Marcos de Souza Oliveira

Marcos de Souza Oliveira

Auto-generated profile, based on publicly available information

Marcos de Souza Oliveira

University of Coimbra

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
9 July 2022 in Expert Systems with Applications
Verified
Journal Article
Closed access
MOMarcos de S. Oliveira
Marcos de S. Oliveira
SQSergio R. de M. Queiroz
Sergio R. de M. Queiroz
FCFrancisco de A.T. de Carvalho
Francisco de A.T. de Carvalho

8 July 2025 in Neurocomputing
Verified
Journal Article
Closed access
MOMarcos de Souza Oliveira
Marcos de Souza Oliveira
SQSergio R. de M. Queiroz
Sergio R. de M. Queiroz
Cleber ZanchettinCleber Zanchettin
Cleber Zanchettin
FCFrancisco de Assis Tenório de Carvalho
Francisco de Assis Tenório de Carvalho

12 August 2023 in Future Generation Computer Systems
Verified
Journal Article
Closed access
MOMarcos de S. Oliveira
Marcos de S. Oliveira
FJFrancisco Erivaldo Fernandes Junior
Francisco Erivaldo Fernandes Junior
LCLukas Cerveny
Lukas Cerveny
FMFlávia Akemi Miyazaki
Flávia Akemi Miyazaki
LNLeonardo Valeriano Neri
Leonardo Valeriano Neri
ÓLÓrion Darshan Winter de Lima
Órion Darshan Winter de Lima

18 June 2026 in Research Square
Verified
Preprint
Open access
PDF file
MOMarcos de Souza Oliveira
Marcos de Souza Oliveira
AGArmin Gharibi
Armin Gharibi
Jorge C. S. CardosoJorge C. S. Cardoso
Jorge C. S. Cardoso
VFVanessa Fernandes Ferreira
Vanessa Fernandes Ferreira
Ferreira AntonioFerreira Antonio
Ferreira Antonio
LRLicinio Roque
Licinio Roque
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.