The Multimedia Pattern Recognition research group works in one of the six major research areas of Fraunhofer IAIS. We develop advanced algorithms for the segmentation, recognition, and indexing of speech, audio, image, and video data. We also analyze social media and investigate how people interact in a networked world.

Please visit our scientific blog for more information.

Latest News

08/27/2016

new numpy/scipy recipe

It has been a while, but finally there is a new note on numpy/scipy recipes ...

Read more
02/09/2016

Lecture "Deep Learning for Multimedia Pattern Recognition", Summer 2016

Starting on 12 April 2016, I will give a lecture course on deep learning for multimedia pattern recognition. The lecture will cover both theory and numerous practical applications.

Read more
11/10/2015

numpy / scipy recipes for data science

The nearest neighbor problem frequently arises in may areas of data science. In this short note, we show how to efficiently tackle it in numpy.

Read more
11/04/2015

new didactic videos on algorithms in data science

There are several new videos illustrating how k-means clustering and its variants behave in practice.

Read more
11/04/2015

numpy / scipy recipes for data science

Data scientists frequently need to compute the eigenvalues and eigenvectors of data covariance matrices. We therefore discuss appropriate ways of how this can be done using numpy/scipy.

Read more