Informedia at TRECVID 2003 Analyzing and searching broadcast news video.pdf

Informedia at TRECVID 2003: Analyzing and Searching Broadcast News Video1 A. Hauptmann, R.V. Baron, M.-Y. Chen, M. Christel, P. Duygulu, C. Huang, R. Jin, W.-H. Lin, T. Ng, N. Moraveji, N. Papernick, C.G.M. Snoek, G. Tzanetakis, J. Yang, R. Yan, and H.D. Wactlar 1 Overview 1.1 Semantic Classifiers We submitted a number of semantic classifiers, most of which were merely trained on keyframes. We also experimented with runs of classifiers were trained exclusively on text data and relative time within the video, while a few were trained using all available multiple modalities. 1.2 Interactive search This year, we submitted two runs using different versions of the Informedia systems. In one run, a version identical to last years interactive system was used by five researchers, who split up the topics between themselves. The system interface emphasizes text queries, allowing search across ASR, closed captions and OCR text. The result set can then be manipulated through: ? storyboards of images spanning across video story segments ? emphasizing matching shots to a user’s query to reduce the image count to a manageable size ? resolution and layout under user control ? additional filtering provided through shot classifiers such as outdoors, and shots with people, etc. ? display of filter count and distribution to guide their use in manipulating storyboard views. In the best-performing interactive run, for all topics a single researcher used an improved version of the system, which allowed more effective browsing and visualization of the results of text queries using a variety of filter strategies. The improvements made included a magnifying lens on the keyframe under mouse focus in the storyboard, simplified classifier filter access and use, and a browsing interface to browse the top-ranked shots according to the different classifiers. Color and texture based image search engines were also optimized for better performance. 1.3 Manual search Our