Method and system for providing video content based on image
AssigneeKorea Advanced Institute of Science and Technology
InventorsJunKyun Choi, Kyu Yeong Jeon, JinHong Yang, YongRok Kim
Life of this patent
Estimating the term…
Abstract
Disclosed is a method for providing a content, the method including extracting at least one still image from video included in the content, extracting audio, which corresponds to the still image, and generating a script corresponding to the audio, adding a caption to the still image based on the generated script, and providing the content in response to a request of consumption to the content and providing the caption-added still image for the video that is streaming in real time.
Claims15
A method for providing content, the method comprising:
- extracting at least one still image from video included in the content;
- extracting audio, which corresponds to the still image, and generating a script corresponding to the audio;
- adding a caption to the still image based on the generated script;
- and
- providing the content in response to a request of consumption to the content and providing the caption-added still image for the video that is streaming in real time.
A computer-readable medium with an instruction controlling a computer system to provide a content, wherein the instruction controls the computer system by a method comprising:
- extracting at least one still image from video included in the content;
- extracting audio, which corresponds to the still image, and generating a script corresponding to the audio;
- adding a caption to the still image based on the generated script;
- and
- providing the content in response to a request of consumption to the content and providing the caption-added still image for the video that is streaming in real time.
A system for providing content, the system comprising:
- an extraction part configured to extract at least one still image from video included in the content;
- a generation part configured to extract audio, which corresponds to the still image, and generating a script corresponding to the audio;
- an addition part configured to add a caption to the still image based on the generated script;
- and
- a provision part configured to provide the content in response to a request of consumption to the content and providing the caption-added still image for the video that is streaming in real time.
Dependencies are inferred from the claim text.