Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods that detect, utilizing a shape detection neural network, one or more shapes depicted in a digital image. The disclosed systems identify, from the one or more shapes depicted in the digital image, a background region comprising background pixels depicted in the digital image. The disclosed systems determine that the background region depicts solid fill pixels. The disclosed systems determine a prominent color for the solid fill pixels based on determining that the background region depicts solid fill pixels. The disclosed systems generate, from the prominent color, an image layer for the digital image.

Abstract: Digital image text grouping techniques are described. A digital image depicting text is received and a plurality of items of text data are extracted from the digital image. A plurality of text characteristic data is detected, respectively, that is associated with the plurality of items of text data. At least one text group is generated that includes two or more of the plurality of items of text data. The text group is generated by determining similarity of the plurality of items of text data, one to another, based on the plurality of text characteristic data. The at least one text group is presented for display in a user interface.

Abstract: A method of presenting video information to a user includes, at a server computer, obtaining video information including a plurality of frame from a real-time video stream of an electronic game and obtaining ML model data. The method includes determining a presence of at least one event in the video information using a ML model and the ML model data to identify the at least one event. Upon receiving a query from a user for the presence of the at least on event in the video information, the method includes denoting a presence of the at least one event in the video information associated with at least one frame of the plurality of frames of the video information and presenting to the user a visual representation of the at least one frame of the plurality of frames of the video information associated with the at least one event.

Abstract: Described herein is a user interface and method for playback of a highlight video comprising a plurality of video segments. The user interface has one or more of: 1) an area for displaying playback of video; 2) a plurality of segment sections each representing a corresponding video segment that can be viewed by a user, each segment section being visually separated from other video segments so that a user can visually discern where one segment section ends, and another segment section begins; 3) caption information that describes a currently selected video segment; 4) icons that represent events in a video segment displayed in proximity to the corresponding segment section; and 5) controls that are tailored to allow a user to interact with playback of a video segment, toggle between playback of the entire video containing the segment and the segment itself.