Abstract: Image captioning comprises a crucial interdisciplinary field between computer vision and natural language processing (NLP) in which text descriptions are produced with the help of images.

The project explores multiple machine learning approaches including traditional ML models (Logistic Regression, SVM, Naive Bayes) and ensemble methods (Random Forest, XGBoost, Voting Classifier).

Abstract: Cross-scene hyperspectral image classification (HSIC) is limited by domain shift and the paucity of labeled samples. Although dual-classifier domain adaptation methods have achieved good ...