상세정보

Video segmentation is the most fundamental process for appropriate index­ ing and retrieval of video intervals. In general, video streams are composed 1 of shots delimited by physical shot boundaries. Substantial work has been done on how to detect such shot boundaries automatically (Arman et aI. , 1993) (Zhang et aI. , 1993) (Zhang et aI. , 1995) (Kobla et aI. , 1997). Through the inte­ gration of technologies such as image processing, speech/character recognition and natural language understanding, keywords can be extracted and associated with these shots for indexing (Wactlar et aI. , 1996). A single shot, however, rarely carries enough amount of information to be meaningful by itself. Usu­ ally, it is a semantically meaningful interval that most users are interested in re­ trieving. Generally, such meaningful intervals span several consecutive shots. There hardly exists any efficient and reliable technique, either automatic or manual, to identify all semantically meaningful intervals within a video stream. Works by (Smith and Davenport, 1992) (Oomoto and Tanaka, 1993) (Weiss et aI. , 1995) (Hjelsvold et aI. , 1996) suggest manually defining all such inter­ vals in the database in advance. However, even an hour long video may have an indefinite number of meaningful intervals. Moreover, video data is multi­ interpretative. Therefore, given a query, what is a meaningful interval to an annotator may not be meaningful to the user who issues the query. In practice, manual indexing of meaningful intervals is labour intensive and inadequate.

Video segmentation is the most fundamental process for appropriate index­ ing and retrieval of video intervals. In general, video streams are composed 1 of shots delimited by physical shot boundaries. Substantial work has been done on how to detect such shot boundaries automatically (Arman et aI. , 1993) (Zhang et aI. , 1993) (Zhang et aI. , 1995) (Kobla et aI. , 1997). Through the inte­ gration of technologies such as image processing, speech/character recognition and natural language understanding, keywords can be extracted and associated with these shots for indexing (Wactlar et aI. , 1996). A single shot, however, rarely carries enough amount of information to be meaningful by itself. Usu­ ally, it is a semantically meaningful interval that most users are interested in re­ trieving. Generally, such meaningful intervals span several consecutive shots. There hardly exists any efficient and reliable technique, either automatic or manual, to identify all semantically meaningful intervals within a video stream. Works by (Smith and Davenport, 1992) (Oomoto and Tanaka, 1993) (Weiss et aI. , 1995) (Hjelsvold et aI. , 1996) suggest manually defining all such inter­ vals in the database in advance. However, even an hour long video may have an indefinite number of meaningful intervals. Moreover, video data is multi­ interpretative. Therefore, given a query, what is a meaningful interval to an annotator may not be meaningful to the user who issues the query. In practice, manual indexing of meaningful intervals is labour intensive and inadequate.

정보제공 :

CONTENTS

Message from the General Chair = ⅸ

Message from the Program Co - chairs = xi

Committers = xiii

Part Ⅰ ADVANCES IN VISUAL INFORMATION MANAGEMENT Ⅰ

 1 Construction of the Multimedia Mediation Systems / Masao Sakauchi = 3

Part Ⅱ VIDEO RETRIEVAL

 2 A New Algebraic Approach to Retrieve Meaningful Video Intervals from Fragmentarily Inexed Video Shots / Sujeet Pradhan ; Takashi Sogo ; Keishi Tajima and Katsumi Tanaka = 11

 3 Toward The MEdiaSys VOdep Searcj Emgine (MEVISE) / Frederic Andres ; Kinji Ono ; Shin'Ichi Satoh and Nicolas Dessaigne = 31

 4 Content-based Video Retrieval Based on Similarity of Camera Motion / Hitoshi Endoh and Ryoji Kataoka = 45

Part Ⅲ INFORMATION VISUALIZATION

 5 Visual Exploration for Social Recommendations / Junichi Tatemura = 63

 6 Web-Based Visualization of Large Hierarchical Graphs Using Invisible Links in a Hyperbolic Space / Ming C. Hao ; Meichun Hsu ; Umesh Dayal and Adrian Krug = 83

 7 Visualizing Electronic Document Repositories : Drawing Books and Pa-pers in a Digital Library / Andreas Rauber and Harald Bina = 95

Part Ⅳ MODELING AND RECOGNITION

 8 A Motion Recognition Method by Using Primitive Motions / Ryuta Osaki ; Mitsuomi Shimada and Kuniaki Uehara = 117

 9 Conceptual Modelling for Database User Interfaces / Richard Cooper ; Jo McKirdy ; Tony Griffiths ; Peter J. Barclay ; Norman W. Paton ; Philip D. Gray ; Jessie Kennedy and Carole A. Goble = 129

Part Ⅴ ADVANCES IN VISUAL INFORMATION MANAGEMENT Ⅱ

 10 Searching, Data Mining and Visualization of Mltimedia Data / Christos Faloutsos = 141

Part Ⅵ IMAGE SIMILARITY RETRIEVAL

 11 Efficient Image Retrieval by Examples / Roberto Brunelli and Ornella Mich = 145

 12 Applying Augmented Orientation spatial Similarity Retrieval in Pictorial Database / Xiao Ming Zhou ; Chuan Heng Ang and Tok Wang Ling = 163

 13 Toward Feature Algebras in Visual Databases : The Case for a Histogram Algebra / Amarnath Gupta and Simone Santini = 177

Part Ⅶ SPATIO-TEMPORAL DATABASE

 14 Query-By-Trace : Visual Predicate Specification in Spatio-Temporal Databases / Martin Erwig and Markus Schneider = 199

 15 Skimming Multiple Perspective Video Using Tempo-Spatial Importance Measures / Toshihiko Hata ; Tatsuo Hirose and Katsumi Tanaka = 219

 16 Networked Augmented Spatial Hypermedia System on Internet / Michihiro Murao ; Masatoshi Arikawa and Koji Okamura = 239

Part Ⅷ VISUAL QUERYING

 17 Drag and Drop : Amalgamation of Authoring, Querying, and Restructur-ing for Multimedia View Construction / Atsuyuki Morishima ; Seiichi Koizumi and Hiroyuki Kitagawa = 257

 18 BBQ : A Visual Interface for Integrated Browsing and Querying of XML / Devin D. Munroe and Yannis Papakonstantiou = 277

 19 MDDQL : A Visual Query Language for Metadata Driven Querying / E. Kapetanios ; M. C. Norrie and D. Fuhrer - Stakic = 297

Part Ⅸ CLUSTERING AND RETRIEVAL

 20 Hierarchical Space Model for Multimedia Data Retrieval / Makoto Onizuka and Shuichi Nishioka = 319

 21 MST Construction with Metric Matrix for Clustering / Masahiro Ishikawa ; Yi Liu ; Kazutaka furuse ; Hanxiong Chen and Nobuo Ohbo = 329

Part Ⅹ USER INTERFACE

 22 Automatic Updates of Interactive Information Visualization User Inter-faces through Database Triggers / Martin Leissler ; Matthias Hemmje and Erich Neuhold = 341

 23 TBE : A graphical Interface for writing Trigger rules in Active Databases / Dongwon Lee ; Wenlei Mao ; Henry Chiu and Wesley W. Chu = 367

 24 WEBSA : Database Support for Efficient Web Site Navigation / Isabel F. Cruz ; Lijun Leo Liu ; and Tony Y. Wu = 387

Index of contributors = 407

Keyword index 409