Wykład dra Matthiasa Zeppelzauera

Zakład Informatyki Stosowanej Instytutu Informatyki i Matematyki Komputerowej zaprasza wszystkich pasjonatów Widzenia komputerowego na wykład dra Matthiasa Zeppelzauera (Uniwersytet w St. Pölten, Austria) pod tytułem "Multimedia Processing – From Ancient Rock Art to Social Web Media", który odbędzie się we środę, 4 czerwca 2014, o godz. 10 w sali 0094.


The processing of multimedia content is a challenging topic that provides a wide range of possible applications. A major challenge lies in the highly heterogeneous characteristics of the underlying data that require specialized treatment in content-based analysis. This talk presents research performed in content-based retrieval of unusual and thus rarely investigated multimedia data. Presented topics include 3D surface and shape analysis of ancient rock art from high resolution 3D scans, object detection and tracking in unconstrained wildlife video, robust sound detection in bioacoustic monitoring, and detection of social events from web data.

Notka biograficzna prelegenta

Matthias Zeppelzauer is a senior researcher at the St. Pölten University of Applied Sciences since 2013. From 2011 to 2013, he was a postdoctoral researcher at the Interactive Media Systems Group at the Vienna University of Technology. He graduated with Master of Sciences at Vienna University of Technology in Computer Science and Business Informatics in 2005 and 2006, respectively, and holds a PhD in Computer Science from the Vienna University of Technology. His fundamental research focuses on content-based audio retrieval (bioacoustic monitoring, audio feature extraction, signal enhancement), visual retrieval (object recognition, model learning), and social media analysis. He is a lecturer for undergraduate- and graduate programs with an emphasis on multimedia. Matthias Zeppelzauer received several performance scholarships from the Vienna University of Technology and was awarded by the Austrian Computer Society for outstanding achievements in the area of pattern recognition in 2006.

Data opublikowania: 30.05.2014
Osoba publikująca: Krzysztof Bartosz