Manifold information through neighbor embedding projection for image retrieval

Registro completo de metadados
MetadadosDescriçãoIdioma
Autor(es): dc.contributorUniversidade Estadual Paulista (UNESP)-
Autor(es): dc.contributorWageningen University and Research-
Autor(es): dc.contributorNorwegian University of Science and Technology-
Autor(es): dc.creatorLeticio, Gustavo Rosseto-
Autor(es): dc.creatorKawai, Vinicius Sato-
Autor(es): dc.creatorValem, Lucas Pascotti-
Autor(es): dc.creatorPedronette, Daniel Carlos Guimarães-
Autor(es): dc.creatorda S. Torres, Ricardo-
Data de aceite: dc.date.accessioned2025-08-21T15:29:01Z-
Data de disponibilização: dc.date.available2025-08-21T15:29:01Z-
Data de envio: dc.date.issued2025-04-29-
Data de envio: dc.date.issued2024-07-01-
Fonte completa do material: dc.identifierhttp://dx.doi.org/10.1016/j.patrec.2024.04.022-
Fonte completa do material: dc.identifierhttps://hdl.handle.net/11449/305202-
Fonte: dc.identifier.urihttp://educapes.capes.gov.br/handle/11449/305202-
Descrição: dc.descriptionAlthough studied for decades, constructing effective image retrieval remains an open problem in a wide range of relevant applications. Impressive advances have been made to represent image content, mainly supported by the development of Convolution Neural Networks (CNNs) and Transformer-based models. On the other hand, effectively computing the similarity between such representations is still challenging, especially in collections in which images are structured in manifolds. This paper introduces a novel solution to this problem based on dimensionality reduction techniques, often used for data visualization. The key idea consists in exploiting the spatial relationships defined by neighbor embedding data visualization methods, such as t-SNE and UMAP, to compute a more effective distance/similarity measure between images. Experiments were conducted on several widely-used datasets. Obtained results indicate that the proposed approach leads to significant gains in comparison to the original feature representations. Experiments also indicate competitive results in comparison with state-of-the-art image retrieval approaches.-
Descrição: dc.descriptionMicrosoft Research-
Descrição: dc.descriptionPetrobras-
Descrição: dc.descriptionDepartment of Statistics Applied Mathematics and Computing State University of São Paulo (UNESP)-
Descrição: dc.descriptionAgricultural Biosystems Engineering and Wageningen Data Competence Center Wageningen University and Research-
Descrição: dc.descriptionDepartment of ICT and Natural Sciences Norwegian University of Science and Technology-
Descrição: dc.descriptionDepartment of Statistics Applied Mathematics and Computing State University of São Paulo (UNESP)-
Descrição: dc.descriptionMicrosoft Research: #105116-
Descrição: dc.descriptionPetrobras: #2023/00095-3-
Formato: dc.format17-25-
Idioma: dc.languageen-
Relação: dc.relationPattern Recognition Letters-
???dc.source???: dc.sourceScopus-
Palavras-chave: dc.subjectData visualization-
Palavras-chave: dc.subjectDimensionality reduction-
Palavras-chave: dc.subjectImage retrieval-
Palavras-chave: dc.subjectt-SNE-
Palavras-chave: dc.subjectUMAP-
Título: dc.titleManifold information through neighbor embedding projection for image retrieval-
Tipo de arquivo: dc.typelivro digital-
Aparece nas coleções:Repositório Institucional - Unesp

Não existem arquivos associados a este item.