A proposal on automatic adaptive metadata for personalized audio-visual contents

Pao Sriprasertsuk, Wataru Kameyama

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Abstract

    At the present, audio-visual searching technology is only to filter information from almost infinite amount of contents according to the static user preferences. However, the user preferences are dynamically changed, and it is not convenient to input such varied preferences information every time when the user preferences changed. In this paper, we propose a method to make the preference information be updated and generated automatically in the terminal side, using user's viewing history as feed-back metadata, and implement the system with optimized parameters. In our implementation, TV-Anytime forum's metadata and MPEG-7 user preferences description are utilized for the proposed system on audio-visual contents searching and filtering. For renewal user preferences information, a basic user preference tool ("preferenceValueType") of MPEG-7 User preferences description is adopted to adapt user aspects. In addition the requirements are summarized, and necessary functional components for implementing the proposed system are designed as well as data generation process to use for experiment. The components are audio-visual contents metadata filtering, data structure transformation, and preferences value weighting system. Finally, parameters that are defined in the paper are optimized according to experimental results. It is shown that the optimized value makes the proposed system more effective.

    Original languageEnglish
    Title of host publicationProceedings of the IASTED International Conference on Internet and Multimedia Systems and Applications
    EditorsM.H. Hamza
    Pages545-551
    Number of pages7
    Volume7
    Publication statusPublished - 2003
    EventProceedings of the Seventh IASTED International Conference on Internet and Multimedia Systems and Applications - Honolulu, HI
    Duration: 2003 Aug 132003 Aug 15

    Other

    OtherProceedings of the Seventh IASTED International Conference on Internet and Multimedia Systems and Applications
    CityHonolulu, HI
    Period03/8/1303/8/15

    Fingerprint

    metadata
    Metadata
    Data structures
    Feedback
    filter
    history
    Experiments
    weighting
    experiment
    Values
    parameter

    Keywords

    • Metadata
    • MPEG-7 User Preferences Description
    • Personalization
    • TV-Anytime

    ASJC Scopus subject areas

    • Development
    • Computer Networks and Communications

    Cite this

    Sriprasertsuk, P., & Kameyama, W. (2003). A proposal on automatic adaptive metadata for personalized audio-visual contents. In M. H. Hamza (Ed.), Proceedings of the IASTED International Conference on Internet and Multimedia Systems and Applications (Vol. 7, pp. 545-551)

    A proposal on automatic adaptive metadata for personalized audio-visual contents. / Sriprasertsuk, Pao; Kameyama, Wataru.

    Proceedings of the IASTED International Conference on Internet and Multimedia Systems and Applications. ed. / M.H. Hamza. Vol. 7 2003. p. 545-551.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Sriprasertsuk, P & Kameyama, W 2003, A proposal on automatic adaptive metadata for personalized audio-visual contents. in MH Hamza (ed.), Proceedings of the IASTED International Conference on Internet and Multimedia Systems and Applications. vol. 7, pp. 545-551, Proceedings of the Seventh IASTED International Conference on Internet and Multimedia Systems and Applications, Honolulu, HI, 03/8/13.
    Sriprasertsuk P, Kameyama W. A proposal on automatic adaptive metadata for personalized audio-visual contents. In Hamza MH, editor, Proceedings of the IASTED International Conference on Internet and Multimedia Systems and Applications. Vol. 7. 2003. p. 545-551
    Sriprasertsuk, Pao ; Kameyama, Wataru. / A proposal on automatic adaptive metadata for personalized audio-visual contents. Proceedings of the IASTED International Conference on Internet and Multimedia Systems and Applications. editor / M.H. Hamza. Vol. 7 2003. pp. 545-551
    @inproceedings{61804f319c384df686d24b0b1187b513,
    title = "A proposal on automatic adaptive metadata for personalized audio-visual contents",
    abstract = "At the present, audio-visual searching technology is only to filter information from almost infinite amount of contents according to the static user preferences. However, the user preferences are dynamically changed, and it is not convenient to input such varied preferences information every time when the user preferences changed. In this paper, we propose a method to make the preference information be updated and generated automatically in the terminal side, using user's viewing history as feed-back metadata, and implement the system with optimized parameters. In our implementation, TV-Anytime forum's metadata and MPEG-7 user preferences description are utilized for the proposed system on audio-visual contents searching and filtering. For renewal user preferences information, a basic user preference tool ({"}preferenceValueType{"}) of MPEG-7 User preferences description is adopted to adapt user aspects. In addition the requirements are summarized, and necessary functional components for implementing the proposed system are designed as well as data generation process to use for experiment. The components are audio-visual contents metadata filtering, data structure transformation, and preferences value weighting system. Finally, parameters that are defined in the paper are optimized according to experimental results. It is shown that the optimized value makes the proposed system more effective.",
    keywords = "Metadata, MPEG-7 User Preferences Description, Personalization, TV-Anytime",
    author = "Pao Sriprasertsuk and Wataru Kameyama",
    year = "2003",
    language = "English",
    isbn = "0889863806",
    volume = "7",
    pages = "545--551",
    editor = "M.H. Hamza",
    booktitle = "Proceedings of the IASTED International Conference on Internet and Multimedia Systems and Applications",

    }

    TY - GEN

    T1 - A proposal on automatic adaptive metadata for personalized audio-visual contents

    AU - Sriprasertsuk, Pao

    AU - Kameyama, Wataru

    PY - 2003

    Y1 - 2003

    N2 - At the present, audio-visual searching technology is only to filter information from almost infinite amount of contents according to the static user preferences. However, the user preferences are dynamically changed, and it is not convenient to input such varied preferences information every time when the user preferences changed. In this paper, we propose a method to make the preference information be updated and generated automatically in the terminal side, using user's viewing history as feed-back metadata, and implement the system with optimized parameters. In our implementation, TV-Anytime forum's metadata and MPEG-7 user preferences description are utilized for the proposed system on audio-visual contents searching and filtering. For renewal user preferences information, a basic user preference tool ("preferenceValueType") of MPEG-7 User preferences description is adopted to adapt user aspects. In addition the requirements are summarized, and necessary functional components for implementing the proposed system are designed as well as data generation process to use for experiment. The components are audio-visual contents metadata filtering, data structure transformation, and preferences value weighting system. Finally, parameters that are defined in the paper are optimized according to experimental results. It is shown that the optimized value makes the proposed system more effective.

    AB - At the present, audio-visual searching technology is only to filter information from almost infinite amount of contents according to the static user preferences. However, the user preferences are dynamically changed, and it is not convenient to input such varied preferences information every time when the user preferences changed. In this paper, we propose a method to make the preference information be updated and generated automatically in the terminal side, using user's viewing history as feed-back metadata, and implement the system with optimized parameters. In our implementation, TV-Anytime forum's metadata and MPEG-7 user preferences description are utilized for the proposed system on audio-visual contents searching and filtering. For renewal user preferences information, a basic user preference tool ("preferenceValueType") of MPEG-7 User preferences description is adopted to adapt user aspects. In addition the requirements are summarized, and necessary functional components for implementing the proposed system are designed as well as data generation process to use for experiment. The components are audio-visual contents metadata filtering, data structure transformation, and preferences value weighting system. Finally, parameters that are defined in the paper are optimized according to experimental results. It is shown that the optimized value makes the proposed system more effective.

    KW - Metadata

    KW - MPEG-7 User Preferences Description

    KW - Personalization

    KW - TV-Anytime

    UR - http://www.scopus.com/inward/record.url?scp=1542748058&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=1542748058&partnerID=8YFLogxK

    M3 - Conference contribution

    AN - SCOPUS:1542748058

    SN - 0889863806

    VL - 7

    SP - 545

    EP - 551

    BT - Proceedings of the IASTED International Conference on Internet and Multimedia Systems and Applications

    A2 - Hamza, M.H.

    ER -