Samsung patents method to train video captioning with generated clips
Samsung describes a system that improves how software describes video content by using artificial intelligence to create training data. A large language model writes text descriptions, which a text-to-video model turns into short video clips to help the main captioning model learn better.
In the filing’s own words
A method includes receiving a video as an input to a video captioning model. The method also includes generating one or more captions using the video captioning model. The method also includes outputting the one or more captions. The video captioning model is trained using a large language model that receives a prompt related to a content category and generates a plurality of captions based on the prompt. The plurality of captions is provided to a text-to-video model that generates video counterparts each associated with a caption of the plurality of captions to finetune the video captioning model based on the plurality of captions and the video counterparts.
What exactly they claim (claim 1)
1. A method comprising: receiving a video as an input to a video captioning model; generating one or more captions using the video captioning model; and outputting the one or more captions, wherein the video captioning model is trained using a large language model that receives a prompt related to a content category and generates a plurality of captions based on the prompt, wherein the plurality of captions is provided to a text-to-video model that generates video counterparts each associated with a caption of the plurality of captions to finetune the video captioning model based on the plurality of captions and the video counterparts.
Facts
- Company
- Samsung (Samsung Electronics Co., Ltd.)
- Official title
- GENERATIVE DATA AUGMENTATION FRAMEWORK FOR THE GENERALIZATION OF VIDEO CAPTIONING IN OUT-OF-DISTRIBUTION SCENARIOS
- Publication number
- US20260279018A1
- Application number
- 19081955
- Filed
- Mar 17, 2025
- Published
- Sep 17, 2026
- Inventors
- 1
- Claims
- 20
Classified under
G06V 10/774 Physics & computingG06F 40/30 Physics & computingG06F 40/40 Physics & computingG06V 10/761 Physics & computingG06V 20/41 Physics & computingMore from Samsung in AI & software
- Samsung patents tool to erase objects from photos using AI Sep 24, 2026
- Samsung patents drawing objects into photos with AI Oct 15, 2026
- Samsung patents AI that creates personalized exercise videos Sep 10, 2026
- Samsung patents AI summaries for paused TV shows based on your viewing habits Sep 24, 2026
- Samsung patents turning chat conversations into image prompts Oct 1, 2026
Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.