Abstract: Methods, apparatus, systems and articles of manufacture to generate temporal representations for action recognition systems are disclosed. An example apparatus includes an optical flow computer to compute first optical flows for a video based on computing differences between pairs of frames of the video; an evolution of trajectories (EoT) generator to generate EoT temporal representations of the video based on (a) computing second optical flows of the video and (b) aggregating ones of the second optical flows having different time spans; an action identifier to: identify first actions in the video based on the first optical flows; identify second actions in the video based on the EoT temporal representations; and identify third actions in the video based on frames of the video; and a fuser to determine a fourth action based on a weighted average of the first actions, second actions, and third actions.

Abstract: The present disclosure is directed to systems and methods of optimizing display image quality on display devices having a plurality of display power modes. Each power mode has associated therewith a respective baseline allowable percentage of distorted pixels and a baseline first relationship between an original pixel value and boosted pixel value. Display control circuitry determines a baseline second relationship using the baseline percentage of distorted pixels and the baseline first relationship. The display control circuitry selects a plurality of test distorted original pixel values and determines a respective test first relationship. Using the test distorted original pixel value, the respective test first relationship, and the baseline second relationship, the display control circuitry determines a respective PSNR and value indicative of the change in display image quality for each of the test distorted original pixel values.

Abstract: The present disclosure is directed to systems and methods of reducing display image power consumption while maintaining image quality on display devices having a plurality of display power modes. Each display power mode has associated therewith a defined baseline value (K1,BASELINE) first relationship. A display image includes a baseline percentage under-boosted pixels (Xi,BASELINE). Using the first relationship value (K1,BASELINE) and the pixel percentage (Xi,BASELINE), a baseline second relationship value is determined (K0,BASELINE). The value associated with the second relationship is adjusted to a first plurality of values. At each value, the value associated with the pixel percentage is adjusted to each of a second plurality of values. At each combination of second relationship value and pixel percentage, a respective first relationship value is determined. A first relationship value, second relationship value are selected to provide a reduced power consumption while maintaining image quality.

Abstract: A mechanism is described for facilitating person tracking and data security in machine learning at autonomous machines. A method of embodiments, as described herein, includes detecting, by a camera associated with one or more trackers, a person within a physical vicinity, where detecting includes capturing one or more images the person. The method may further include tracking, by the one or more trackers, the person based on the one or more images of the person, where tracking includes collect tracking data relating to the person. The method may further include selecting a tracker of the one or more trackers as a preferred tracker based on the tracking data.

Abstract: The present disclosure is directed to systems and methods for reducing display image power consumption while maintaining a consistent, objectively measurable, level of image distortion that comports with a display image quality metric. Raw image data is converted to an HSV format. “V” values are extracted from the HSV format raw image data and a histogram generates a plurality of “V” values. HSV format raw image data is provided to at least one layer of a trained CNN to extract a plurality of features. The plurality of “V” values and the plurality of features are provided to an AI circuit to generate a plurality of distortion class value pairs. Each of the distortion class value pairs is weighted based on proximity of display image distortion and the display image quality metric. The distortion class pair providing a display image distortion close to the display image quality metric is applied to the raw image data to generate the display image data.

Abstract: Methods, apparatus, systems and articles of manufacture to generate temporal representations for action recognition systems are disclosed. An example apparatus includes an optical flow computer to compute a first optical flow based on first and second video frames separated by a first amount of time and compute a second optical flow based on third and fourth video frames separated by a second amount of time, the second amount of time different than the first amount of time, and an aggregator to combine the first optical flow and the second optical flow to form an image representing action in a video.

Abstract: A mechanism is described for facilitating recognition, reidentification, and security in machine learning at autonomous machines. A method of embodiments, as described herein, includes facilitating a camera to detect one or more objects within a physical vicinity, the one or more objects including a person, and the physical vicinity including a house, where detecting includes capturing one or more images of one or more portions of a body of the person. The method may further include extracting body features based on the one or more portions of the body, comparing the extracted body features with feature vectors stored at a database, and building a classification model based on the extracted body features over a period of time to facilitate recognition or reidentification of the person independent of facial recognition of the person.

Abstract: The present disclosure is directed to systems and methods of reducing display image power consumption while maintaining image quality on display devices having a plurality of display power modes. Each display power mode has associated therewith a defined baseline value (K1,BASELINE) first relationship. A display image includes a baseline percentage under-boosted pixels (Xi,BASELINE). Using the first relationship value (K1,BASELINE) and the pixel percentage (Xi,BASELINE), a baseline second relationship value is determined (K0,BASELINE). The value associated with the second relationship is adjusted to a first plurality of values. At each value, the value associated with the pixel percentage is adjusted to each of a second plurality of values. At each combination of second relationship value and pixel percentage, a respective first relationship value is determined. A first relationship value, second relationship value are selected to provide a reduced power consumption while maintaining image quality.

Abstract: One embodiment provides for a graphics processor comprising a block of graphics compute units, a graphics processor pipeline coupled to the block of graphics compute units, and a programmable neural network unit including one or more neural network hardware blocks. The programmable neural network unit is coupled with the block of graphics compute units and the graphics processor pipeline. The one or more neural network hardware blocks include hardware to perform neural network operations and activation operations for a layer of a neural network. The programmable neural network unit can configure settings of one or more hardware blocks within the graphics processor pipeline based on a machine learning model trained to optimize performance of a set of workloads.

Abstract: The present disclosure is directed to systems and methods for reducing display image power consumption while maintaining a consistent, objectively measurable, level of image distortion that comports with a display image quality metric. Raw image data is converted to an HSV format. “V” values are extracted from the HSV format raw image data and a histogram generates a plurality of “V” values. HSV format raw image data is provided to at least one layer of a trained CNN to extract a plurality of features. The plurality of “V” values and the plurality of features are provided to an AI circuit to generate a plurality of distortion class value pairs. Each of the distortion class value pairs is weighted based on proximity of display image distortion and the display image quality metric. The distortion class pair providing a display image distortion close to the display image quality metric is applied to the raw image data to generate the display image data.

Abstract: A mechanism is described for facilitating recognition, reidentification, and security in machine learning at autonomous machines. A method of embodiments, as described herein, includes facilitating a camera to detect one or more objects within a physical vicinity, the one or more objects including a person, and the physical vicinity including a house, where detecting includes capturing one or more images of one or more portions of a body of the person. The method may further include extracting body features based on the one or more portions of the body, comparing the extracted body features with feature vectors stored at a database, and building a classification model based on the extracted body features over a period of time to facilitate recognition or reidentification of the person independent of facial recognition of the person.

Abstract: A mechanism is described for facilitating person tracking and data security in machine learning at autonomous machines. A method of embodiments, as described herein, includes detecting, by a camera associated with one or more trackers, a person within a physical vicinity, where detecting includes capturing one or more images the person. The method may further include tracking, by the one or more trackers, the person based on the one or more images of the person, where tracking includes collect tracking data relating to the person. The method may further include selecting a tracker of the one or more trackers as a preferred tracker based on the tracking data.

Abstract: A mechanism is described for facilitating person tracking and data security in machine learning at autonomous machines. A method of embodiments, as described herein, includes detecting, by a camera associated with one or more trackers, a person within a physical vicinity, where detecting includes capturing one or more images the person. The method may further include tracking, by the one or more trackers, the person based on the one or more images of the person, where tracking includes collect tracking data relating to the person. The method may further include selecting a tracker of the one or more trackers as a preferred tracker based on the tracking data.

Abstract: The present disclosure is directed to systems and methods of optimizing display image quality on display devices having a plurality of display power modes. Each power mode has associated therewith a respective baseline allowable percentage of distorted pixels and a baseline first relationship between an original pixel value and boosted pixel value. Display control circuitry determines a baseline second relationship using the baseline percentage of distorted pixels and the baseline first relationship. The display control circuitry selects a plurality of test distorted original pixel values and determines a respective test first relationship. Using the test distorted original pixel value, the respective test first relationship, and the baseline second relationship, the display control circuitry determines a respective PSNR and value indicative of the change in display image quality for each of the test distorted original pixel values.

Abstract: A mechanism is described for facilitating recognition, reidentification, and security in machine learning at autonomous machines. A method of embodiments, as described herein, includes facilitating a camera to detect one or more objects within a physical vicinity, the one or more objects including a person, and the physical vicinity including a house, where detecting includes capturing one or more images of one or more portions of a body of the person. The method may further include extracting body features based on the one or more portions of the body, comparing the extracted body features with feature vectors stored at a database, and building a classification model based on the extracted body features over a period of time to facilitate recognition or reidentification of the person independent of facial recognition of the person.

Abstract: Methods, apparatus, systems and articles of manufacture to generate temporal representations for action recognition systems are disclosed. An example apparatus includes an optical flow computer to compute a first optical flow based on first and second video frames separated by a first amount of time and compute a second optical flow based on third and fourth video frames separated by a second amount of time, the second amount of time different than the first amount of time, and an aggregator to combine the first optical flow and the second optical flow to form an image representing action in a video.

Abstract: A mechanism is described for facilitating recognition, reidentification, and security in machine learning at autonomous machines. A method of embodiments, as described herein, includes facilitating a camera to detect one or more objects within a physical vicinity, the one or more objects including a person, and the physical vicinity including a house, where detecting includes capturing one or more images of one or more portions of a body of the person. The method may further include extracting body features based on the one or more portions of the body, comparing the extracted body features with feature vectors stored at a database, and building a classification model based on the extracted body features over a period of time to facilitate recognition or reidentification of the person independent of facial recognition of the person.

Abstract: A mechanism is described for facilitating recognition, reidentification, and security in machine learning at autonomous machines. A method of embodiments, as described herein, includes facilitating a camera to detect one or more objects within a physical vicinity, the one or more objects including a person, and the physical vicinity including a house, where detecting includes capturing one or more images of one or more portions of a body of the person. The method may further include extracting body features based on the one or more portions of the body, comparing the extracted body features with feature vectors stored at a database, and building a classification model based on the extracted body features over a period of time to facilitate recognition or reidentification of the person independent of facial recognition of the person.

Abstract: A mechanism is described for facilitating person tracking and data security in machine learning at autonomous machines. A method of embodiments, as described herein, includes detecting, by a camera associated with one or more trackers, a person within a physical vicinity, where detecting includes capturing one or more images the person. The method may further include tracking, by the one or more trackers, the person based on the one or more images of the person, where tracking includes collect tracking data relating to the person. The method may further include selecting a tracker of the one or more trackers as a preferred tracker based on the tracking data.

Abstract: This disclosure describes systems, methods, and computer-readable media related to wireless displays with audio skipping. In some embodiments, a plurality of audio packets may be captured. Each of the plurality of audio packets may be analyzed. Analyzing the packets may include determining whether an audio packet of the plurality of audio packets is silent. In response to determining the audio packet of the plurality of audio packets is not silent, an audio non-skip mode may be entered. In response to determining the audio packet of the plurality of audio packets is silent, a determination may be made as to whether an indicator has exceeded a threshold. The indicator may indicate a sequential number of silent audio packets. In response to the indicator indicating the indicator exceeds the threshold, an audio skip mode may be entered. In response to the indicator indicating the indicator has not exceeded the threshold, the audio non-skip mode may be entered.