To efficiently analyze a structure of an image intrinsic to a domain.
In the method of analyzing a high-level syntax and structure of continuous compressed video based upon a plurality of states, first of all, a set of hidden Markov models for each of the states is trained with a training video segmented into known states. Next, a set of domain specific features are extracted from a fixed-length sliding window of the continuous compressed video, and a set of maximum likelihoods is determined for each set of the domain specific features from the fixed-length sliding window of the continuous compressed video. Finally, dynamic programming is applied to each set of maximum likelihoods to determine a specific state for each fixed-length sliding window of frames of the compressed video.
JP2003173350 | SYSTEM FOR RECOMMENDING MUSIC OR IMAGE CONTENTS |
JPS6257020 | MERGING PROCESS SYSTEM FOR RELATIONAL DATA BASE |
JPH04117561 | DATA BASE SYSTEM |
CHANG SHIH-FU
DIVAKARAN AJAY
SUN HUIFANG
UNIV COLUMBIA
Michiharu Soga
Hidetoshi Furukawa
Suzuki Kenchi
Kajinami order
Next Patent: DATA PROCESSING APPARATUS