Multimedia Information Retrieval (MIR) is a research discipline of computer science that aims at extracting semantic information from multimedia data sources. Data sources include directly perceivable media such as audio, image and video, indirectly perceivable sources such as text, bio-signals as well as not perceivable sources such as bio-information, stock prices, etc.

HUMIR Lab's goal is to research in basic and applied information retrieval topics, working in close collaboration with industries to transfer its research results. Much of our MIR research has been directed at the fundamental issues of text representation, query acquisition, and retrieval models that form the basis of all search engines.