by Emanuele Salerno
The National Research Council of Italy in Pisa hosted the International Workshop on Computational Intelligence for Multimedia Understanding, organized by the ERCIM Working Group on Multimedia Understanding through Semantics, Computation and Learning (Muscle), 11-13 December 2011. The workshop was co-sponsored by CNR and Inria. Proceedings to come in LNCS 7252
Computational intelligence is becoming increasingly important in our households, and in all commercial, industrial and scientific environments. A host of information sources, different in nature, format, reliability and content are normally available at virtually no expense. Analyzing raw data to provide them with semantics is essential to exploit their full potential and help us manage our everyday tasks. This is also important for data description for storage and mining. Interoperability and exchangeability of heterogeneous and distributed data is an essential requirement for any practical application. Semantics is information at the highest level, and inferring it from raw data (that is, from information at the lowest level) entails exploiting both data and prior information to extract structure and meaning. Computation, machine learning, ontologies, statistical and Bayesian methods are tools to achieve this goal. They were all discussed in this workshop.
Ovidio Salvetti and Emanuele Salerno open the workshop.
30 participants from eleven countries attended the workshop. With the help of more than 20 external reviewers, the program committee ensured a high scientific level, accepting 19 papers for presentation. Both theoretical and application-oriented talks, covering a very wide range of subjects, were given. Papers on applications included both the development of basic concepts towards the real-world practice and the actual realization of working systems. Most contributions focussed on still images, but there were some on video and text. Two presentations exploited results from studies on human visual perception for image and video analysis and synthesis. Two greatly appreciated invited lectures were given by Sanni Siltanen, VTT, former Muscle chair, and Bülent Sankur, Bogaziçi University, Istanbul. These dealt with emotion detection from facial images (Sankur) and advanced applications of augmented reality (Siltanen).
The Muscle group has more than 50 members from research groups in 15 countries. Their expertise ranges from machine learning and artificial intelligence to statistics, signal processing and multimedia database management. The goal of Muscle is to foster international cooperation in multimedia research and carry out training initiatives for young researchers.
Emanuele Salerno, MUSCLE WG chair, ISTI-CNR, Italy