摘要 |
One embodiment of the present invention provides a computer-based system that automatically characterizes a video. During operation, the system extracts feature vectors from sampled frames in the video. Next, the system uses the extracted feature vectors for successive sampled frames in the video to define a curve. The system then determines a set of invariants for the curve. Next, the system using the set of invariants to characterize the video. The system can then use the characterization of the video to perform various operations, such as classifying the video with respect to other videos or detecting duplicates of the video.
|