Abstract: Multiple punchouts of a video may be presented based on multiple viewing windows. The video may include visual content having a field of view. Multiple viewing windows may be determined for the video, with individual viewing window defining a set of extents of the visual content. Different punchouts of the visual content may be presented based on the different viewing windows. Individual punchout of the visual content may include the set of extents of the visual content defined by corresponding viewing window.

Abstract: Multiple punchouts of a video may be presented based on multiple viewing windows. The video may include visual content having a field of view. Multiple viewing windows may be determined for the video, with individual viewing window defining a set of extents of the visual content. Different punchouts of the visual content may be presented based on the different viewing windows. Individual punchout of the visual content may include the set of extents of the visual content defined by corresponding viewing window.

Abstract: Multiple punchouts of a video may be presented based on multiple viewing windows. The video may include visual content having a field of view. Multiple viewing windows may be determined for the video, with individual viewing window defining a set of extents of the visual content. Different punchouts of the visual content may be presented based on the different viewing windows. Individual punchout of the visual content may include the set of extents of the visual content defined by corresponding viewing window.

Abstract: Multiple punchouts of a video may be presented based on multiple viewing windows. The video may include visual content having a field of view. Multiple viewing windows may be determined for the video, with individual viewing window defining a set of extents of the visual content. Different punchouts of the visual content may be presented based on the different viewing windows. Individual punchout of the visual content may include the set of extents of the visual content defined by corresponding viewing window.

Abstract: Multiple punchouts of a video may be presented based on multiple viewing windows. The video may include visual content having a field of view. Multiple viewing windows may be determined for the video, with individual viewing window defining a set of extents of the visual content. Different punchouts of the visual content may be presented based on the different viewing windows. Individual punchout of the visual content may include the set of extents of the visual content defined by corresponding viewing window.

Abstract: Multiple punchouts of a video may be presented based on multiple viewing windows. The video may include visual content having a field of view. Multiple viewing windows may be determined for the video, with individual viewing window defining a set of extents of the visual content. Different punchouts of the visual content may be presented based on the different viewing windows. Individual punchout of the visual content may include the set of extents of the visual content defined by corresponding viewing window.

Abstract: Cameras may monitor its operation and automatically switch between operation modes thereby to best capture users' experiences. Auxiliary sensor data collected by the one or more sensors and/or captured image data may be analyzed to determine when a camera should switch to a high-motion operation mode. The auxiliary sensor data include motion information of the camera and the content of the captured images include motion information of the captured objects. When a camera or objects captured by the camera are moving rapidly, the camera is switched to operate at the high-motion operation mode to ensure image quality and minimize artifacts to best capture users' experiences. Motion of the camera may be detected or predicted by analyzing the auxiliary sensor data and motion of the captured objects may be detected by analyzing the captured image data thereby to determine whether or not the camera should switch to the high-motion operation mode.

Abstract: Multiple punchouts of a video may be presented based on multiple viewing windows. The video may include visual content having a field of view. Multiple viewing windows may be determined for the video, with individual viewing window defining a set of extents of the visual content. Different punchouts of the visual content may be presented based on the different viewing windows. Individual punchout of the visual content may include the set of extents of the visual content defined by corresponding viewing window.

Abstract: Multiple punchouts of a video may be presented based on multiple viewing windows. The video may include visual content having a field of view. Multiple viewing windows may be determined for the video, with individual viewing window defining a set of extents of the visual content. Different punchouts of the visual content may be presented based on the different viewing windows. Individual punchout of the visual content may include the set of extents of the visual content defined by corresponding viewing window.

Abstract: Cameras may monitor its operation and automatically switch between operation modes thereby to best capture users' experiences. Auxiliary sensor data collected by the one or more sensors and/or captured image data may be analyzed to determine when a camera should switch to a high-motion operation mode. The auxiliary sensor data include motion information of the camera and the content of the captured images include motion information of the captured objects. When a camera or objects captured by the camera are moving rapidly, the camera is switched to operate at the high-motion operation mode to ensure image quality and minimize artifacts to best capture users' experiences. Motion of the camera may be detected or predicted by analyzing the auxiliary sensor data and motion of the captured objects may be detected by analyzing the captured image data thereby to determine whether or not the camera should switch to the high-motion operation mode.

Abstract: Cameras may monitor its operation and automatically switch between operation modes thereby to best capture users' experiences. Auxiliary sensor data collected by the one or more sensors and/or captured image data may be analyzed to determine when a camera should switch to a high-motion operation mode. The auxiliary sensor data include motion information of the camera and the content of the captured images include motion information of the captured objects. When a camera or objects captured by the camera are moving rapidly, the camera is switched to operate at the high-motion operation mode to ensure image quality and minimize artifacts to best capture users' experiences. Motion of the camera may be detected or predicted by analyzing the auxiliary sensor data and motion of the captured objects may be detected by analyzing the captured image data thereby to determine whether or not the camera should switch to the high-motion operation mode.

Abstract: Cameras may monitor its operation and automatically switch between operation modes thereby to best capture users' experiences. Auxiliary sensor data collected by the one or more sensors and/or captured image data may be analyzed to determine when a camera should switch to a high-motion operation mode. The auxiliary sensor data include motion information of the camera and the content of the captured images include motion information of the captured objects. When a camera or objects captured by the camera are moving rapidly, the camera is switched to operate at the high-motion operation mode to ensure image quality and minimize artifacts to best capture users' experiences. Motion of the camera may be detected or predicted by analyzing the auxiliary sensor data and motion of the captured objects may be detected by analyzing the captured image data thereby to determine whether or not the camera should switch to the high-motion operation mode.

Abstract: Cameras may monitor its operation and automatically switch between operation modes thereby to best capture users' experiences. Auxiliary sensor data collected by the one or more sensors and/or captured image data may be analyzed to determine when a camera should switch to a high-motion operation mode. The auxiliary sensor data include motion information of the camera and the content of the captured images include motion information of the captured objects. When a camera or objects captured by the camera are moving rapidly, the camera is switched to operate at the high-motion operation mode to ensure image quality and minimize artifacts to best capture users' experiences. Motion of the camera may be detected or predicted by analyzing the auxiliary sensor data and motion of the captured objects may be detected by analyzing the captured image data thereby to determine whether or not the camera should switch to the high-motion operation mode.

Abstract: Cameras may monitor its operation and automatically switch between operation modes thereby to best capture users' experiences. Auxiliary sensor data collected by the one or more sensors and/or captured image data may be analyzed to determine when a camera should switch to a different operation mode. The auxiliary sensor data and/or the content of the captured images may include motion information indicating whether the camera or the captured scene has relatively high-motion, relatively low-motion, or no motion. Event(s) may be detected by analyzing the auxiliary sensor data and/or analyzing captured image data, and preferred operation mode(s) suitable for capturing the events can be determined. Each preferred operation mode may be associated with a confidence value. A camera may switch to a preferred operation mode for capturing an event if the event is determined with high confidence to take place at a time point.

Abstract: Cameras may monitor its operation and automatically switch between operation modes thereby to best capture users' experiences. Auxiliary sensor data collected by the one or more sensors and/or captured image data may be analyzed to determine when a camera should switch to a high-motion operation mode. The auxiliary sensor data include motion information of the camera and the content of the captured images include motion information of the captured objects. When a camera or objects captured by the camera are moving rapidly, the camera is switched to operate at the high-motion operation mode to ensure image quality and minimize artifacts to best capture users' experiences. Motion of the camera may be detected or predicted by analyzing the auxiliary sensor data and motion of the captured objects may be detected by analyzing the captured image data thereby to determine whether or not the camera should switch to the high-motion operation mode.

Abstract: Cameras may monitor its operation and automatically switch between operation modes thereby to best capture users' experiences. Auxiliary sensor data collected by the one or more sensors and/or captured image data may be analyzed to determine when a camera should switch to a different operation mode. The auxiliary sensor data and/or the content of the captured images may include motion information indicating whether the camera or the captured scene has relatively high-motion, relatively low-motion, or no motion. Event(s) may be detected by analyzing the auxiliary sensor data and/or analyzing captured image data, and preferred operation mode(s) suitable for capturing the events can be determined. Each preferred operation mode may be associated with a confidence value. A camera may switch to a preferred operation mode for capturing an event if the event is determined with high confidence to take place at a time point.

Abstract: Video and corresponding metadata is accessed. Events of interest within the video are identified based on the corresponding metadata, and best scenes are identified based on the identified events of interest. A video summary can be generated including one or more of the identified best scenes. The video summary can be generated using a video summary template with slots corresponding to video clips selected from among sets of candidate video clips. Best scenes can also be identified by receiving an indication of an event of interest within video from a user during the capture of the video. Metadata patterns representing activities identified within video clips can be identified within other videos, which can subsequently be associated with the identified activities.