Abstract

This paper begins by considering a number of important design questions for a web-scale, widely available, multimedia test collection intended to support long-term scientific evaluation and comparison of content-based video analysis and exploitation systems. Such exploitation systems would include the kinds of functionality already explored within the annual TRECVid benchmarking activity such as search, semantic concept detection, and automatic summarisation. We then report on our progress in creating such a multimedia collection which we believe to be web scale and which will support a next generation of benchmarking activities for content-based video operations, and we report on our plans for how we intend to put this collection, the IACC.1 collection, to use.