Semantically enabled exploratory video search
Proceedings of the 3rd International Semantic Search Workshop
Towards exploratory video search using linked data
Multimedia Tools and Applications
| Hi-index | 0.00 |
In this paper we describe the current performance of our MediaMill system as presented in the TRECVID 2006 benchmark for video search engines. The MediaMill team participated in two tasks: concept detection and search. For concept detection we use the MediaMill Challenge as ex- perimental platform. The MediaMill Challenge divides the generic video indexing problem into a visual-only, textual- only, early fusion, late fusion, and combined analysis ex- periment. We provide a baseline implementation for each experiment together with baseline results. We extract im- age features, on global, regional, and keypoint level, which we combine with various supervised learners. A late fusion approach of visual-only analysis methods using geometric mean was our most successful run. With this run we con- quer the Challenge baseline by more than 50%. Our con- cept detection experiments have resulted in the best score for three concepts: i.e. desert, flag us, and charts. What is more, using LSCOM annotations, our visual-only approach generalizes well to a set of 491 concept detectors. To han- dle such a large thesaurus in retrieval, an engine is devel- oped which allows users to select relevant concept detectors based on interactive browsing using advanced visualiza- tions. Similar to previous years our best interactive search runs yield top performance, ranking 2nd and 6th overall.