© 2000

Advances in Visual Information Management

Visual Database Systems. IFIP TC2 WG2.6 Fifth Working Conference on Visual Database Systems May 10–12, 2000, Fukuoka, Japan

  • Hiroshi Arisawa
  • Tiziana Catarci
Book VDB 2000

Part of the IFIP — The International Federation for Information Processing book series (IFIPAICT, volume 40)

Table of contents

  1. Front Matter
    Pages i-xiii
  2. Advances in Visual Information Management I

    1. Front Matter
      Pages 1-1
  3. Video Retrieval

    1. Front Matter
      Pages 9-9
    2. Sujeet Pradhan, Takashi Sogo, Keishi Tajima, Katsumi Tanaka
      Pages 11-30
    3. Frédéric Andrès, Kinji Ono, Shin’Ichi Satoh, Nicolas Dessaigne
      Pages 31-44
  4. Information Visualization

    1. Front Matter
      Pages 61-61
    2. Junichi Tatemura
      Pages 63-82
    3. Ming C. Hao, Meichun Hsu, Umesh Dayal, Adrian Krug
      Pages 83-94
  5. Modeling and Recognition

    1. Front Matter
      Pages 115-115
    2. Ryuta Osaki, Mitsuomi Shimada, Kuniaki Uehara
      Pages 117-127
    3. Richard Cooper, Jo McKirdy, Tony Griffiths, Peter J. Barclay, Norman W. Paton, Philip D. Gray et al.
      Pages 129-138
  6. Advances in Visual Information Management II

    1. Front Matter
      Pages 139-139
  7. Image Similarity Retrieval

    1. Front Matter
      Pages 143-143
    2. Roberto Brunelli, Ornella Mich
      Pages 145-162
    3. Xiao Ming Zhou, Chuan Heng Ang, Tok Wang Ling
      Pages 163-175

About this book


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.


communication database information information visualization multimedia tools visualization

Editors and affiliations

  • Hiroshi Arisawa
    • 1
  • Tiziana Catarci
    • 2
  1. 1.Yokohama National UniversityJapan
  2. 2.Università degli Studi di Roma “La Sapienza”Italy

Bibliographic information

Industry Sectors
IT & Software
Finance, Business & Banking