Method and server for providing media content

A server for providing media content, the server comprising:

• a communication interface;
• a memory storing one or more instructions;
• and
• at least one processor configured to execute the one or more instructions,
• wherein the at least one processor is further configured to execute the one or more instructions to:
• obtain media content comprising video data and audio data, the video data comprising a plurality of video frames;
• obtain scene information by applying object recognition to a first at least one video frame of the plurality of video frames;
• generate at least one scene graph corresponding to the first at least one video frame, based on the scene information;
• obtain first context data representing context of the video data, based on the at least one scene graph;
• obtain scene-sound information by applying at least one of voice recognition, sound event detection, or sound event classification to the audio data;
• obtain second context data representing context of the audio data, based on the scene-sound information;
• based on the first context data and the second context data, generate scene context data corresponding to the plurality of video frames;
• determine user intention information for navigating the media content based on a first user input, wherein the user intention information corresponds to an intention of the user with respect to the first user input;
• identify a second at least one video frame of the plurality of video frames corresponding to the user intention information based on the scene context data;
• and
• output the identified second at least one video frame.

A non-transitory computer-readable recording medium storing one or more instructions, which, when executed by a processor of a server providing media content, causes the server to:

• obtain media content comprising video data and audio data, the video data comprising a plurality of video frames;
• obtain scene information by applying object recognition to a first at least one video frame of the plurality of video frames;
• generate at least one scene graph corresponding to the first at least one video frame, based on the scene information;
• obtain first context data representing context of the video data, based on the at least one scene graph;
• obtain scene-sound information by applying at least one of voice recognition, sound event detection, or sound event classification to the audio data;
• obtain second context data representing context of the audio data, based on the scene-sound information;
• based on the first context data and the second context data, generate scene context data corresponding to the plurality of video frames;
• determine user intention information for navigating the media content based on a user input, wherein the user intention information corresponds to an intention of the user with respect to the user input;
• identify a second at least one video frame of the plurality of video frames corresponding to the user intention information based on the scene context data;
• and
• output the identified second at least one video frame.