Graph Convolutional Networks based on manifold learning for semi-supervised image classification

LP Valem, DCG Pedronette, LJ Latecki - Computer Vision and Image …, 2023 - Elsevier
Due to a huge volume of information in many domains, the need for classification methods is
imperious. In spite of many advances, most of the approaches require a large amount of …

Rank flow embedding for unsupervised and semi-supervised manifold learning

LP Valem, DCG Pedronette… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Impressive advances in acquisition and sharing technologies have made the growth of
multimedia collections and their applications almost unlimited. However, the opposite is true …

Weakly supervised classification through manifold learning and rank-based contextual measures

JGC Presotto, LP Valem, NG de Sá, DCG Pedronette… - Neurocomputing, 2024 - Elsevier
Over the last decade, significant advances have been achieved by machine learning
approaches, notably in supervised learning scenarios. Supported by the advent of deep …

Weakly supervised learning based on hypergraph manifold ranking

JGC Presotto, SF dos Santos, LP Valem… - Journal of Visual …, 2022 - Elsevier
Significant challenges still remain despite the impressive recent advances in machine
learning techniques, particularly in multimedia data understanding. One of the main …

Contextual similarity learning for image retrieval and classification: applications in person re-identification

LP Valem - 2024 - repositorio.unesp.br
The exponential growth of image collections has demanded a significant increase in the use
of machine learning and image retrieval applications across various scenarios. Despite the …

NecklaceFIR: A Large Volume Benchmarked Necklace Dataset for Fashion Image Retrieval

SM Islam, S Joardar, AA Sekh - International Symposium on Artificial …, 2022 - Springer
In this paper, we present a new necklace dataset related to the fashion domain, namely,
NecklaceFIR. In recent years, the retrieval of clothing items has attracted a lot of attention …

Métodos de aprendizado de máquina fracamente supervisionados baseados em ranqueamento

JGC Presotto - 2021 - repositorio.unesp.br
Apesar dos impressionantes avanços recentes nas técnicas de aprendizado de máquina,
principalmente na compreensão de dados multimídia, desafios significativos ainda …