptance of the paper.Agencia Estatal de InvestigaciónUniversidad de AlcaláComunidad de MadridMDPI20202020-05-22journal articlehttp://purl.org/coar/resource_type/c_6501NAhttp://purl.org/coar/version/c_be7fb7dd8ff6fe43info:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10017/67458https://dx.doi.org/10.3390/s20102953reponame:e_Buah Biblioteca Digital Universidad de Alcaláinstname:Universidad de Alcalá (UAH)InglésengAgencia Estatal de Investigación http://dx.doi.org/10.13039/501100011033 Plan Estatal de Investigación Científica y Técnica y de Innovación 2013-2016 TEC2016-80326-R PROCESADO DIGITAL Y RECONOCIMIENTO DE PATRONES PARA AYUDAS TECNICAS A LA DIVERSIDAD FUNCIONALUAH Not available CM-JIN-2019-022UAH Not available CCG2019%2FIA-066Comunidad de Madrid http://dx.doi.org/10.13039/100012818 Not available PEJD-2019-PRE%2FTIC-15519open accesshttp://purl.org/coar/access_right/c_abf2Attribution 4.0 Internationalhttp://creativecommons.org/licenses/by/4.0/info:eu-repo/semantics/openAccessoai:ebuah.uah.es:10017/674582026-06-18T11:13:07Z
dc.title.none.fl_str_mv Unsupervised action proposals using support vector classifiers for online video processing
title Unsupervised action proposals using support vector classifiers for online video processing
spellingShingle Unsupervised action proposals using support vector classifiers for online video processing
Baptista Ríos, Marcos
Action proposals
Action recognition
Computer vision
Unsupervised learning
Intelligent video sensor
Electrónica
Electronics
title_short Unsupervised action proposals using support vector classifiers for online video processing
title_full Unsupervised action proposals using support vector classifiers for online video processing
title_fullStr Unsupervised action proposals using support vector classifiers for online video processing
title_full_unstemmed Unsupervised action proposals using support vector classifiers for online video processing
title_sort Unsupervised action proposals using support vector classifiers for online video processing
dc.creator.none.fl_str_mv Baptista Ríos, Marcos
López Sastre, Roberto Javier|||0000-0002-2477-0152
Acevedo Rodríguez, Francisco Javier|||0000-0002-4727-1575
Martín Martín, María del Pilar|||0000-0002-9793-7371
Maldonado Bascón, Saturnino|||0000-0001-6472-5359
author Baptista Ríos, Marcos
author_facet Baptista Ríos, Marcos
López Sastre, Roberto Javier|||0000-0002-2477-0152
Acevedo Rodríguez, Francisco Javier|||0000-0002-4727-1575
Martín Martín, María del Pilar|||0000-0002-9793-7371
Maldonado Bascón, Saturnino|||0000-0001-6472-5359
author_role author
author2 López Sastre, Roberto Javier|||0000-0002-2477-0152
Acevedo Rodríguez, Francisco Javier|||0000-0002-4727-1575
Martín Martín, María del Pilar|||0000-0002-9793-7371
Maldonado Bascón, Saturnino|||0000-0001-6472-5359
author2_role author
author
author
author
dc.subject.none.fl_str_mv Action proposals
Action recognition
Computer vision
Unsupervised learning
Intelligent video sensor
Electrónica
Electronics
topic Action proposals
Action recognition
Computer vision
Unsupervised learning
Intelligent video sensor
Electrónica
Electronics
description In this work, we introduce an intelligent video sensor for the problem of Action Proposals (AP). AP consists of localizing temporal segments in untrimmed videos that are likely to contain actions. Solving this problem can accelerate several video action understanding tasks, such as detection, retrieval, or indexing. All previous AP approaches are supervised and offline, i.e., they need both the temporal annotations of the datasets during training and access to the whole video to effectively cast the proposals. We propose here a new approach which, unlike the rest of the state-of-the-art models, is unsupervised. This implies that we do not allow it to see any labeled data during learning nor to work with any pre-trained feature on the used dataset. Moreover, our approach also operates in an online manner, which can be beneficial for many real-world applications where the video has to be processed as soon as it arrives at the sensor, e.g., robotics or video monitoring. The core of our method is based on a Support Vector Classifier (SVC) module which produces candidate segments for AP by distinguishing between sets of contiguous video frames. We further propose a mechanism to refine and filter those candidate segments. This filter optimizes a learning-to-rank formulation over the dynamics of the segments. An extensive experimental evaluation is conducted on Thumos?14 and ActivityNet datasets, and, to the best of our knowledge, this work supposes the first unsupervised approach on these main AP benchmarks. Finally, we also provide a thorough comparison to the current state-of-the-art supervised AP approaches. We achieve 41% and 59% of the performance of the best-supervised model on ActivityNet and Thumos?14, respectively, confirming our unsupervised solution as a correct option to tackle the AP problem. The code to reproduce all our results will be publicly released upon acceptance of the paper.
publishDate 2020
dc.date.none.fl_str_mv 2020
2020-05-22
dc.type.none.fl_str_mv journal article
http://purl.org/coar/resource_type/c_6501
NA
http://purl.org/coar/version/c_be7fb7dd8ff6fe43
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv http://hdl.handle.net/10017/67458
https://dx.doi.org/10.3390/s20102953
url http://hdl.handle.net/10017/67458
https://dx.doi.org/10.3390/s20102953
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.relation.none.fl_str_mv Agencia Estatal de Investigación http://dx.doi.org/10.13039/501100011033 Plan Estatal de Investigación Científica y Técnica y de Innovación 2013-2016 TEC2016-80326-R PROCESADO DIGITAL Y RECONOCIMIENTO DE PATRONES PARA AYUDAS TECNICAS A LA DIVERSIDAD FUNCIONAL
UAH Not available CM-JIN-2019-022
UAH Not available CCG2019%2FIA-066
Comunidad de Madrid http://dx.doi.org/10.13039/100012818 Not available PEJD-2019-PRE%2FTIC-15519
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
Attribution 4.0 International
http://creativecommons.org/licenses/by/4.0/
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
Attribution 4.0 International
http://creativecommons.org/licenses/by/4.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv MDPI
publisher.none.fl_str_mv MDPI
dc.source.none.fl_str_mv reponame:e_Buah Biblioteca Digital Universidad de Alcalá
instname:Universidad de Alcalá (UAH)
instname_str Universidad de Alcalá (UAH)
reponame_str e_Buah Biblioteca Digital Universidad de Alcalá
collection e_Buah Biblioteca Digital Universidad de Alcalá
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869405450441588736
score 15,812455

Similares en LA Referencia