Unsupervised video summarization with piecewise linear interpolation
AssigneeInha University Research and Business Foundation
InventorsGeun Sik Jo, Ui Nyoung Yoon
Life of this patent
Estimating the term…
Abstract
Aspects of the present invention provide an approach for reinforcement learning for unsupervised video summarization with piecewise linear interpolation. A candidate importance score is anticipated by training a video summarization network using a set of video frames in a video. The candidate importance score is interpolated with respect to other candidate importance scores in the video in order to generate a selection probably for each frame of the video. A video summarization that includes a set of selected frames is generated frame selection probability.
Claims10
A method for video summarization, comprising:
- anticipating, by a video summarization system, a candidate importance score by training of the video summarization network using a set of video frames in a video;
- interpolating the candidate importance score with respect to other candidate importance scores in the video in order to generate a selection probability for each frame of the video;
- and
- generating a video summarization that includes a set of selected frames based on the generated frame selection probability.
A video summarization system, comprising:
- a memory medium comprising instructions;
- a bus coupled to the memory medium;
- and
- a processor coupled to the bus that when executing the instructions causes the system to:
- anticipate a candidate importance score by training of the video summarization network using a set of video frames in a video;
- interpolate the candidate importance score with respect to other candidate importance scores in the video in order to generate a selection probability for each frame of the video;
- and
- generate a video summarization that includes a set of selected frames based on the generated frame selection probability.
Dependencies are inferred from the claim text.