Abstract: The present invention provides a method and system for automatically reframing and transforming videos to different aspect ratios, such that the source video has a fixed resolution and multiple outputs of different aspect ratios are generated. The present invention automatically reframes and transforms horizontal videos into vertical, portrait, square, and/or landscape for social media distribution. The method comprises acquiring input video details; extracting audio; detecting shot change points and extracting frames; detecting salient regions; detecting text; generating and stabilizing viewports; applying genre-specific transformations and generating transformed images; recreating text; obtaining output frames; generating videos and uploading the reframed and transformed videos into cloud. The present invention helps to reframe and transform videos by maintaining the visibility of regions of interest.

Abstract: A system (700) including a media comparison engine (MCE) (507) and a method for determining matches between frames in media assets for automating downstream media workflows are provided. For a target master frame in each boundary of master shots of a master media asset (MMA), the MCE (507) performs a comparison with each source frame from each source media asset (SMA), in an optimal search space, using computed signatures; determines matches in the optimal search space; computes a rate of information exchange (RIE) score for each match based on the signature(s) and similarity scores of each source frame in a final search space; identifies a best match based on the RIE score of each match; performs a comparison of source frames subsequent to the best matching source frame with master frames subsequent to the target master frame.

Abstract: A system (700) including a media comparison engine (MCE) (507) and a method for determining matches between frames in media assets for automating downstream media workflows are provided. For a target master frame in each boundary of master shots of a master media asset (MMA), the MCE (507) performs a comparison with each source frame from each source media asset (SMA), in an optimal search space, using computed signatures; determines matches in the optimal search space computers a rate of information exchange (RIE) score for each match based on the signature(s) and similarity scores of each source frame in a final search space; identifies a best match based on the RIE score of each match; performs a comparison of source frames subsequent to the best matching source frame with master frames subsequent to the target master frame.