This book contens: Part I Review of the State-of-the-Art, (1) Cross-Modal Integration for Performance Improving in Multimedia: A Review (2) Human-Computer Interfaces to Multimedia Content: A Review. Part II Integrated Multimedia Analysis and Recognition, (3) Stochastic Models for Multimodal Video Analysis (4) Adaptive Multimodal Fusion by Uncertainty Compensation with Application to Audio-Visual Speech Rocognition (5) Action Recognition in Multimedia Streams (6) Surveillance Using Both Video and Audio (7) Movie Analysis with Emphasis to Dialogue and Action Scene Detection (8) Aidiovisual Attention Modling and Salient Event Detection (9) Toward the Integration of Natural Language Processing and Automatic Speech Recognition: Using Mopho-Syntax and Pragmatics for Trancription. Part III Searching Multimedia Content, (10) Interactive Image Retrieval Using a Hybrid Visual and Conceptual Content Representation (11) Multimodal Analysis of Text and Audio Features for Music Information Retrieval (12) Intellegent Search for Image Information on the Web through Text and Link Structure Analysis. Part IV Interfaces to Multimedia Content, (13) Design Principles for Multimodal Spoken Dialogue Systems (14) Eye Tracking: A New Intervace for Visual Exploration (15) User Interaction for Mobile Devices. //ir