The emerging field of vision–language models, which combines computer vision and natural
language processing (NLP), has gained significant interest and exploration. This integration …

Vision-language models have emerged as transformative tools, revolutionizing the
integration of visual and textual information, forging pathways for nuanced interpretations …

This paper explores post-disaster analytics using multimodal deep learning models trained
with curriculum learning method. Studying post-disaster analytics is important as it plays a …

Social media aids disaster response but suffers from noise, hindering accurate impact
assessment and decision making for resilient cities, which few studies considered. To …

Today's era follows a data-driven decision process for large-scale environment analysis.
Aerial view-based decision process plays a key role in various domains including …

The Visual Question Answering project described in this work uses a multi-modal approach
that combines Bidirectional Encoder Representations from Transformers for complex natural …

Social media aids disaster response but suffers from noise, hindering accurate impact
assessment and decision making for resilient cities, which few studies considered. To …

Object tracking and recognition are essential tools for advanced autonomous navigation
systems, particularly in Unmanned Aerial Vehicles (UAVs). This project centers around the …