National Institute of Informatics, Japan at TRECVID 2008

This paper reports our experiments for TRECVID 2008 tasks: high level feature extraction, search and contentbased copy detection. For the high level feature extraction task, we use the baseline features such as color moments, edge orientation histogram and local binary patterns with SVM classifiers and nearest neighbor classifiers. For the search task, we use different approaches including search by the baseline features and search by concept suggestion. And for the video copy detection task, we study two approaches that are based on the pattern of motions in feature point trajectories and matches of all frame pairs using normalized cross correlation. Our approaches can be considered as one of the baseline approaches for evaluation of these tasks. I. HIGH LEVEL FEATURE EXTRACTION A. Method Overview In our framework, features are extracted from the input keyframe images representing for shots. We extracted five keyframes per shot that are spaced out equally within the provided shot boun...

• Type: Conference
• Year: 2008
• Where: TRECVID
• Authors: Duy-Dinh Le, Xiaomeng Wu, Shin'ichi Satoh, Sheetal Rajgure, Jan Gemert
• Keywords: Internet Technology, Level Feature Extraction, Nearest Neighbor Classifiers, Output Scores, TRECVID 2008