Augmented Segmentation and Visualization for Presentation Videos

Simple item page
dc.creatorHaubold, Alexander
dc.creatorKender, John R.
dc.date2005-01-20
dc.date.accessioned2026-07-07T03:22:22Z
dc.date.available2026-07-07T03:22:22Z
dc.descriptionWe investigate methods of segmenting, visualizing, and indexing presentation videos by separately considering audio and visual data. The audio track is segmented by speaker, and augmented with key phrases which are extracted using an Automatic Speech Recognizer (ASR). The video track is segmented by visual dissimilarities and augmented by representative key frames. An interactive user interface combines a visual representation of audio, video, text, and key frames, and allows the user to navigate a presentation video. We also explore clustering and labeling of speaker data and present preliminary results.
dc.identifierhttps://arxiv.org/abs/cs/0501044
dc.identifierhttp://arxiv.org/abs/cs/0501044
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/32571
dc.subjectMultimedia
dc.subjectInformation Retrieval
dc.subjectH.2.4;H.3.1
dc.titleAugmented Segmentation and Visualization for Presentation Videos
dc.typetext

Files

Collections

arXiv