Inhalt

[ 921INSYMSRK13 ] KV (*)Multimedia Search and Retrieval

Versionsauswahl
(*) Leider ist diese Information in Deutsch nicht verfügbar.
Workload Ausbildungslevel Studienfachbereich VerantwortlicheR Semesterstunden Anbietende Uni
4,5 ECTS M1 - Master 1. Jahr Informatik Markus Schedl 3 SSt Johannes Kepler Universität Linz
Detailinformationen
Quellcurriculum Masterstudium Computer Science 2021W
Ziele (*)This course enables students to understand and apply basic methods of multimedia processing and analysis, aimed at building multimedia search and retrieval systems. At the end of the course, students will be capable of

  • extracting textual features from multimedia data
  • extracting audio/music features from multimedia data
  • extracting image and video features from multimedia data
  • analyzing multimedia data using statistical and exploratory methods
  • fusing multimodal representations using early and late fusion
  • building search and retrieval systems for multimedia repositories
Lehrinhalte (*)We will first discuss the most important types of multimedia data (text, audio/music, image, video) individually, focusing on particularities of each modality and on aspects of feature extraction. Subsequently, strategies to fuse the individual, single-modal representations (using early and late fusion) will be elaborated. Methods to analyze the extracted features will be discussed, in particular methods of linear and non-linear data analysis for pattern discovery and visual analytics. In the practical part, students will work on a multimedia retrieval task (e.g., content-based result diversification).
Beurteilungskriterien (*)written exam, practical exercise(s)
Lehrmethoden (*)lectures, practical exercise(s)
Abhaltungssprache Englisch
Literatur (*)slides, scientific papers
Lehrinhalte wechselnd? Nein
Präsenzlehrveranstaltung
Teilungsziffer -
Zuteilungsverfahren Direktzuteilung