Undirected Graphical Models for Video Analysis and Classification

Yan Liu, Jun Yang, Alexander G. Hauptmann

Abstract

Accurate andefficient videoclassification andretrieval demandsthefusion ofmultimodal information andtheuseof intermediate representations. Thispaperdescribes anundirected graphical modelbasedonexponential-family harmonium, whichderives intermediate semantic representations of video databyjointly modeling thetextual andimageinformation inthevideo. Wepropose anextension ofthemodel toderive category-specific video representation andintegrate video classification asapartofthemodeling process. We report satisfactory classification performance onasetof15 video categories fromTRECVIDcollection aswellascomparison ontheeffectiveness ofdifferent inference algorithms.
BibTeX
@inproceedings{liu2007undirected,
  author = {Yan Liu and Jun Yang and Alexander G. Hauptmann},
  title = {{Undirected Graphical Models for Video Analysis and Classification}},
  booktitle = {ICME},
  year = {2007},
  doi = {10.1109/icme.2007.4284945},
}

Loading related content...

Figure