This third seminar takes the contents of the first two seminars—namely, the motivations, foundational concepts, basic modality combinations, component analyses, and recognition and fusion techniques—to the next level. MMI 3 discusses how to design and build functioning multimodal-multisensor systems that can sustain real-world use.
This seminar is most appropriate for graduate students and of primary interest to students studying computer science and information technology, human-computer interfaces, mobile and ubiquitous interfaces, affective and behavioral computing, machine learning, and related multidisciplinary majors. It is very useful if you want to work on practical applications, transfer of AI technology to application domains such as medicine and healthcare, and industrial prototypes.
Central part of the seminar is the reference book "The Handbook of Multimodal-Multisensor Interfaces: Language Processing, Software, Commercialization, and Emerging Directions - Volume 3" (https://dl.acm.org/doi/book/10.1145/3233795). At the beginning there will be an introduction to the subject. Everyone will receive a chapter, for which a presentation (30 min. + 30 min. discussion) and a written elaboration (5-10 pages) are to be prepared.