Process and system for identifying a position in video using content-based video timelines

摘要

The method involves generating a signature sequence from content of a version of the video. Another signature is generated from content of another version of the video. The signature sequences are compared to determine a match. Positions of annotations in the latter version of the video are recovered corresponding to positions of the annotations in the former version of the video. Independent claims are also included for the following: (a) a computer-readable medium having computer-executable instructions for performing the method of processing a video (b) a video position identification system.