TREC video retrieval evaluation: a case study and status report

Abstract

The TREC Video Retrieval Evaluation is a multiyear, international effort, funded by the US Advanced Research and Development Agency (ARDA) and the National Institute of Standards and Technology (NIST) to promote progress in content-based retrieval from digital video via open, metrics-based evaluation. Now beginning its fourth year, it aims over time to develop both a better understanding of how systems can effectively accomplish such retrieval and how one can reliably benchmark their performance. This paper can be seen as a case study in the development of video retrieval systems and their evaluation as well as a report on their status to-date. After an introduction to the evolution of the evaluation over the past three years, the paper reports on the most recent evaluation TRECVID 2003: the evaluation framework — the 4 tasks (shot boundary determination, high-level feature extraction, story segmentation and typing, search), 133 hours of US television news data, and measures —, the results, and the approaches taken by the 24 participating groups.