Advances in Multimodal Interfaces - ICMI 2000

Multimodal Interfaces represents an emerging interdisciplinary research direction and has become one of the frontiers in Computer Science. Multimodal interfaces aim at efficient, convenient and natural interaction and communication between computers (in their broadest sense) and human users. They will ultimately enable users to interact with computers using their everyday skills. These proceedings include the papers accepted for presentation at the Third International Conference on Multimodal Interfaces (ICMI 2000) held in Beijing, China on 1416 O ctober 2000. The papers were selected from 172 contributions submitted worldwide. Each paper was allocated for review to three members of the Program Committee, which consisted of more than 40 leading researchers in the field. Final decisions of 38 oral papers and 48 poster papers were made based on the reviewers' comments and the desire for a balance of topics. The decision to have a single track conference led to a competitive selection process and it is very likely that some good submissions are not included in this volume. The papers collected here cover a wide range of topics such as affective and perceptual computing, interfaces for wearable and mobile computing, gestures and sign languages, face and facial expression analysis, multilingual interfaces, virtual and augmented reality, speech and handwriting, multimodal integration and application systems. They represent some of the latest progress in multimodal interfaces research.

Inhalt

Affective and Perceptual Computing.- Gaze and Speech in Attentive User Interfaces.- Resolving References to Graphical Objects in Multimodal Queries by Constraint Satisfaction.- Human-Robot Interface Based on Speech Understanding Assisted by Vision.- Designing Multi-sensory Models for Finding Patterns in Stock Market Data.- Audio-visual Segmentation and "The Cocktail Party Effect".- Visual Recognition of Emotional States.- An Experimental Study of Input Modes for Multimodal Human-Computer Interaction.- Emotion Expression Function in Multimodal Presentation.- A Sound MagicBoard.- Gesture Recognition.- A Head Gesture Recognition Algorithm.- Gesture Recognition for a Walking Person by Using a Sequence of Spatially Reduced Range Image.- Virtual Mouse-Inputting Device by Hand Gesture Tracking and Recognition.- A Self-reliance Smoothness of the Vision-Based Recognition of Hand Gestures.- Hand Shape Extraction and Understanding by Virtue of Multiple Cues Fusion Technology.- Head Pose Estimation for Video-Conferencing with Multiple Cameras and Microphones.- Face and Facial Expression Detection, Recognition and Synthesis.- A General Framework for Face Detection.- Glasses Detection for Face Recognition Using Bayes Rules.- Real-Time Face Tracking under Partial Occlusion and Illumination Change.- Eye-State Action Unit Detection by Gabor Wavelets.- Web-PICASSO: Internet Implementation of Facial Caricature System PICASSO.- Recognition of Human Faces Based on Fast Computation of Circular Harmonic Components.- Multiple Faces Tracking and Zooming System.- Face Warping Using a Single Image.- Hierarchical Framework for Facial Expression Recognition.- Detecting Facial Features on Images with Multiple Faces.- The Synthesis of Realistic Human Face.- Gravity-Center Template Based Human Face Feature Detection.- A Improved Facial Expression Recognition Method.- Face Direction Estimation using Multiple Cameras for Human Computer Interaction.- Face Recognition Based on Local Fisher Features.- Combining Skin Color Model and Neural Network for Rotation Invariant Face Detection.- Multilingual Interfaces and Natural Language Understanding.- Multimodal Integration Using Complex Feature Set.- Bilingual Dictionary Based Sentence Alignment for Chinese English Bitext.- A Task Oriented Natural Language Understanding Model.- Variable Length Language Model for Chinese Character Recognition.- Automatic Lexical Errors Detecting of Chinese Texts Based on the Orderly-Neighborship1.- Statistical Analysis of Chinese Language and Language Modeling Based on Huge Text Corpora1.- On Building a Simulating Translation Environment for Multilingual Conversation.- Approach to Recognition and Understanding of the Time Constituents in the Spoken Chinese Language Translation.- Speech Processing and Speaker Detection.- KD2000 Chinese Text-To-Speech System.- Multimodal Speaker Detection Using Input/Output Dynamic Bayesian Networks.- Research on Speech Recognition Based on Phase Space Reconstruction Theory.- Object Motion, Tracking and Recognition.- Estimating the Pose of Phicons for Human Computer Interaction.- An Approach to Robust and Fast Locating Lip Motion.- Multi-level Human Tracking.- Region-Based Tracking in Video Sequences Using Planar Perspective Models.- A Novel Motion Estimation Algorithm Based on Dynamic Search Window and Spiral Search.- Determining Motion Components Using the Point Distribution Model.- Handwriting Recognition.- Automatic Recognition of Unconstrained Off-Line Bangla Handwritten Numerals.- A Novel Algorithm for Handwritten Chinese Character Recognition.- An HMM Based Two-Pass Approach for Off-Line Cursive Handwriting Recognition.- On-Line Recognition of Mathematical Expressions Using Automatic Rewriting Method.- On-Line Hand-Drawn Symbol Recognition Based on Primitives Separation and Fuzzy Inference.- Integration MBHMM and Neural Network for Totally Unconstrained Handwritten Numerals Recognition.- Aspect Ratio Adaptive Normalization for Handwritten Character Recognition.- A Neural-Network Dimension Reduction Method for Large-Set Pattern Classification*.- Local Subspace Classifier in Reproducing Kernel Hilbert Space.- A Recognition System for Devnagri and English Handwritten Numerals.- Deformation Transformation for Handwritten Chinese Character Shape Correction.- Offline Handwritten Chinese Character Recognition Using Optimal Sampling Features.- A New Multi-classifier Combination Scheme and Its Application in Handwriting Chinese Character Recognition.- Off-Line Handwritten Chinese Character Recognition with Nonlinear Pre-classification.- Input Devices and Its Usability.- Detection of the Indicated Area with an Indication Stick.- Heuristic Walkthroughs Evaluation of Pen-Based Chinese Word Edit System (PCWES) Usability.- Design and Realization of 3D Space Coordinate Serial Input.- Virtual and Augmented Reality.- User's Vision Based Multi-resolution Rendering of 3D Models in Distributed Virtual Environment DVENET.- Vision-Based Registration Using 3-D Fiducial for Augmented Reality.- The Study on Stereoscopic Image Generating Algorithm Based on Image Transformation1.- Jacob - An Animated Instruction Agent in Virtual Reality.- Multimodal Interfaces for Wearable and Mobile Computing.- Penbuilder: Platform for the Development of Pen-Based User Interface.- Information Presentation for a Wearable Messenger Device.- Usability of Browser-Based Pen-Touch/Speech User Interfaces for Form-Based Applications in Mobile Environment.- A Lock Opening and Closing System with the Image Base Using a Cellular Phone through the Internet.- Sign Languages and Multimodal Navigation for the Disabled.- HandTalker: A Multimodal Dialog System Using Sign Language and 3-D Virtual Human.- A Vision-Based Method for Recognizing Non-manual Information in Japanese Sign Language.- A Parallel Multistream Model for Integration of Sign Language Recognition and Lip Motion.- Multi-modal Navigation for Interactive Wheelchair.- A Fast Sign Word Recognition Method for Chinese Sign Language.- Multimodal Integration and Application Systems.- Automatic Keystone Correction for Camera-Assisted Presentation Interfaces.- A Multimodal User Interface for Geoscientific Data Investigation.- Partial Information in Multimodal Dialogue.- Multimodal Interface Techniques in Content-Based Multimedia Retrieval.- Design of Retrieval Method of Map Targets in the Multimodal Interface.- First-Personness Approach to Co-operative Multimodal Interaction.-…