Marcos de Souza Oliveira
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Marcos de Souza Oliveira has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Francisco de Assis Tenorio de Carvalho
Univ Fed Pernambuco, Ctr Informat, Av Jornalista Anibal Fernandes S-N,Cidade Univ, BR-50740560 Recife, PE, Brazil
2 shared publications - Sérgio Ricardo de Melo Queiroz
UFPE
2 shared publications - Alan Dasilva
Department of Statistics Universidade de Brasília Brasília Brazil
1 shared publication - André Perrotta
University of Coimbra, CISUC/LASI – Centre for Informatics and Systems of the University of Coimbra, Department of Informatics Engineering, Portugal
1 shared publication - António César Silva Ferreira
Escola Superior de Biotecnologia, Universidade Católica Portuguesa, 4200-072 Porto, Portugal
1 shared publication - Armin Gharibi
Department of Information Engineering, University of Pisa, 56123 Pisa, Italy
1 shared publication
Latest Publications
- Open Access
- 18 June 2026
- Published by Springer Nature in Research Square
Unsupervised Representation Learning for Surface Variability Discovery in Natural Cork Stoppers
Quality control of natural cork stoppers is essential in the wine industry, as aesthetic grading dictates market value. Current pricing relies heavily on visual quality, defining market classes ranging from premium “flor” to low-grade “quintos”. While traditional manual inspection is subjective, the application of supervised learning is strictly hindered by the high natural heterogeneity of cork and the unreliability of subjective ground-truth labels. To address this, we shift from rigid classification to an exploratory data analysis approach, proposing an unsupervised representation learning framework based on a Vision Transformer Autoencoder (ViTAE). The model leverages transformer-based feature extraction to obtain rich, multiview embeddings of cork surfaces. Evaluated on a large-scale industrial dataset (80,000 training and 40,000 test samples), the ViTAE latent space was compared against handcrafted descriptors (LBP and HOG) and autoencoder baselines (CAE and VAE). Performance was assessed via internal clustering metrics, statistical significance tests, and computational feasibility for real-time inspection. Results demonstrate that while classical descriptors like HOG produce statistically compact clusters, ViTAE yields a robust feature space with a critical operational advantage: spatial interpretability. Through image reconstruction, ViTAE acts as a visual auditing tool, where the reconstruction behavior naturally highlights atypical structural variations. This establishes ViTAE not merely as an automated classifier, but as a highly descriptive feature extractor capable of mapping raw material variability to support human-in-the-loop quality assessment systems.
- 18 June 2026
- Published by Springer Nature in Research Square
Open AccessUnsupervised Representation Learning for Surface Variability Discovery in Natural Cork Stoppers
Quality control of natural cork stoppers is essential in the wine industry, as aesthetic grading dictates market value. Current pricing relies heavily on visual quality, defining market classes ranging from premium “flor” to low-grade “quintos”. While traditional manual inspection is subjective, the application of supervised learning is strictly hindered by the high natural heterogeneity of cork and the unreliability of subjective ground-truth labels. To address this, we shift from rigid classification to an exploratory data analysis approach, proposing an unsupervised representation learning framework based on a Vision Transformer Autoencoder (ViTAE). The model leverages transformer-based feature extraction to obtain rich, multiview embeddings of cork surfaces. Evaluated on a large-scale industrial dataset (80,000 training and 40,000 test samples), the ViTAE latent space was compared against handcrafted descriptors (LBP and HOG) and autoencoder baselines (CAE and VAE). Performance was assessed via internal clustering metrics, statistical significance tests, and computational feasibility for real-time inspection. Results demonstrate that while classical descriptors like HOG produce statistically compact clusters, ViTAE yields a robust feature space with a critical operational advantage: spatial interpretability. Through image reconstruction, ViTAE acts as a visual auditing tool, where the reconstruction behavior naturally highlights atypical structural variations. This establishes ViTAE not merely as an automated classifier, but as a highly descriptive feature extractor capable of mapping raw material variability to support human-in-the-loop quality assessment systems.
- 8 July 2025
- Published by Elsevier in Neurocomputing
- Vol. 650
Deep contrastive variational subspace clustering
- 8 July 2025
- Published by Elsevier in Neurocomputing
- Vol. 650
Deep contrastive variational subspace clustering
- 12 August 2023
- Published by Elsevier in Future Generation Computer Systems
- Vol. 149, 622-636
FastAiAlloc: A real-time multi-resources allocation framework proposal based on predictive model and multiple optimization strategies
- 12 August 2023
- Published by Elsevier in Future Generation Computer Systems
- Vol. 149, 622-636
FastAiAlloc: A real-time multi-resources allocation framework proposal based on predictive model and multiple optimization strategies