Method Of Learning Structure Of Video

  • Published: Jul 21, 2005
  • Earliest Priority: Dec 12 2003
  • Family: 3
  • Cited Works: 0
  • Cited by: 4
  • Cites: 0
  • Additional Info: Published

The full document isn't yet available to us from the patent office, but we've found a related patent (family member) to use for our images and PDF.


<P>PROBLEM TO BE SOLVED: To provide a method for learning a structure of a video in unmanaged setting to detect events within the video consistent with the structure of the video. <P>SOLUTION: Sets of features are selected. From the selected features, a hierarchical statistical model is updated, and an information gain of the hierarchical statistical model is evaluated. Next, redundant features are filtered out and the hierarchical statistical model is updated based on the filtered features. A Bayesian information criteria is applied to each model and the feature set pair, which can then be rank ordered according to the criteria to detect the events in the video. <P>COPYRIGHT: (C)2005,JPO&NCIPI


Information currently unavailable.

Family Member PDF
Family Member Preview
These are the images from a related family member, as the full document isn't yet available to us from the patent office.
Document History
  • Publication: Jul 21, 2005
  • Application: Dec 9, 2004
    JP 2004357093 A
  • Priority: Dec 12, 2003
    US US 73445103 A

Sign in to the Lens