Representation Learning for Image Retrieval through 3D CNN and Manifold Ranking

Registro completo de metadados
MetadadosDescriçãoIdioma
Autor(es): dc.contributorUniversidade Estadual Paulista (UNESP)-
Autor(es): dc.contributorUniversidade de São Paulo (USP)-
Autor(es): dc.creatorDe Almeida, Lucas Barbosa-
Autor(es): dc.creatorPereira-Ferrero, Vanessa Helena-
Autor(es): dc.creatorValem, Lucas Pascotti-
Autor(es): dc.creatorAlmeida, Jurandy-
Autor(es): dc.creatorPedronette, Daniel Carlos Guimaraes-
Data de aceite: dc.date.accessioned2025-08-21T18:35:56Z-
Data de disponibilização: dc.date.available2025-08-21T18:35:56Z-
Data de envio: dc.date.issued2022-04-29-
Data de envio: dc.date.issued2022-04-29-
Data de envio: dc.date.issued2020-12-31-
Fonte completa do material: dc.identifierhttp://dx.doi.org/10.1109/SIBGRAPI54419.2021.00063-
Fonte completa do material: dc.identifierhttp://hdl.handle.net/11449/230348-
Fonte: dc.identifier.urihttp://educapes.capes.gov.br/handle/11449/230348-
Descrição: dc.descriptionDespite of the substantial success of Convolutional Neural Networks (CNNs) on many recognition and representation tasks, such models are very reliant on huge amount of data to allow effective training. In order to improve the generalization ability of CNNs, several approaches have been proposed, including variations of data augmentation strategies. With the goal of achieving more effective retrieval results on unsupervised learning scenarios, we propose a representation learning approach which exploits a rank-based formulation to build a more comprehensive data representation. The proposed model uses 2D and 3D CNNs trained by transfer learning and fuse both representations through a rank-based formulation based on manifold learning algorithms. Our approach was evaluated on an unsupervised image retrieval scenario applied to action recognition datasets. The experimental results indicated that significant effectiveness gains can be obtained on various datasets, reaching +56.93% of relative gains on MAP scores.-
Descrição: dc.descriptionSão Paulo State University (UNESP) Department of Statistics Applied Math. and Computing (DEMAC)-
Descrição: dc.descriptionFederal University of São Paulo (UNIFESP) Institute of Science and Technology-
Descrição: dc.descriptionSão Paulo State University (UNESP) Department of Statistics Applied Math. and Computing (DEMAC)-
Formato: dc.format417-424-
Idioma: dc.languageen-
Relação: dc.relationProceedings - 2021 34th SIBGRAPI Conference on Graphics, Patterns and Images, SIBGRAPI 2021-
???dc.source???: dc.sourceScopus-
Palavras-chave: dc.subjectimage retrieval-
Palavras-chave: dc.subjectmanifold learning-
Palavras-chave: dc.subjectrepresentation learning-
Título: dc.titleRepresentation Learning for Image Retrieval through 3D CNN and Manifold Ranking-
Tipo de arquivo: dc.typeaula digital-
Aparece nas coleções:Repositório Institucional - Unesp

Não existem arquivos associados a este item.