TRECVID 2005 - An Overview

TRECVID 2005 represented the fifth running of a TREC-style video retrieval evaluation, the goal of which remained to promote progress in content-based retrieval from digital video via open, metrics-based evaluation. Over time this effort is yielding a better understanding of how systems can effectively accomplish such retrieval and how one can reliably benchmark their performance. TRECVID is funded by the Disruptive Technology Office (DTO) and the National Institute of Standards and Technology (NIST). Forty-two teams from various research organizations — 11 from Asia/Australia, 17 from Europe, 13 from the Americas, and 1 US/EU team — participated in one or more of five tasks: shot boundary determination, low-level feature (camera motion) extraction, high-level feature extraction, search (automatic, manual, interactive) or pre-production video management. Results for the first four tasks were scored by NIST using manually created truth data for shot boundary determination and camera motion detection. Feature and search submissions were evalu-