Abstract
We describe a new system for searching video databases us- ing free-hand sketched queries. Our query sketches depict both object appearance and motion, and are annotated with keywords that indicate the semantic category of each object. We parse space-time volumes from video to form graph rep- resentation, which we match to sketches under a Markov Random Field (MRF) optimization. The MRF energy func- tion is used to rank videos for relevance and contains unary, pairwise and higher-order potentials that reflect the colour, shape, motion and type of sketched objects. We evaluate performance over a dataset of 500 sports footage clips.