Codemill joins EU project MICO as a transfer partner

MICO, short for Media in Context, is a European Union part-funded research project to provide cross-media analysis solutions for online multimedia producers. It is now official that Swedish system developers CodeMill AB are joining MICO as a transfer partner, and will as such help disseminate project results to a wider audience. Codemill services media-oriented customers on an international market, typically building on open-source platforms with a usability-focus. Recent projects include tools for automatic metadata-extraction developed in collaboration with Vidispine, as well as a publishing system tailored for Guardian News and Media. The company was founded in Umeå 2007, and still has its head office there. Today, the company consists of just over 30 employees with levels from junior to senior computer scientists, interaction designers and even PhD:s.

“Our customers are continually challenging us to find new and better ways to manage their content”, says CEO Rickard Lönneborg, “and we believe that the MICO platform shows great potential as a unifying framework.”

Research contribution
By participating in MICO, Codemill wants to contribute to a much appreciated research initiative, and to encourage knowledge exchange in the field of video analysis. This is in line with the company’s general policy of acting in the intersection of Industry and Academia. Codemill has previously participated in the EU-project SATIN on user-driven development of mobile applications, and has on-going collaborations with researchers and start-ups in the field of media analysis.

“The availability of more and better data sets, together with advances in machine learning, is driving progress. We expect that many relevant forms of data analysis will cross over from the purely theoretical sphere into the real world.” adds CTO Johanna Björklund. “Emotion recognition is a prime example, we see lots of interesting things happening there.”

Codemill believes that MICO can accelerate the progress even further, as it allows data analysis to be made with respect to many different aspects of a media asset. It may e.g. be difficult to determine who appears in a low-resolution video based on the visual component alone, but by adding in speaker recognition and extracting proper names from associated comment fields, precision can be improved.

“The beauty of it is that the abstractions used in many machine-learning models allow for different kinds of features to be blended freely. Such is for instance the case for support vector machines and neural networks. Now we would like to see this principle applied in practise.”, Björklund concludes.

About MICO

MICO is an international research effort meant to provide cross-media analysis solutions for online multimedia producers. The project is funded in part by the European Union, and participants include Salzburg Research, Fraunhofer IDMT, Oxford University, Univerisity of Passau, Umeå University, Zaizi, and InsideOut10. During a span of three years, MICO will develop models, standards, and software tools for media management tasks. In particular, the aim is to jointly analyse, query, and retrieve information out of connected and related media objects (text, image, audio, video, office documents) to provide better information extraction results for more relevant search and information discovery.

An interesting MICO use case is provided by the crowdsourcing platform Zooniverse at Oxford University. Zooniverse is host to scientific projects that invite the public to help classify data. One example is Snapshot Serengeti, in which researchers have rigged motion activated cameras across the savannah. When an animal walks by a camera, this triggers series of photographs to be taken. The researchers behind Snapshot Serengeti are asking for help to decide what species appear in the photographs, and what they are doing (a wildebeest that is grazing, two zebras that are resting, etc). MICO helps by developing software for supportive tasks such as determining whether there are any animals in an images at all, if the quality of the image is up to par, and what species names are mentioned in the user comments.