This book constitutes extended and revised versions of selected papers from the 14th International Conference on Pattern Recognition Applications and Methods, ICPRAM 2025, held in Porto, Portugal, during February 23-25, 2025.
The 7 full papers and 4 short papers presented in this book were carefully reviewed and selected from 132 submissions. They were organized into the following topical sections: Theory and Methods; Applications.
Table of Contents:
.- Theory and Methods.
.- ImageNet Accuracy and Model Popularity Don’t Always Select the Best Pretrained Model for Transfer Learning.
.- Meta-Learned Implicit Neural Representations for Scalable and Fast Hyperspectral Image Compression.
.- Beyond the Pixels: Robust Cattle Segmentation for Enhanced Livestock Monitoring.
.- XPD-MelVAE: A Hybrid Conditional β-VAE and ML Framework for Explainable Early Parkinson’s Disease Detection from Mel-Spectrograms.
.- Generative Sparse Data Augmentation Dealing with Performance Evaluation.
.- Sparse Machine Learning Models for Predicting Malnutrition in Children Under Five.
.- Principal Direction-Based 2-Gaussian Fitting Method.
.- On the Use of Union and Intersection for K-Fold Feature Selection.
.- Applications.
.- Multi-Object 2DGS: Occlusion-Robust Background Removal for Multiple Object Models.
.- Enhancing Real-Time Object Detection on NVIDIA Jetson Nano via Class-Specific Dataset Splitting for YOLO Models.
.- Spatio-Temporal Transformers for Long-Term NDVI Forecasting.
