BLIP-2 is a system which can create image captions from pictures. CLIP is a system which can compare captions to pictures allowing us to choose images from a dataset based on how well the captions match. This project is intended to look more deeply at this field and compare this approach to other image retrieval approaches.
The concept for this project is drawn from the paper “Caption-Matching: A Multimodal Approach for Cross-Domain Image Retrieval” from VISAPP 2026 (See SciTePress – Publication Details).
Details of how I run projects are available at https://www.scss.tcd.ie/Kenneth.Dawson-Howe/Projects/project_details.php
Please note that I will be only supervised 3-4 projects in total this year.