Marsland, S.: Machine Learning: An Algorithmic Perspective. Master’s thesis, Universität Bremen (2015) Jacob, F.: Ereignis-basierte Analyse von Mediendaten mit Methoden des maschinellen Lernens. ISO 15938–3, International Organization for Standardization (2002) Information technology - multimedia content description interface. Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., Witten, I.H.: The weka data mining software: an update. FIMS Media SOA Framework 1.0Ĭormen, T.H., Leiserson, C.E., Rivest, R.L.: Introduction to Algorithms. Technical report, Advanced Media Workflow Association and European Broadcasting Union (2011).
Framework for interoperable media services (FIMS). This process is experimental and the keywords may be updated as the learning algorithm improves.ĪMWA and EBU. These keywords were added by machine and not by the authors. In addition to that, further results and limitations will be presented. It can be shown, that this objective can be achieved by applying the developed methods.
This will save operator-time in an automated process environment for quality control of audiovisual files. Thus aspects of data mining and media technology will be discussed and combined with the goal to reach a reasonable reduction of the input-set by projecting it on an output-set. After that, per time slot and requested event type, a binary classification will be applied. By using methods of supervised machine learning the two sets of events will be mapped onto each other. On the one hand, these sets of events will be extracted from video files and on the other hand it will be manually annotated. In this work, several approaches to feature extraction on sets of time-based events will be developed and evaluated.
0 kommentar(er)
