Synthetic Data Generation of Body Motion Data by Neural Gas Network for Emotion Recognition
-
Updated
May 14, 2025 - Python
Synthetic Data Generation of Body Motion Data by Neural Gas Network for Emotion Recognition
Synthetic Data Generation for Emotional Depth Faces: Optimizing Conditional DCGANs via Genetic Algorithms in the Latent Space and Stabilizing Training with Knowledge Distillation
Official Code for "Walking the energy lines: Physics-inspired fuzzy self-ensembling for medical image classification" Published at Biomedical Signal Processing and Control Journal
Spectral vision transformer for efficient tokenization with limited data
Fuzzy-MAP EM algorithm presented at the ECAI workoshop HC@AIxIA
Investigated Meta Pseudo Labels for breast cancer CAD. The pipeline failed because the baseline segmentation model could not learn from the extremely limited labeled data. This research demonstrates that it's success is contingent on first establishing a functional supervised model, a step that was ultimately hampered by severe data scarcity
A sports image recognition system developed for the Visual Information Processing and Management 2025-2026 exam. The application uses deep learning models to classify images of different sports, perform similarity searches, and apply image augmentation and enhancement techniques.
A sports image recognition system developed for the Visual Information Processing and Management 2025-2026 exam. The application uses deep learning models to classify images of different sports, perform similarity searches, and apply image augmentation and enhancement techniques.
Add a description, image, and links to the data-scarcity topic page so that developers can more easily learn about it.
To associate your repository with the data-scarcity topic, visit your repo's landing page and select "manage topics."