Abstract: Embodiments described herein include systems and methods for automatically creating a compilation video from a source video based on metadata associated with the source video. For example, a method for creating a compilation video may include identifying a source video having a plurality of video frames; identifying metadata associated with the plurality of video frames of the source video; comparing the identified metadata with a machine-learned baseline feature set that indicates interesting metadata; determining that a first video frame of the plurality of video frames is associated with at least a portion of the interesting metadata; and creating the compilation video that includes the first frame of the plurality of video frames based on the first video frame being associated with the at least a portion of the interesting metadata.

Abstract: Embodiments described herein include systems and methods for automatically creating compilation videos from a source video based on metadata associated with the source video. For example, a method for creating a compilation video may include receiving a source video having a set of video frames, each video frame in the set of video frames having associated metadata; generating a relevance score for each video frame in the set of video frames based on the associated metadata; selecting a first video frame from the set of video frames based on a first relevance score for the first video frame; and creating the compilation video that includes the first video frame.