Jia-Yu Pan's Publications

Sorted by DateClassified by Publication TypeClassified by Research Category

MMSS: Multi-modal Story-oriented Video Summarization

Jia-Yu Pan, Hyungjeong Yang, and Christos Faloutsos. MMSS: Multi-modal Story-oriented Video Summarization. In Proceedings of the Fourth IEEE International Conference on Data Mining (ICDM 04), 2004.
Brighton, UK, November 01-04, 2004

Download

[PDF]648.1kB  

Abstract

We propose multi-modal story-oriented video summarization (MMSS) which, unlike previous works that use fine-tuned, domain-specific heuristics, provides a domain-independent, graph-based framework. MMSS uncovers correlation between information of different modalities which gives meaningful story-oriented news video summaries. MMSS can also be applied for video retrieval, giving performance that matches the best traditional retrieval techniques (OKAPI and LSI), with no fine-tuned heuristics such as tf/idf.

BibTeX Entry

@InProceedings{ICDM04MMSS,
  author =	 {Jia-Yu Pan and Hyungjeong Yang and Christos Faloutsos},
  title =	 {MMSS: Multi-modal Story-oriented Video Summarization},
  booktitle =	 {Proceedings of the Fourth IEEE International Conference on Data Mining (ICDM 04)},
  year =	 2004,
  wwwnote =	 {Brighton, UK, November 01-04, 2004},
  abstract = {We propose multi-modal story-oriented video summarization (<i>MMSS</i>) which, unlike previous works that use fine-tuned, domain-specific heuristics, provides a domain-independent, <i>graph-based</i> framework. MMSS uncovers correlation between information of different modalities which gives meaningful story-oriented news video summaries. MMSS can also be applied for video retrieval, giving performance that matches the best traditional retrieval techniques (OKAPI and LSI), with no fine-tuned heuristics such as tf/idf.},
  bib2html_pubtype = {Refereed Conference},
  bib2html_rescat = {Multimedia Data Mining},
}

Generated by bib2html (written by Patrick Riley ) on Wed Sep 01, 2004 13:24:30