Social Signal Processing is the first book to cover all aspects of the modeling, automated detection, analysis, and synthesis of nonverbal behavior in human-human and human-machine interactions. Authoritative surveys address conceptual foundations, machine analysis and synthesis of social signal processing, and applications. Foundational topics include affect perception and interpersonal coordination in communication; later chapters cover technologies for automatic detection and understanding such as computational paralinguistics and facial expression analysis and for the generation of artificial social signals such as social robots and artificial agents. The final section covers a broad spectrum of applications based on social signal processing in healthcare, deception detection, and digital cities, including detection of developmental diseases and analysis of small groups. Each chapter offers a basic introduction to its topic, accessible to students and other newcomers, and then outlines challenges and future perspectives for the benefit of experienced researchers and practitioners in the field.

"The Oxford Handbook of Affective Computing is a definitive reference in the burgeoning field of affective computing (AC), a multidisciplinary field encompassing computer science, engineering, psychology, education, neuroscience, and other disciplines. AC research explores how affective factors influence interactions between humans and technology, how affect sensing and affect generation techniques can inform our understanding of human affect, and on the design, implementation, and evaluation of systems involving affect at their core. The volume features 41 chapters and is divided into five sections: history and theory, detection, generation, methodologies, and applications. Section 1 begins with the making of AC and a historical review of the science of emotion. The following chapters discuss the theoretical underpinnings of AC from an interdisciplinary viewpoint. Section 2 examines affect detection or recognition, a commonly investigated area. Section 3 focuses on aspects of affect generation, including the synthesis of emotion and its expression via facial features, speech, postures, and gestures. Cultural issues are also discussed. Section 4 focuses on methodological issues in AC research, including data collection techniques, multimodal affect databases, formats for the representation of emotion, crowdsourcing techniques, machine learning approaches, affect elicitation techniques, useful AC tools, and ethical issues. Finally, Section 5 highlights applications of AC in such domains as formal and informal learning, games, robotics, virtual reality, autism research, health care, cyberpsychology, music, deception, reflective writing, and cyberpsychology. This compendium will prove suitable for use as a textbook and serve as a valuable resource for everyone with an interest in AC."--

This unique text/reference provides a coherent and comprehensive overview of all aspects of video analysis of humans. Broad in coverage and accessible in style, the text presents original perspectives collected from preeminent researchers gathered from across the world. In addition to presenting state-of-the-art research, the book reviews the historical origins of the different existing methods, and predicts future trends and challenges. Features: with a Foreword by Professor Larry Davis; contains contributions from an international selection of leading authorities in the field; includes an extensive glossary; discusses the problems associated with detecting and tracking people through camera networks; examines topics related to determining the time-varying 3D pose of a person from video; investigates the representation and recognition of human and vehicular actions; reviews the most important applications of activity recognition, from biometrics and surveillance, to sports and driver assistance.

Cooperative and Graph Signal Processing: Principles and Applications presents the fundamentals of signal processing over networks and the latest advances in graph signal processing. A range of key concepts are clearly explained, including learning, adaptation, optimization, control, inference and machine learning. Building on the principles of these areas, the book then shows how they are relevant to understanding distributed communication, networking and sensing and social networks. Finally, the book shows how the principles are applied to a range of applications, such as Big data, Media and video, Smart grids, Internet of Things, Wireless health and Neuroscience. With this book readers will learn the basics of adaptation and learning in networks, the essentials of detection, estimation and filtering, Bayesian inference in networks, optimization and control, machine learning, signal processing on graphs, signal processing for distributed communication, social networks from the perspective of flow of information, and how to apply signal processing methods in distributed settings. - Presents the first book on cooperative signal processing and graph signal processing - Provides a range of applications and application areas that are thoroughly covered - Includes an editor in chief and associate editor from the IEEE Transactions on Signal Processing and Information Processing over Networks who have recruited top contributors for the book

Powerful and economic sensors such as high definition cameras and corresponding recognition software have become readily available, e.g. for face and motion recognition. However, designing user interfaces for robots, phones and computers that facilitate a seamless, intuitive, and apparently effortless communication as between humans is still highly challenging. This has shifted the focus from developing ever faster and higher resolution sensors to interpreting available sensor data for understanding social signals and recognising users' intentions. Psychologists, Ethnologists, Linguists and Sociologists have investigated social behaviour in human-human interaction. But their findings are rarely applied in the human-robot interaction domain. Instead, robot designers tend to rely on either proof-of-concept or machine learning based methods. In proving the concept, developers effectively demonstrate that users are able to adapt to robots deployed in the public space. Typically, an initial period of collecting human-robot interaction data is used for identifying frequently occurring problems. These are then addressed by adjusting the interaction policies on the basis of the collected data. However, the updated policies are strongly biased by the initial design of the robot and might not reflect natural, spontaneous user behaviour. In the machine learning approach, learning algorithms are used for finding a mapping between the sensor data space and a hypothesised or estimated set of intentions. However, this brute-force approach ignores the possibility that some signals or modalities are superfluous or even disruptive in intention recognition. Furthermore, this method is very sensitive to peculiarities of the training data. In sum, both methods cannot reliably support natural interaction as they crucially depend on an accurate model of human intention recognition. Therefore, approaches to social robotics from engineers and computer scientists urgently have to be informed by studies of intention recognition in natural human-human communication. Combining the investigation of natural human behaviour and the design of computer and robot interfaces can significantly improve the usability of modern technology. For example, robots will be easier to use by a broad public if they can interpret the social signals that users spontaneously produce for conveying their intentions anyway. By correctly identifying and even anticipating the user's intention, the user will perceive that the system truly understands her/his needs. Vice versa, if a robot produces socially appropriate signals, it will be easier for its users to understand the robot's intentions. Furthermore, studying natural behaviour as a basis for controlling robots and other devices results in greater robustness, responsiveness and approachability. Thus, we welcome submissions that (a) investigate how relevant social signals can be identified in human behaviour, (b) investigate the meaning of social signals in a specific context or task, (c) identify the minimal set of intentions for describing a context or task, (d) demonstrate how insights from the analysis of social behaviour can improve a robot's capabilities, or (e) demonstrate how a robot can make itself more understandable to the user by producing more human-like social signals.

This volume describes frontiers in social-behavioral modeling for contexts as diverse as national security, health, and on-line social gaming. Recent scientific and technological advances have created exciting opportunities for such improvements. However, the book also identifies crucial scientific, ethical, and cultural challenges to be met if social-behavioral modeling is to achieve its potential. Doing so will require new methods, data sources, and technology. The volume discusses these, including those needed to achieve and maintain high standards of ethics and privacy. The result should be a new generation of modeling that will advance science and, separately, aid decision-making on major social and security-related subjects despite the myriad uncertainties and complexities of social phenomena. Intended to be relatively comprehensive in scope, the volume balances theory-driven, data-driven, and hybrid approaches. The latter may be rapidly iterative, as when artificial-intelligence methods are coupled with theory-driven insights to build models that are sound, comprehensible and usable in new situations. With the intent of being a milestone document that sketches a research agenda for the next decade, the volume draws on the wisdom, ideas and suggestions of many noted researchers who draw in turn from anthropology, communications, complexity science, computer science, defense planning, economics, engineering, health systems, medicine, neuroscience, physics, political science, psychology, public policy and sociology. In brief, the volume discusses: Cutting-edge challenges and opportunities in modeling for social and behavioral science Special requirements for achieving high standards of privacy and ethics New approaches for developing theory while exploiting both empirical and computational data Issues of reproducibility, communication, explanation, and validation Special requirements for models intended to inform decision making about complex social systems

Multimodal signal processing is an important research and development field that processes signals and combines information from a variety of modalities – speech, vision, language, text – which significantly enhance the understanding, modelling, and performance of human-computer interaction devices or systems enhancing human-human communication. The overarching theme of this book is the application of signal processing and statistical machine learning techniques to problems arising in this multi-disciplinary field. It describes the capabilities and limitations of current technologies, and discusses the technical challenges that must be overcome to develop efficient and user-friendly multimodal interactive systems. With contributions from the leading experts in the field, the present book should serve as a reference in multimodal signal processing for signal processing researchers, graduate students, R&D engineers, and computer engineers who are interested in this emerging field. - Presents state-of-art methods for multimodal signal processing, analysis, and modeling - Contains numerous examples of systems with different modalities combined - Describes advanced applications in multimodal Human-Computer Interaction (HCI) as well as in computer-based analysis and modelling of multimodal human-human communication scenes.

This book is concerned with the processing of signals that have been sam pled and digitized. The fundamental theory behind Digital Signal Process ing has been in existence for decades and has extensive applications to the fields of speech and data communications, biomedical engineering, acous tics, sonar, radar, seismology, oil exploration, instrumentation and audio signal processing to name but a few [87]. The term "Digital Signal Processing", in its broadest sense, could apply to any operation carried out on a finite set of measurements for whatever purpose. A book on signal processing would usually contain detailed de scriptions of the standard mathematical machinery often used to describe signals. It would also motivate an approach to real world problems based on concepts and results developed in linear systems theory, that make use of some rather interesting properties of the time and frequency domain representations of signals. While this book assumes some familiarity with traditional methods the emphasis is altogether quite different. The aim is to describe general methods for carrying out optimal signal processing.

Handbook of Signal Processing Systems is organized in three parts. The first part motivates representative applications that drive and apply state-of-the art methods for design and implementation of signal processing systems; the second part discusses architectures for implementing these applications; the third part focuses on compilers and simulation tools, describes models of computation and their associated design tools and methodologies. This handbook is an essential tool for professionals in many fields and researchers of all levels.

This book covers the basics of processing and spectral analysis of monovariate discrete-time signals. The approach is practical, the aim being to acquaint the reader with the indications for and drawbacks of the various methods and to highlight possible misuses. The book is rich in original ideas, visualized in new and illuminating ways, and is structured so that parts can be skipped without loss of continuity. Many examples are included, based on synthetic data and real measurements from the fields of physics, biology, medicine, macroeconomics etc., and a complete set of MATLAB exercises requiring no previous experience of programming is provided. Prior advanced mathematical skills are not needed in order to understand the contents: a good command of basic mathematical analysis is sufficient. Where more advanced mathematical tools are necessary, they are included in an Appendix and presented in an easy-to-follow way. With this book, digital signal processing leaves the domain of engineering to address the needs of scientists and scholars in traditionally less quantitative disciplines, now facing increasing amounts of data.