Abstract
Disclosed herein is an improved mechanism for generating condensed videos. The mechanism can identify a video for which a condensed video is to be generated. The mechanism can generate a summary transcript of the video. The mechanism can identify frames of the video that are deemed most relevant to portions of the generated summary transcript. Based on the identified frames of the video that are deemed most relevant to portions of the generated summary transcript, the mechanism can generate additional frames of video content that are used to connect the identified relevant frames of the video. The mechanism can then generate a condensed video by stitching together the identified frames of the video and the generated additional frames of video content.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Carbune, Victor and Damian, Alexandru, "Generating Condensed Videos", Technical Disclosure Commons, (May 27, 2020)
https://www.tdcommons.org/dpubs_series/3269