@inproceedings{36d0f19d6efc4645baaec8745022855a,
title = "Graphical models for multi-modal automatic video editing in meetings",
abstract = "In this work we present a multi-modal video editing system for meetings, which uses graphical models for the segmentation and classification of the video modes. The task of video editing is about selecting the camera, that represents the meeting in the best way out of various available cameras. Therefore a new training structure for graphical models was developed. This is necessary for the learning of boundaries combined with the video mode itself. All developed and known decoding structures can be easily connected for an EM-training to our training structure. The achieved results of the system are state of the art.",
keywords = "Human-machine interaction, Machine learning, Meeting analysis, Multi cameras, Multi-modal low level features",
author = "Benedikt H{\"o}rnier and Dejan Arsi{\'c} and Bj{\"o}rn Schuller and Gerhard Rigoll",
year = "2009",
doi = "10.1109/ICDSP.2009.5201117",
language = "English",
isbn = "9781424432981",
series = "DSP 2009: 16th International Conference on Digital Signal Processing, Proceedings",
publisher = "IEEE Computer Society",
booktitle = "DSP 2009:16th International Conference on Digital Signal Processing, Proceedings",
note = "16th International Conference on Digital Signal Processing, DSP 2009 ; Conference date: 05-07-2009 Through 07-07-2009",
}