Abstract: Framing options of different types may be determined for various moments in the video based on one or more aspects of the video. The aspects of the video may include capture aspects of the video (e.g., how the image capture device moved during capture of the video) and/or content aspects (e.g., what is captured/depicted within the video) of the video. The video may be framed by automatically switching between different framing options based on a priority matrix. The values of the priority matrix may be set/updated based on user data to provide views of the video that are customized for the user. The framing options selected for the video may be used to select which moments of the video are included in the framed video (e.g., video edit with the framed views, video playback with the framed views). The present disclosure may be used to automatically determine which spatial extents and which temporal parts of the video are included in the framed video.

Abstract: An image capture device may capture visual content of a video. During the capture of the video, a user may perform a framing interaction with the image capture device. The framing interaction with the image capture device may provide information/instruction on how the visual content being captured by the image capture device should be framed. The framing interaction with the image capture device may assign a direction of the visual content for framing. The framing interaction performed during the capture of the visual content may be used to frame the visual content after capture.

Abstract: A wide field of view video is split into multiple perspective projections, with individual perspective projections providing a two-dimensional view of a spatial extent of the wide field of view video. Object detection is performed within individual perspective projections to determine the placement of the objects within individual perspective projections. The placement of the objects are projected back into the wide field of view video to merge the detections. Redundant detection are filtered out and the remaining detections are used to perform object tracking in the wide field of view video.

Abstract: A wide field of view video is split into multiple perspective projections, with individual perspective projections providing a two-dimensional view of a spatial extent of the wide field of view video. Object detection is performed within individual perspective projections to determine the placement of the objects within individual perspective projections. The placement of the objects are projected back into the wide field of view video to merge the detections. Redundant detection are filtered out and the remaining detections are used to perform object tracking in the wide field of view video.