Publication: Feature Similarity and Frequency-Based Weighted Visual Words Codebook Learning Scheme for Human Action Recognition
dc.affiliation.dpto | UC3M. Departamento de Informática | es |
dc.affiliation.grupoinv | UC3M. Grupo de Investigación: Inteligencia Artificial Aplicada (GIAA) | es |
dc.contributor.author | Nazir, Saima | |
dc.contributor.author | Yousaf, Muhammad Haroon | |
dc.contributor.author | Velastin Carroza, Sergio Alejandro | |
dc.contributor.funder | European Commission | en |
dc.contributor.funder | Ministerio de EconomÃa y Competitividad (España) | es |
dc.date.accessioned | 2019-10-01T08:57:22Z | |
dc.date.available | 2019-10-01T08:57:22Z | |
dc.date.issued | 2017-11-20 | |
dc.description | This paper has been presented at : 8th Pacific-Rim Symposium, PSIVT 2017. | en |
dc.description.abstract | Human action recognition has become a popular field for computer vision researchers in the recent decade. This paper presents a human action recognition scheme based on a textual information concept inspired by document retrieval systems. Videos are represented using a commonly used local feature representation. In addition, we formulate a new weighted class specific dictionary learning scheme to reflect the importance of visual words for a particular action class. Weighted class specific dictionary learning enriches the scheme to learn a sparse representation for a particular action class. To evaluate our scheme on realistic and complex scenarios, we have tested it on UCF Sports and UCF11 benchmark datasets. This paper reports experimental results that outperform recent state-of-the-art methods for the UCF Sports and the UCF11 dataset i.e. 98.93% and 93.88% in terms of average accuracy respectively. To the best of our knowledge, this contribution is first to apply a weighted class specific dictionary learning method on realistic human action recognition datasets. | en |
dc.description.sponsorship | Sergio A Velastin acknowledges funding by the Universidad Carlos III de Madrid, the European Unions Seventh Framework Programme for research, technological development and demonstration under grant agreement n 600371, el Ministerio de EconomÃa y Competitividad (COFUND2013-51509) and Banco Santander. Authors also acknowledges support from the Directorate of ASR and TD, University of Engineering and Technology Taxila, Pakistan. | en |
dc.format.extent | 11 | |
dc.identifier.bibliographicCitation | Nazir, S., Yousaf, M.H. y Velastin, S.A. (2018). Feature Similarity and Frequency-Based Weighted Visual Words Codebook Learning Scheme for Human Action Recognition. In PSIVT 2017 Image and Video Technology,10749, pp. 326-336. | en |
dc.identifier.isbn | 978-3-319-75786-5 | |
dc.identifier.publicationfirstpage | 326 | |
dc.identifier.publicationlastpage | 336 | |
dc.identifier.publicationtitle | Image and Video Technology PSIVT 2017 | en |
dc.identifier.publicationvolume | 10749 | |
dc.identifier.uri | https://hdl.handle.net/10016/28933 | |
dc.identifier.uxxi | CC/0000029176 | |
dc.language.iso | eng | en |
dc.publisher | Springer | en |
dc.relation.eventdate | 20-24 November 2017 | en |
dc.relation.eventplace | Wuhan, China | en |
dc.relation.eventtitle | 8th Pacific-Rim Symposium on Image and Video Technology (PSIVT) | en |
dc.relation.projectID | info:eu-repo/grantAgreement/EC/PCOFUND-GA-2012-600371 | en |
dc.relation.projectID | Gobierno de España. COFUND2013-51509 | es |
dc.rights | © Springer International Publishing AG, part of Springer Nature 2018 | en |
dc.rights.accessRights | open access | en |
dc.subject.eciencia | Informática | es |
dc.subject.other | Human action recognition | en |
dc.subject.other | Bag of visual words | en |
dc.subject.other | Spatio-temporal features | en |
dc.subject.other | Ucf sports | en |
dc.title | Feature Similarity and Frequency-Based Weighted Visual Words Codebook Learning Scheme for Human Action Recognition | en |
dc.type | conference paper | * |
dc.type.hasVersion | AM | * |
dspace.entity.type | Publication |
Files
Original bundle
1 - 1 of 1