TR2004-128

Discovering Meaningful Multimedia Patterns with Audio-Visual Concepts and Associated Text


    •  Xie, L., Kennedy, L., Chang, S.-F., Divakaran, A., Sun, H., Lin, C.-Y., "Discovering Meaningful Multimedia Patterns with Audio-Visual Concepts and Associated Text", IEEE International Conference on Image Processing (ICIP), October 2004, vol. 4, pp. 2383-2386.
      BibTeX TR2004-128 PDF
      • @inproceedings{Xie2004oct,
      • author = {Xie, L. and Kennedy, L. and Chang, S.-F. and Divakaran, A. and Sun, H. and Lin, C.-Y.},
      • title = {Discovering Meaningful Multimedia Patterns with Audio-Visual Concepts and Associated Text},
      • booktitle = {IEEE International Conference on Image Processing (ICIP)},
      • year = 2004,
      • volume = 4,
      • pages = {2383--2386},
      • month = oct,
      • issn = {1522-4880},
      • url = {https://www.merl.com/publications/TR2004-128}
      • }
  • MERL Contact:
Abstract:

This paper presents algorithms for finding the meanings of the audio-visual video patterns obtained in the unsupervised discovery process. This problem is interesting in domains where neither perceptual patterns nor semantic concepts have simple structures. The patterns in the video are modeled with hierarchical hidden Markov models, with efficient algorithms to jointly learn the model parameters, the optimal model complexity, as well as the relevant feature subsets. The meanings are contained in words of the speech transcript of the video. The pattern-word association is obtained via co-occurrence analysis and machine translation models. Promising results are obtained on TRECVID news videos: video patterns that associate with distinct topics such as el-nino and politics are itentified; a temporal structure model compares favorably to a non-temporal clustering algorithm.

 

  • Related News & Events

    •  NEWS    ICIP 2004: 6 publications by Anthony Vetro, Ajay Divakaran and Huifang Sun
      Date: October 24, 2004
      Where: IEEE International Conference on Image Processing (ICIP)
      MERL Contacts: Anthony Vetro; Huifang Sun
      Brief
      • The papers "Nonlinear Warping Function Recovery by Scan-Line Search Using Dynamic Programming" by Porikli, F.M., "A Hidden Markov Model Framework for Traffic Event Detection Using Video Features" by Li, X. and Porikli, F.M., "Adaptive Fuzzy Post-Filtering for Highly Compressed Video" by Kong, H.S., Nie, Y., Vetro, A., Sun, H. and Barner, K., "An Investigation of 3D Dual-Tree Wavelet Transform for Video Coding" by Wang, B., Wang, Y., Selesnick, I. and Vetro, A., "Video Mining: Pattern Discovery Versus Pattern Recognition" by Divakaran, A., Peker, K.A., Chang, S.-F., Radhakrishnan, R. and Xie, L. and "Discovering Meaningful Multimedia Patterns with Audio-Visual Concepts and Associated Text" by Xie, L., Kennedy, L., Chang, S.-F., Divakaran, A., Sun, H. and Lin, C.-Y. were presented at the IEEE International Conference on Image Processing (ICIP).
    •  
    •  AWARD    ICIP 2004 Best Student Paper Award
      Date: January 1, 2004
      Awarded to: L. Xie, L. Kennedy, S.-F. Chang, A. Divakaran, H. Sun, and C.-Y. Lin
      Awarded for: "Discovering Meaningful Multimedia Patterns with Audio-Visual Concepts and Associated Text"
      Awarded by: IEEE International Conference on Image Processing (ICIP)
      MERL Contact: Huifang Sun
    •