Multi-Modal Video Retrieval (PhD Thesis, ongoing)

The objective of this project is to design, develop, and evaluate a retrieval back-end that is able to jointly support a large variety of query types, e.g., keyword queries on manual annotations to videos, query-by-example with images as query objects, query-by-sketch capturing contents of video frames, and/or spatio-temporal motion queries.

Funding Agencies



Research Topics