Abstract: Systems and methods herein are for a video encoder to be associated with a temporal filter and a coding tree and that can perform a main pass for video encoding using individual video blocks towards prediction of at least one frame associated with the media stream, where the coding tree is associated with a lookahead pass, and where the temporal filter can enable denoising within the lookahead pass to reduce an effect of noise in one or more of motion estimation or mode selection of the video encoding.

Abstract: Systems and methods disclosed herein may include or use a video encoder and an inference sub-system. The inference sub-system may infer a quantization matrix (QM) level from video or frame statistics within features of a media stream. The video encoder may use the QM level to apply a QM for the video encoder. The QM may be used in the video encoder for encoding the media stream.

Abstract: Systems and methods herein are for a video encoder to be associated with a rate optimization distortion (RDO) module and a calibration module, where the RDO module may be to perform RDO for received frames of a media stream and may be to generate at least an RDO output that is based in part on quality measures between the received frames and decoded frames, and where the calibration module may be to provide an evaluation metric that is to scale or transform at least a range of the quality measures, with the scaling or transforming to potentially reduce an effect on a compression performed in the video encoder.

Abstract: A method for performing content-based video compression using reinforcement learning (RL) is provided. The method includes obtaining frame information associated with a frame from a video. The frame information comprises quantization parameter (QP) information associated with the frame, and the QP information indicates an initial compression level for encoding aspects of the frame. The frame information and additional information are processed by an RL agent to generate a generated QP map indicating a plurality of updated values associated with a plurality of macro-blocks (MBs) of the frame. A bitstream is generated comprising a plurality of bits for the frame based on the generated QP map. Specifically, the plurality of updated values from the generated QP map indicates an amount of allocated bits from the bitstream to allocate for each of the plurality of MBs. The bitstream is provided to a downstream model.

Abstract: In one embodiment, a device includes clock circuitry including an oscillator to generate a local clock signal having a clock frequency, and a hardware clock to maintain a local clock responsively to the clock signal, at least one sensor to measure at least one value of at least one environmental parameter, processing circuitry to find at least one value of at least one filter parameter based on the at least one value of the at least one environmental parameter, and a filter to receive an error signal between a remote clock and the local clock, and filter the error signal and generate an adjustment to cause the clock circuitry to adjust the local clock signal or the local clock based on the at least one value of the at least one filter parameter.

Abstract: Systems and methods herein are for a video encoder to be associated with a rate optimization distortion (RDO) module and a calibration module, where the RDO module may be to perform RDO for received frames of a media stream and may be to generate at least an RDO output that is based in part on quality measures between the received frames and decoded frames, and where the calibration module may be to provide an evaluation metric that is to scale or transform at least a range of the quality measures, with the scaling or transforming to potentially reduce an effect on a compression performed in the video encoder.

Abstract: Systems and methods herein are for a video encoder to be associated with a temporal filter and a coding tree and that can perform a main pass for video encoding using individual video blocks towards prediction of at least one frame associated with the media stream, where the coding tree is associated with a lookahead pass, and where the temporal filter can enable denoising within the lookahead pass to reduce an effect of noise in one or more of motion estimation or mode selection of the video encoding.

Abstract: A method for performing content-based video compression using reinforcement learning (RL) for video rate control for a downstream task is provided. The method includes processing frame information associated with a raw frame from a video using an RL agent to generate quantization parameter (QP) information that indicates one or more values associated with a compression level of the raw frame and encoding the raw frame into a bitstream based on the QP information. The method further includes reconstructing the raw frame using the bitstream to obtain a reconstructed frame and processing the raw frame as well as the reconstructed frame using a pre-trained downstream model to generate two outputs. The method then includes determining a downstream task reward based on the two outputs and training the RL agent based on the downstream task reward.

Abstract: A method for performing content-based video compression using reinforcement learning (RL) is provided. The method includes obtaining frame information associated with a frame from a video. The frame information comprises quantization parameter (QP) information associated with the frame, and the QP information indicates an initial compression level for encoding aspects of the frame. The frame information and additional information are processed by an RL agent to generate a generated QP map indicating a plurality of updated values associated with a plurality of macro-blocks (MBs) of the frame. A bitstream is generated comprising a plurality of bits for the frame based on the generated QP map. Specifically, the plurality of updated values from the generated QP map indicates an amount of allocated bits from the bitstream to allocate for each of the plurality of MBs. The bitstream is provided to a downstream model.

Abstract: In one embodiment, a system includes clock circuitry to generate a local clock signal, the clock circuitry including an oscillator, clock synchronization circuitry to adjust the local clock signal based on a remote clock, and a processor to train a machine learning model to predict a frequency or a frequency adjustment for applying to the local clock signal during clock holdover.

Abstract: In one embodiment, a device includes clock circuitry including an oscillator to generate a local clock signal having a clock frequency, and a hardware clock to maintain a local clock responsively to the clock signal, at least one sensor to measure at least one value of at least one environmental parameter, processing circuitry to find at least one value of at least one filter parameter based on the at least one value of the at least one environmental parameter, and a filter to receive an error signal between a remote clock and the local clock, and filter the error signal and generate an adjustment to cause the clock circuitry to adjust the local clock signal or the local clock based on the at least one value of the at least one filter parameter.

Abstract: Systems and methods herein are for a video encoder to be associated with a temporal filter and a coding tree and that can perform a main pass for video encoding using individual video blocks towards prediction of at least one frame associated with the media stream, where the coding tree is associated with a lookahead pass, and where the temporal filter can enable denoising within the lookahead pass to reduce an effect of noise in one or more of motion estimation or mode selection of the video encoding.

Abstract: Systems and methods herein are for at least one execution unit that can perform an inference using a machine learning (ML) model and that is coupled to a video encoder, where the ML model can determine a genre associated with received frames of a media stream based in part on using ML model features associated with different genres, where the video encoder can encode the media stream based in part on the determined genre.

Abstract: A system includes a processing device to receive video content, metadata related to the video content, and a target bit rate for encoding the video content. The processing device further detects a content type of the video content based on the metadata and encodes hardware to perform frame encoding on the video content. The system further includes a controller coupled between the processing device and the encoding hardware. The controller is programmed with machine instructions to generate first QP values on a per-frame basis using a frame machine learning model with a first plurality of weights. The first plurality of weights depends at least in part on the content type and the target bit rate. The controller further provides the first QP values to the encoding hardware for rate control of the frame encoding.

Abstract: A method for photogrammetric measurement includes capturing a sequence of images of an infant lying in a crib and processing the images so as to extract a skeleton of the infant from one or more of the images. A height of the infant is estimated based on the extracted skeleton.

Abstract: Systems and methods herein are for a video encoder to be associated with a rate optimization distortion (RDO) module and a calibration module, where the RDO module may be to perform RDO for received frames of a media stream and may be to generate at least an RDO output that is based in part on quality measures between the received frames and decoded frames, and where the calibration module may be to provide an evaluation metric that is to scale or transform at least a range of the quality measures, with the scaling or transforming to potentially reduce an effect on a compression performed in the video encoder.

Abstract: A system includes a processing device to receive a video content, a quality metric, and a target bit rate for encoding the video content. The system includes encoding hardware to perform frame encoding on the video content and a controller coupled between the processing device and the encoding hardware. The controller is programmed with machine instructions to generate first QP values on a per-frame basis using a frame machine learning model with a first plurality of weights. The first plurality of weights depends at least in part on the quality metric and the target bit rate. The controller is further programmed to provide the first QP values to the encoding hardware for rate control of the frame encoding.

Abstract: Systems and methods herein are for a video encoder to be associated with an interface that is to receive, from an application, at least one metric that is associated with a quality preference for video compression to be performed by the video encoder and that is to provide a weight map to enable the video encoder to perform rate-distortion optimization (RDO) for received frames from the application using the weight map to weigh one or more first blocks associated with an individual one of the frames more than one or more second blocks associated with the individual one of the frames.

Abstract: Approaches in accordance with various illustrative embodiments provide for the determination and/or optimization the quality of an image or video, such as an image that has been compressed for transmission or storage then decompressed for presentation. Weights can be determined for a set of weight-based quality metrics to produce an overall quality metric that is a weighted combination of these metrics. Because different portions of an image or video frame may have different types of features, an image or video frame can be divided into blocks of pixels, for example, with different weights being assigned to different blocks using quality metrics. Different metrics can be considered as points in a high-dimensional weight space, with each dimension corresponding to a weight of a block. A combination of these points results in an improved quality metric. Compression settings can be updated based in part upon the overall quality metric values.

Abstract: One or more computing devices, systems, and/or methods for selecting content items for transmission to client devices are provided. A request for content associated with a client device may be received. Bid values and/or click probabilities associated with content items may be determined. A probability of receiving a negative signal associated with a content item of the content items from the client device responsive to presenting the content item via the client device may be determined based upon a user profile associated with the client device. A content item score, of content item scores associated with the content items, may be generated based upon the probability, a click probability and/or a bid value associated with the content item. The content item may be selected from the content items for presentation via the client device based upon the content item scores. The content item may be transmitted to the client device.