Research The world is full of digital images and videos. In this deluge of visual information, the grand challenge is to unlock its content. This quest is the central research aim of the Intelligent Sensory Information Systems group. We address the complete knowledge chain of image and video retrieval by machine and human. Topics of study are semantic understanding, image and video mining, interactive picture analytics, and scalability. Our research strives for automation that matches human visual cognition, interaction surpassing man and machine intelligence, visualization blending it all in interfaces giving instant insight, and database architectures for extreme sized visual collections. Our research culminates in state-of-the-art image and video search engines which we evaluate in leading benchmarks, often as the best performer, in user studies, and in challenging applications.
Impact and embedding Inside the Informatics Institute, we address research challenges which demand visual analysis enriched with information retrieval and machine learning. To that end we are closely working together with ILPS for information retrieval and text analysis and with IAS for machine learning. For scalability in data management, we collaborate with the Centrum Wiskunde en Informatica. In Amsterdam we are co-initiators of Amsterdam Data Science opening opportunities in massive scale computing, knowledge engineering, and living labs for visual data. At national level we coordinate the research agenda for ICT by leading the COMMIT program and chairing the IPN. Internationally we coordinate EU projects and we are the only non-American partner in the IARPA Aladdin Video program. For education ISIS focuses mainly on the Artificial Intelligence program of the institute together with the other members of IvI.
Innovation and application Visual information is key in preserving culture, sharing life and advancing society by monitoring health, enhancing safety, personalizing news and communication, and accelerating scientific discovery. Our image and video retrieval research has currently applications in forensics and intelligence with the Netherlands Forensics Institute and the police, business analytics with the Amsterdam Business School and broadcast television search engines for the Netherlands Institute for Sound and Vision. The research has led to university spin-off Euvision Technologies, now acquired by Qualcomm, which applies the research results in automated moderation for social media platform owners, interactive search for forensic organizations and media publishers, and image classification providing mobile phone owners new ways of accessing their images.