Randomized Autoencoder-based Representation for Dynamic Texture Recognition

Registro completo de metadados
MetadadosDescriçãoIdioma
Autor(es): dc.contributorUniversidade Estadual Paulista (UNESP)-
Autor(es): dc.creatorFares, Ricardo T.-
Autor(es): dc.creatorRibas, Lucas C.-
Data de aceite: dc.date.accessioned2025-08-21T15:21:58Z-
Data de disponibilização: dc.date.available2025-08-21T15:21:58Z-
Data de envio: dc.date.issued2025-04-29-
Data de envio: dc.date.issued2023-12-31-
Fonte completa do material: dc.identifierhttp://dx.doi.org/10.1109/IWSSIP62407.2024.10634031-
Fonte completa do material: dc.identifierhttps://hdl.handle.net/11449/301103-
Fonte: dc.identifier.urihttp://educapes.capes.gov.br/handle/11449/301103-
Descrição: dc.descriptionThis paper proposes a single-parameter spatio-temporal representation for dynamic texture recognition using statistical measures of the decoder's learned weights of Randomized Autoencoders (RAE) applied across three orthogonal planes. Firstly, for each orthogonal plane, a randomized autoencoder is applied to each frame to extract discriminating features. Following this, the decoder's learned weights for each frame are vertically concatenated, and statistical measures, namely average, standard deviation, and skewness, are applied to create three partial descriptors. Thus, our proposed spatio-temporal representation is constructed by replicating this procedure across each orthogonal plane XY, XT, and YT, and merging the partial feature descriptors, to capture both appearance and motion characteristics. The proposed representation was evaluated on four benchmarks to demonstrate its robustness and effectiveness on dynamic texture recognition, achieving high accuracies, on the UCLA-50, UCLA-9, UCLA-8, and DynTex++ benchmarks. Finally, the achieved results evidence a highly discriminating and robust dynamic texture descriptor using randomized autoencoders and statistical measures for weight summarization. This approach shows its potential and an important contribution to the field of dynamic texture analysis.-
Descrição: dc.descriptionSão Paulo State University (UNESP) Institute of Biosciences Humanities and Exact Sciences-
Descrição: dc.descriptionSão Paulo State University (UNESP) Institute of Biosciences Humanities and Exact Sciences-
Idioma: dc.languageen-
Relação: dc.relationInternational Conference on Systems, Signals, and Image Processing-
???dc.source???: dc.sourceScopus-
Palavras-chave: dc.subjectDynamic texture analysis-
Palavras-chave: dc.subjectRandomized autoencoders-
Palavras-chave: dc.subjectRepresentation learning-
Título: dc.titleRandomized Autoencoder-based Representation for Dynamic Texture Recognition-
Tipo de arquivo: dc.typeaula digital-
Aparece nas coleções:Repositório Institucional - Unesp

Não existem arquivos associados a este item.