We are primarily focused on the intersection of semantics, metadata, knowledge representation and information science. We think deeply about how people describe what they experience visually and how to capture and formalize this knowledge into machine readable structures.
Our research ends up somewhere in the middle of a venn diagram where the fields of embedded metadata, knowledge graphs, and data-centric AI overlap and all examined from a distinctly human-centered perspective.
Most metadata about image description stops at keywords and a caption. Our work goes deeper and seeks to parse out the description itself into structured data.