Abstract: Various examples are directed to systems and method for creating a summary video of user content comprising a plurality of frames of data. A summarization engine may identify from the user content a first region-of-interest and a second region-of-interest. The summarization engine may generate a first content clip that comprises the first region-of-interest and has a first time length. The summarization engine may receive a new input variable for the summary video. The summarization engine may determine a modified first time length of the first content clip and generate a modified first content clip having the first modified time length. The summarization engine may generate the summary video including the modified first content clip.

Abstract: The present invention relates to a method and device for generating a description file about a video sequence at a server device for a client device, to retrieve a video segment and containing a region of interest. The method comprising for each video segment, determining a time interval during which the detected region of interest is spatially included in a same frame region in the video sequence; and generating a description file comprising spatial information describing the frame region and temporal information describing a duration at least equal to the determined time interval.