Both the way we look at data, through a DBMS, and the nature of data we ask a DBMS to manage have drastically evolved over the last decade, moving from text to images (and to sound to a lesser extent). Visual representations are used extensively within new user interfaces. Powerful visual approaches are being experimented for data manipulation, including the investigation of three dimensional display techniques. Similarly, sophisticated data visualization techniques are dramatically improving the understanding of the information extracted from a database. On the other hand, more and more applications use images as basic data or to enhance the quality and richness of data manipulation services. Image management has opened a wide area of new research topics in image understanding and analysis. The IFIP 2.6 Working Group on Databases strongly believes that a significant mutual enrichment is possible by confronting ideas, concepts and techniques supporting the work of researcher and practitioners in the two areas of visual interfaces to DBMS and DBMS management of visual data. For this reason, IFIP 2.6 has launched a series of conferences on Visual Database Systems. The first one has been held in Tokyo, 1989. VDB-2 was held in Budapest, 1991. This conference is the third in the series. As the preceding editions, the conference addresses researchers and practitioners active or interested in user interfaces, human-computer communication, knowledge representation and management, image processing and understanding, multimedia database techniques and computer vision.

With the proliferation of citizen reporting, smart mobile devices, and social media, an increasing number of people are beginning to generate information about events they observe and participate in. A significant fraction of this information contains multimedia data to share the experience with their audience. A systematic information modeling and management framework is necessary to capture this widely heterogeneous, schemaless, potentially humongous information produced by many different people. This book is an attempt to examine the modeling, storage, querying, and applications of such an event management system in a holistic manner. It uses a semantic-web style graph-based view of events, and shows how this event model, together with its query facility, can be used toward emerging applications like semi-automated storytelling. Table of Contents: Introduction / Event Data Models / Implementing an Event Data Model / Querying Events / Storytelling with Events / An Emerging Application / Conclusion

Motion-based recognition deals with the recognition of an object and/or its motion, based on motion in a series of images. In this approach, a sequence containing a large number of frames is used to extract motion information. The advantage is that a longer sequence leads to recognition of higher level motions, like walking or running, which consist of a complex and coordinated series of events. Unlike much previous research in motion, this approach does not require explicit reconstruction of shape from the images prior to recognition. This book provides the state-of-the-art in this rapidly developing discipline. It consists of a collection of invited chapters by leading researchers in the world covering various aspects of motion-based recognition including lipreading, gesture recognition, facial expression recognition, gait analysis, cyclic motion detection, and activity recognition. Audience: This volume will be of interest to researchers and post- graduate students whose work involves computer vision, robotics and image processing.

Motion-based recognition deals with the recognition of an object and/or its motion, based on motion in a series of images. In this approach, a sequence containing a large number of frames is used to extract motion information. The advantage is that a longer sequence leads to recognition of higher level motions, like walking or running, which consist of a complex and coordinated series of events. Unlike much previous research in motion, this approach does not require explicit reconstruction of shape from the images prior to recognition. This book provides the state-of-the-art in this rapidly developing discipline. It consists of a collection of invited chapters by leading researchers in the world covering various aspects of motion-based recognition including lipreading, gesture recognition, facial expression recognition, gait analysis, cyclic motion detection, and activity recognition. Audience: This volume will be of interest to researchers and post- graduate students whose work involves computer vision, robotics and image processing.

Both the way we look at data, through a DBMS, and the nature of data we ask a DBMS to manage have drastically evolved over the last decade, moving from text to images (and to sound to a lesser extent). Visual representations are used extensively within new user interfaces. Powerful visual approaches are being experimented for data manipulation, including the investigation of three dimensional display techniques. Similarly, sophisticated data visualization techniques are dramatically improving the understanding of the information extracted from a database. On the other hand, more and more applications use images as basic data or to enhance the quality and richness of data manipulation services. Image management has opened a wide area of new research topics in image understanding and analysis. The IFIP 2.6 Working Group on Databases strongly believes that a significant mutual enrichment is possible by confronting ideas, concepts and techniques supporting the work of researcher and practitioners in the two areas of visual interfaces to DBMS and DBMS management of visual data. For this reason, IFIP 2.6 has launched a series of conferences on Visual Database Systems. The first one has been held in Tokyo, 1989. VDB-2 was held in Budapest, 1991. This conference is the third in the series. As the preceding editions, the conference addresses researchers and practitioners active or interested in user interfaces, human-computer communication, knowledge representation and management, image processing and understanding, multimedia database techniques and computer vision.

This book introduces the concept of Event Mining for building explanatory models from analyses of correlated data. Such a model may be used as the basis for predictions and corrective actions. The idea is to create, via an iterative process, a model that explains causal relationships in the form of structural and temporal patterns in the data. The first phase is the data-driven process of hypothesis formation, requiring the analysis of large amounts of data to find strong candidate hypotheses. The second phase is hypothesis testing, wherein a domain expert's knowledge and judgment is used to test and modify the candidate hypotheses. The book is intended as a primer on Event Mining for data-enthusiasts and information professionals interested in employing these event-based data analysis techniques in diverse applications. The reader is introduced to frameworks for temporal knowledge representation and reasoning, as well as temporal data mining and pattern discovery. Also discussed are the design principles of event mining systems. The approach is reified by the presentation of an event mining system called EventMiner, a computational framework for building explanatory models. The book contains case studies of using EventMiner in asthma risk management and an architecture for the objective self. The text can be used by researchers interested in harnessing the value of heterogeneous big data for designing explanatory event-based models in diverse application areas such as healthcare, biological data analytics, predictive maintenance of systems, computer networks, and business intelligence.

This book introduces the concept of Event Mining for building explanatory models from analyses of correlated data. Such a model may be used as the basis for predictions and corrective actions. The idea is to create, via an iterative process, a model that explains causal relationships in the form of structural and temporal patterns in the data. The first phase is the data-driven process of hypothesis formation, requiring the analysis of large amounts of data to find strong candidate hypotheses. The second phase is hypothesis testing, wherein a domain expert's knowledge and judgment is used to test and modify the candidate hypotheses. The book is intended as a primer on Event Mining for data-enthusiasts and information professionals interested in employing these event-based data analysis techniques in diverse applications. The reader is introduced to frameworks for temporal knowledge representation and reasoning, as well as temporal data mining and pattern discovery. Also discussed are the design principles of event mining systems. The approach is reified by the presentation of an event mining system called EventMiner, a computational framework for building explanatory models. The book contains case studies of using EventMiner in asthma risk management and an architecture for the objective self. The text can be used by researchers interested in harnessing the value of heterogeneous big data for designing explanatory event-based models in diverse application areas such as healthcare, biological data analytics, predictive maintenance of systems, computer networks, and business intelligence.

The word multimedia is often associated with specific applications from entertainment to web design to video to music. This innovative textbook presents emerging techniques in multimedia computing from an experiential perspective in which each medium audio, images, text, and so on is a strong component of the complete, integrated exchange of information or experience. Humans are the best functioning example of multimedia communication and computing that is, we understand information and experiences through the unified perspective offered by our five senses. The goal of this book is to present current techniques in computing and communication that will lead to the development of a unified and holistic approach to computing using heterogeneous data sources. The authors introduce the fundamentals of multimedia computing, describing the properties of perceptually encoded information, presenting common algorithms and concepts for handling it, and outlining the typical requirements for emerging applications that use multifarious information sources. Designed for advanced undergraduate and beginning graduate courses, the book will also serve as an introduction for engineers and researchers interested in understanding the elements of multimedia and their role in building specific applications."