Weakly supervised learning based on hypergraph 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.contributorUniversidade Federal de São Carlos (UFSCar)-
Autor(es): dc.creatorPresotto, João Gabriel Camacho-
Autor(es): dc.creatordos Santos, Samuel Felipe-
Autor(es): dc.creatorValem, Lucas Pascotti-
Autor(es): dc.creatorFaria, Fabio Augusto-
Autor(es): dc.creatorPapa, João Paulo-
Autor(es): dc.creatorAlmeida, Jurandy-
Autor(es): dc.creatorPedronette, Daniel Carlos Guimarães-
Data de aceite: dc.date.accessioned2025-08-21T22:31:57Z-
Data de disponibilização: dc.date.available2025-08-21T22:31:57Z-
Data de envio: dc.date.issued2023-07-29-
Data de envio: dc.date.issued2023-07-29-
Data de envio: dc.date.issued2022-10-31-
Fonte completa do material: dc.identifierhttp://dx.doi.org/10.1016/j.jvcir.2022.103666-
Fonte completa do material: dc.identifierhttp://hdl.handle.net/11449/249306-
Fonte: dc.identifier.urihttp://educapes.capes.gov.br/handle/11449/249306-
Descrição: dc.descriptionSignificant challenges still remain despite the impressive recent advances in machine learning techniques, particularly in multimedia data understanding. One of the main challenges in real-world scenarios is the nature and relation between training and test datasets. Very often, only small sets of coarse-grained labeled data are available to train models, which are expected to be applied on large datasets and fine-grained tasks. Weakly supervised learning approaches handle such constraints by maximizing useful training information in labeled and unlabeled data. In this research direction, we propose a weakly supervised approach that analyzes the dataset manifold to expand the available labeled set. A hypergraph manifold ranking algorithm is exploited to represent the contextual similarity information encoded in the unlabeled data and identify strong similarity relations, which are taken as a path to label expansion. The expanded labeled set is subsequently exploited for a more comprehensive and accurate training process. The proposed model was evaluated jointly with supervised and semi-supervised classifiers, including Graph Convolutional Networks. The experimental results on image and video datasets demonstrate significant gains and accurate results for different classifiers in diverse scenarios.-
Descrição: dc.descriptionMicrosoft Research-
Descrição: dc.descriptionPetrobras-
Descrição: dc.descriptionFundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)-
Descrição: dc.descriptionConselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)-
Descrição: dc.descriptionDepartment of Statistics Applied Mathematics and Computing State University of São Paulo (UNESP), Av. 24-A, 1515-
Descrição: dc.descriptionInstitute of Science and Technology Federal University of São Paulo (UNIFESP)-
Descrição: dc.descriptionSchool of Sciences State University of São Paulo (UNESP)-
Descrição: dc.descriptionDepartment of Computing Federal University of São Carlos (UFSCAR)-
Descrição: dc.descriptionDepartment of Statistics Applied Mathematics and Computing State University of São Paulo (UNESP), Av. 24-A, 1515-
Descrição: dc.descriptionSchool of Sciences State University of São Paulo (UNESP)-
Descrição: dc.descriptionPetrobras: #2017/ 00285-6-
Descrição: dc.descriptionFAPESP: #2017/25908-6-
Descrição: dc.descriptionFAPESP: #2018/15597-6-
Descrição: dc.descriptionFAPESP: #2018/23908-1-
Descrição: dc.descriptionFAPESP: #2019/ 04754-6-
Descrição: dc.descriptionFAPESP: #2020/11366-0-
Descrição: dc.descriptionCNPq: #309439/2020-5-
Descrição: dc.descriptionCNPq: #314868/2020-8-
Descrição: dc.descriptionCNPq: #422667/2021-8-
Idioma: dc.languageen-
Relação: dc.relationJournal of Visual Communication and Image Representation-
???dc.source???: dc.sourceScopus-
Palavras-chave: dc.subjectHypergraph-
Palavras-chave: dc.subjectManifold learning-
Palavras-chave: dc.subjectRanking-
Palavras-chave: dc.subjectWeakly supervised learning-
Título: dc.titleWeakly supervised learning based on hypergraph manifold ranking-
Tipo de arquivo: dc.typelivro digital-
Aparece nas coleções:Repositório Institucional - Unesp

Não existem arquivos associados a este item.