Multimodal Processing and Interaction: Audio, Video, Text

Front Cover
Petros Maragos, Alexandros Potamianos, Patrick Gros
Springer Science & Business Media, Dec 16, 2008 - Computers - 374 pages

Multimodal Processing and Interaction: Audio, Video and Text presents high quality, state-of-the-art research ideas and results from theoretic, algorithmic and application viewpoints. This edited volume contains both state-of-the-art reviews and original contributions by leading experts in the scientific and technological field of multimedia. It grew out of a four-year collaboration among research groups participating in the European network of Excellence on Multimedia Understanding, Semantics, Computation and Learning (MUSCLE).

Multimodal Processing and Interaction: Audio, Video and Text covers a broad spectrum of novel perspectives, analytic tools, algorithms, design practices and applications in multimedia science and engineering with emphasis on multimodal integration and modality fusion. This volume also contains contributions in the area of interaction with multimedia, especially multimodal interfaces for accessing multimedia content.

Multimodal Processing and Interaction: Audio, Video and Text is designed for a professional audience composed of practitioners and researchers in industry and academia. This book is suitable for advanced-level students in computer science and engineering as well.

 

Contents

CrossModal Integration for Performance Improving
3
Movie Analysis with Emphasis to Dialogue and Action
7
Stochastic Models for Multimodal Video Analysis
89
Adaptive Multimodal Fusion by Uncertainty Compensation
111
Action Recognition in Multimedia Streams
126
Surveillance Using Both Video and Audio
143
Scene Detection
157
Audiovisual Attention Modeling and Salient Event
178
Interactive Image Retrieval Using a Hybrid Visual
220
Multimodal Analysis of Text and Audio Features
241
Intelligent Search for Image Information on the
259
Design Principles for Multimodal Spoken Dialogue
279
A New Interface for Visual Exploration
297
User Interaction for Mobile Devices
311
References
331
Index
365

Toward the Integration of Natural Language Processing
201

Other editions - View all

Common terms and phrases