Thomas S. Huang

As computers become prevalent in all aspects of daily life, the need for natural and effective Human-Computer Interaction (HCI) becomes increasingly important. Computer vision and pattern recognition continue to play a dominant role in the HCI realm. However, computer vision methods often fail to become pervasive in the field due to the lack of real-time, robust algorithms, as well as novel and convincing applications. This state-of-the-art contributed volume presents a series of peer-reviewed survey articles written by international leading experts in computer vision, pattern recognition and Human-Computer Interaction. It is the first published text capturing the latest research in this rapidly advancing field with exclusive focus on real-time algorithms and practical applications in numerous industries, including computer games and medical and automotive systems. It is also an excellent starting point for further research in these areas. Contributions to this volume address specific topics such as: Real-Time Algorithms: from Signal Processing to Computer Vision Recognition of Isolated Fingerspelling Gestures Using Depth Edges Appearance-Based Real-Time Understanding of Gestures Using Projected Euler Angles Flocks of Features for Tracking Articulated Objects Static Hand Posture Recognition Based on Okapi-Chamfer Matching Visual Modeling of Dynamic Gestures Using 3D Appearance and Motion Features Head and Facial Animation Tracking Using Appearance-Adaptive Models and Particle Filters A Real-Time Vision Interface Based on Gaze Detection – Eyekeys Map Building From Human-Computer Interactions Real-Time Inference of Complex Mental States from Facial Expressions and Head Gestures Epipolar Constrained User Pushbutton Selection in Projected Interfaces Vision-Based HCI Applications The Office of the Past MPEG-4 Face and Body Animation Coding Applied to HCI Multimodal Human-Computer Interaction Real-Time Vision for Human-Computer Interaction is an invaluable reference for HCI researchers in both academia and industry, and a useful supplement for advanced-level courses in HCI and Computer Vision.

Welcome to the 2nd International Conference on Image and Video Retrieval, CIVR2003. The goal of CIVR is to illuminate the state of the art in visual information retrieval and to stimulate collaboration between researchers and practitioners. This year we received 110 submissions from 26 countries. Based upon the reviews of at least 3 members of the program committee, 43 papers were accepted for the research track of the conference. First, we would like to thank all of the members of the Program Committee and the additional referees listed below. Their reviews of the submissions played a pivotal role in the quality of the conference. Moreover,we are grateful to Nicu Sebe and Xiang Zhou for helping to organize the review process; Shih-Fu Chang and Alberto del Bimbo for setting up the practitioner track; and Erwin Bakker for editing the proceedings and designing the conference poster. Special thanks go to our keynote and plenary speakers, Nevenka Dimitrova fromPhilipsResearch,RameshJainfromGeorgiaTech,ChrisPorterfromGetty Images,andAlanSmeatonfromDublinCityUniversity.Furthermore,wewishto acknowledge our sponsors, the Beckman Institute at the University of Illinois at Urbana-Champaign,TsingHuaUniversity,theInstitutionofElectricalEngineers (IEE),PhilipsResearch,andtheLeidenInstituteofAdvancedComputerScience at Leiden University. Finally, we would like to express our thanks to severalpeople who performed important work related to the organization of the conference: Jennifer Quirk and Catherine Zech for the localorganizationat the BeckmanInstitute; Richard Harvey for his help with promotional activity and sponsorship for CIVR2003; andtotheorganizingcommitteeofthe?rstCIVRforsettinguptheinternational mission and structure of the conference.