Please download the official programme (in pdf format) from the following link: MIE Official Programme
Title: NeuralStory: Automatic Understanding the Video Content for Interactive Education
Speaker: Rita Cucchiara, Università di Modena E Reggio Emilia, Italy.
Abstract: Video are entering in the education processes as the most valuable and high-impact media instruments for the training and engagement of students, from children to university scholars. The video language, based on a simple and direct multimodal communication, including visual, textual and audio information, is particularly appreciated by children, boys and girls and for adults too; it could provide a communication bridge between scientific studies and humanities and movies, TV and Web. However, not all technologies are available, or exploited in educational platforms; we lack automatic instruments for video structure detection, decomposition, annotation and description in one hand, and interactive services for using and enjoying with video content. This talk will discuss the state-of-the-art of multimedia and multimodal solutions for dealing with video in education and some new research results in automatic video summarization and video annotation. As well, a new platform called Neuralstory will be presented, which has been developed at UNIMORE AImage Lab, in an Italian MIUR project “Educating City” of the Smart Community Technology Cluster. The talk will describe also the back-end technologies necessary for new services: new Deep Learning technologies for joining video, audio and text analysis for automatic video understanding by means of neural network architectures. Then we will propose simple and effective services and their exploitation for students and children, in order to interact, enjoy and enrich the video content. At the end, new research results in automatic video captioning in natural language, with saliency analysis and naming will be discussed, as a potential new paradigm for multimodal interactivity, for cultural experiences and education.
Bio: Rita Cucchiara (Laurea in Electronic Eng. in 1989 ;Ph.D. in Computer Eng. in 1992 at UNIBO )is full professor with the Dipartimento di Ingegneria “Enzo Ferrari” at UNIMORE, Università di Modena e Reggio Emilia, Italy since 2005. She is Director of the Center of Research in Ict Softech-ICT of UNIMORE of the Modena Technopole. She holds the Research Lab AImagl Lab in Computer Vision, Pattern Recognition, AI, Machine Learning and Multimedia (www.aimagelab.unimore). She is Director of Master in “Visual Computing and Multimedia Technology in the deep Learning Era” and Rector Delegate of UNIMORE for industrial Research, innovation and technology transfer of Emilia-Romagna. At UNIMORE she holds the courses of “Computer architecture ” for Computer Engineering ungraduated cv and “Computer Vision” for Magistrale cv. Rita Cucchiara is currently President of the Italian Association in Computer Vision, Pattern Recognition and Machine Learning GIRPR, Member of the Governing Board of IAPR, Member of the advisory Board of the Computer Vision Foundation and Member of the Board of Directors of Italian Institute of Tehcnology (IIT). Rita Cucchiara coordinates several National and international Research projects with public bodies and industries. She is Associated Editor of IEEE Transactions of Multimedia and author or co-author of more than 300 scientific papers. For the complete list of publication see at http://imagelab.ing.unimore.it/imagelab/publications.asp.
Title: Multimodal interaction for digital inclusion in education
Speaker: Stephen Brewster
Abstract: Access to information, data and teaching resources is vital for education; if students who are blind or who have visual impairments cannot access such information their education will be significantly poorer. In this talk, I will discuss research that we have been doing a Glasgow looking at different ways of making graphical material, such as graphs and charts, accessible to blind students. I will also discuss a collaborative teaching aid that helps children learn handwriting and improve spatial skills.
Bio: Stephen Brewster is a Professor of Human-Computer Interaction in the School of Computing Science at the University of Glasgow. He leads the Multimodal Interaction Group. His research focuses on multimodal HCI, or using multiple sensory modalities and control mechanisms (particularly audio, haptics and gesture) to create a rich, natural interaction between human and computer. His work has a strong experimental focus, applying perceptual research to practical situations. A long-term focus has been on accessibility of interfaces for people with disabilities using audio and haptics. He is a member of the SIGCHI Academy and an ACM Distinguished Speaker.