PyUDLF: A Python Framework for Unsupervised Distance Learning Tasks

Registro completo de metadados
MetadadosDescriçãoIdioma
Autor(es): dc.contributorUniversidade Estadual Paulista (UNESP)-
Autor(es): dc.creatorLeticio, Gustavo-
Autor(es): dc.creatorValem, Lucas Pascotti-
Autor(es): dc.creatorLopes, Leonardo Tadeu-
Autor(es): dc.creatorPedronette, Daniel Carlos Guimarães-
Data de aceite: dc.date.accessioned2025-08-21T19:07:28Z-
Data de disponibilização: dc.date.available2025-08-21T19:07:28Z-
Data de envio: dc.date.issued2025-04-29-
Data de envio: dc.date.issued2023-10-25-
Fonte completa do material: dc.identifierhttp://dx.doi.org/10.1145/3581783.3613466-
Fonte completa do material: dc.identifierhttps://hdl.handle.net/11449/310012-
Fonte: dc.identifier.urihttp://educapes.capes.gov.br/handle/11449/310012-
Descrição: dc.descriptionThe representation of multimedia content experienced tremendous advances in the last decades. Mainly supported by deep learning models, impressive results have been obtained. However, despite such advances in representation, the definition of similarity has been neglected. Effectively computing the similarity between representations remains a challenge. Traditional distance functions, such as the Euclidean distance, are not able to properly consider the relevant similarity information encoded in the dataset manifold. In fact, manifolds are essential to perception in many scenarios, such that exploiting the underlying structure of dataset manifolds plays a central role in multimedia content understanding and retrieval. In this paper, we present a framework for unsupervised distance learning which provides easy and uniform access to methods capable of considering the dataset manifold for redefining similarity. Such methods perform context-sensitive similarity learning based on more global measures, capable of improving the effectiveness of retrieval and machine learning tasks. The framework can use distance, similarity, or ranking information both as input and output and compute traditional retrieval effectiveness measures. Implemented as a wrapper in Python, the framework allows integration with a large number of Python libraries while keeping a back-end in C++ for efficiency. The paper also discusses diverse applications of the methods available in the pyUDLF framework, including image re-ranking, video retrieval, person re-ID, and pre-processing of distance measurements for clustering and classification.-
Descrição: dc.descriptionPetrobras-
Descrição: dc.descriptionSão Paulo State University (UNESP), SP-
Descrição: dc.descriptionSão Paulo State University (UNESP), SP-
Descrição: dc.descriptionPetrobras: 2023/00095-3-
Formato: dc.format9680-9684-
Idioma: dc.languageen-
Relação: dc.relationMM 2023 - Proceedings of the 31st ACM International Conference on Multimedia-
???dc.source???: dc.sourceScopus-
Palavras-chave: dc.subjectdistance learning-
Palavras-chave: dc.subjectframework-
Palavras-chave: dc.subjectmultimedia retrieval-
Palavras-chave: dc.subjectunsupervised-
Título: dc.titlePyUDLF: A Python Framework for Unsupervised Distance Learning Tasks-
Tipo de arquivo: dc.typeaula digital-
Aparece nas coleções:Repositório Institucional - Unesp

Não existem arquivos associados a este item.