• DocumentCode
    1299240
  • Title

    Neural networks for intelligent multimedia processing

  • Author

    Kung, S.Y. ; Hwang, Jenq-Neng

  • Author_Institution
    Princeton Univ., NJ, USA
  • Volume
    14
  • Issue
    4
  • fYear
    1997
  • fDate
    7/1/1997 12:00:00 AM
  • Firstpage
    44
  • Lastpage
    45
  • Abstract
    Multimedia technologies represent new ground for research interactions among a variety of media such as speech, audio, image, video, text, and graphics. Future multimedia technologies will need to handle information a with an increasing level of intelligence, i.e., automatic recognition and interpretation of multimodal signals. The main attribute of neural processing is its adaptive learning capability, which enables machines to be taught to interpret possible variations of a same object or pattern, e.g. scale, orientation, and perspective. Moreover, we are able to accurately approximate unknown systems based on sparse sets of noisy data. In addition, spatial/temporal neural structures and hierarchical models are promising for multirate, multiresolution multimedia processing
  • Keywords
    adaptive systems; learning (artificial intelligence); multimedia communication; neural nets; signal processing; adaptive learning; audio; automatic signal interpretation; automatic signal recognition; graphics; hierarchical models; image; intelligent multimedia processing; multimedia technologies; multimodal signals; multirate processing; multiresolution multimedia processing; neural networks; neural processing; noisy data; orientation; scale; spatial/temporal neural structures; speech; text; video; Artificial neural networks; Content based retrieval; Face detection; IEEE Press; Indexing; Intelligent networks; MPEG 7 Standard; Neural networks; Pattern recognition; Speech;
  • fLanguage
    English
  • Journal_Title
    Signal Processing Magazine, IEEE
  • Publisher
    ieee
  • ISSN
    1053-5888
  • Type

    jour

  • DOI
    10.1109/79.598594
  • Filename
    598594