Abstract: A method to highlight video segments in a video stream, where the method includes receiving a video stream from a video source, identifying a highlight segment within the video stream based on a machine learning model, the highlight segment being deemed to be worthy of replay by the machine learning model, and starting and ending frames of the highlight segment being identified by applying the machine learning model to the video stream and corresponding audio data, and providing an availability indication of the highlight segment in the video stream once the starting and ending frames of the highlight segment are identified.

Abstract: A method for reducing artifacts in streaming video implemented by a computing device involves determining whether a video quality assessment score for a current segment of a channel of a video stream with a first resolution and a first bit rate meets a quality threshold, replacing the current segment with a replacement segment with a lower resolution than the first resolution, in response to the current segment failing to meet the quality threshold, and publishing the replacement segment at the first bit rate as part of the video stream.

Abstract: A method for reducing artifacts in streaming video implemented by a computing device involves determining whether a video quality assessment score for a current segment of a channel of a video stream with a first resolution and a first bit rate meets a quality threshold, replacing the current segment with a replacement segment with a lower resolution than the first resolution, in response to the current segment failing to meet the quality threshold, and publishing the replacement segment at the first bit rate as part of the video stream.

Abstract: A method to highlight video segments in a video stream, where the method includes receiving a video stream from a video source, identifying a highlight segment within the video stream based on a machine learning model, the highlight segment being deemed to be worthy of replay by the machine learning model, and starting and ending frames of the highlight segment being identified by applying the machine learning model to the video stream and corresponding audio data, and providing an availability indication of the highlight segment in the video stream once the starting and ending frames of the highlight segment are identified.

Abstract: A method for video quality assessment implemented by a computing device, where the method includes selecting a first set of frames from an input video source, determining features of the first set of frames for input into a first machine learning model, applying the first machine learning model to the features of the first set of frames to obtain a video quality score and a confidence score, and triggering a retraining of the first machine learning model in response to the confidence score being determined to be out of bounds.

Abstract: A method for reducing artifacts in streaming video implemented by a computing device involves determining whether a video quality assessment score for a current segment of a channel of a video stream with a first resolution and a first bit rate meets a quality threshold, replacing the current segment with a replacement segment with a lower resolution than the first resolution, in response to the current segment failing to meet the quality threshold, and publishing the replacement segment at the first bit rate as part of the video stream.

Abstract: A method for video quality assessment implemented by a computing device, where the method includes selecting a first set of frames from an input video source, determining features of the first set of frames for input into a first machine learning model, applying the first machine learning model to the features of the first set of frames to obtain a video quality score and a confidence score, and triggering a retraining of the first machine learning model in response to the confidence score being determined to be out of bounds.

Abstract: A method for video quality assessment implemented by a computing device, where the method includes selecting a first set of frames from an input video source, determining features of the first set of frames for input into a first machine learning model, applying the first machine learning model to the features of the first set of frames to obtain a video quality score and a confidence score, and triggering a retraining of the first machine learning model in response to the confidence score being determined to be out of bounds.

Abstract: A toy article (10) includes a first body (14), a first engager (16), a first rotation inhibitor (18) and a first coupling element (20). The first engager (16) engages a second engager (16A) of a second toy article (10A) during a battle. The first rotation inhibitor (18) inhibits relative rotation between the first engager (16) and the first body (14) about an axis (37) until a predetermined force by the second toy article (10A) deforms the first rotation inhibitor (18) to allow for relative rotation between the first engager (16) and the first body (14) about the axis (37). The first coupling element (20) couples the first engager (16) to the first body (14). The first coupling element (20) limits movement of the first engager (16) along the axis (37), but allows for relative rotation between the first engager (16) and the first body (14) about the axis (37).