Jia-Yu Pan's Publications

Sorted by DateClassified by Publication TypeClassified by Research Category

"Geoplot": Spatial Data Mining on Video Libraries

Jia-Yu Pan and Christos Faloutsos. "Geoplot": Spatial Data Mining on Video Libraries. In Proceedings of the Eleventh International Conference on Information and Knowledge Management (CIKM 2002), 2002.
Mclean, VA (near Washington DC), November 4-9, 2002

Download

[PDF]455.4kB  [gzipped postscript]500.5kB  [HTML]3.9kB  

Abstract

Are ``tornado'' touchdowns related to ``earthquakes''? How about to ``floods'', or to ``hurricanes''? In Informedia \citeinformedia, using a gazetteer on news video clips, we map news onto points on the globe and find correlations between sets of points. In this paper we show how to find answers to such questions, and how to look for patterns on the geo-spatial relationships of news events. The proposed tool is ``\gplotns'', which is fast to compute and gives a lot of useful information which traditional text retrieval can not find.We describe our experiments on 2 year worth of video data ($\approx$ 20 Gbytes). There we found that \gplot can find unexpected correlations that text retrieval would never find, such as those between ``earthquake'' and ``volcano'', and ``tourism'' and ``wine''.In addition, \gplot provides a good visualization of a data set's characteristics. Characteristics at all scale are shown in one plot and a wealth of information is given, for example, geo-spatial clusters, characteristic scales, and intrinsic (fractal) dimensions of the events' locations.

BibTeX Entry

@InProceedings{cikm2002Geoplot,
  author =	 {Jia-Yu Pan and Christos Faloutsos},
  title =	 {"Geoplot": Spatial Data Mining on Video Libraries},
  booktitle =	 {Proceedings of the Eleventh International Conference on Information and Knowledge Management (CIKM 2002)},
  year =	 2002,
  wwwnote =	 {Mclean, VA (near Washington DC), November 4-9, 2002},
  abstract =	 {Are ``tornado'' touchdowns related to ``earthquakes''? 
How about to ``floods'', or to ``hurricanes''? In Informedia~\cite{informedia}, using a gazetteer on news video clips, we map news onto points on the globe and find correlations between sets of points. In this paper we show how to find answers to such questions, and how to look for patterns on the geo-spatial relationships of news events. The proposed tool is ``\gplotns'', which is fast to compute and gives a lot of useful information which traditional text retrieval can not find.
We describe our experiments on 2 year worth of video data ($\approx$ 20 Gbytes). There we found that \gplot can find unexpected correlations that text retrieval would never find, such as those between ``earthquake'' and ``volcano'', and ``tourism'' and ``wine''.
In addition, \gplot provides a good visualization of a data set's characteristics. Characteristics at all scale are shown in one plot and a wealth of information is given, for example, \textit{geo-spatial clusters}, \textit{characteristic scales}, and \textit{intrinsic (fractal) dimensions} of the events' locations.},
  bib2html_pubtype = {Refereed Conference},
  bib2html_rescat = {Multimedia Data Mining},
}

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