TR2003-138

Audio/Visual Independent Components


Abstract:

This paper presents a methodology for extracting meaningful audio/visual features from video streams. We propose a statistical method that does not distinguish between the auditory and visual data, but one that operates on a fused data set. By doing so we discover audio/visual features that correspond to events depicted in the stream. Using these features, we can obtain a segmentation of the input video stream by separating independent auditory and visual events.

 

  • Related News & Events

    •  NEWS    ICA 2003: publication by MERL researchers and others
      Date: April 1, 2003
      Where: International Symposium on Independent Component Analysis and Blind Source Separation (ICA)
      Research Area: Speech & Audio
      Brief
      • The paper "Audio/Visual Independent Components" by Smaragdis, P. and Casey, M. was presented at the International Symposium on Independent Component Analysis and Blind Source Separation (ICA).
    •