Intel Corporation

Charu Srivastava

Stanley J Baran

Srikanth Potluri

Changliang Wang

Kristoffer Fleming

James M Holland

Jong Dae Oh

Archie Sharma

Michael D Rosenzweig

Nir Gerber

Qixiong Bian

Satish Kumar Bhrugumalla

Systems and methods for applying style transfer functions in multi-camera systems and multi-microphone systems are disclosed herein. An example multi-camera style transfer system includes at least one memory, instructions in the system, and processor circuitry to execute the instructions to at least apply a style transfer function to a second image from a second video feed to generate a stylized image based on a reference image. The reference image corresponds to a first image from a first video feed. The first video feed is from a first camera. The second video feed is from a second camera. The processor circuitry also executed the instructions to adjust one or more parameter settings of a video filter based on the stylized image, and filter the second video feed using the video filter with the adjusted parameter settings to generate a filtered version of the second video feed.

Systems and methods for applying style transfer functions in multi-camera systems and multi-microphone systems

Methods, apparatus, systems, and articles of manufacture are disclosed to align processing events. An example apparatus includes a comparator to compare a value of a counter to a threshold value, the threshold value associated with an amount of time to defer provision of a first or second input signal to a corresponding first or second IP device, respectively, signal deferring circuitry to defer provision of the first or second input signals to a corresponding one of the first or second IP devices based on an output of the comparator, deferral of the first or second input signals to cause alignment of first and second processing events performed by the first and second IP devices, respectively, and power controlling circuitry to cause the first and second IP devices to power down based on completion of the first and second processing events.

Methods and apparatus to align media workloads

An example apparatus includes image processing circuitry to determine an uncovered region of a background image in a current video frame relative to the background image in a previous video frame, the uncovered region obscured in the previous video frame by a first foreground region of the previous video frame, and the uncovered region uncovered in the current video frame based on movement of a second foreground region in the current video frame relative to the first foreground region of the previous video frame, and encoder circuitry to generate an updated frame portion by encoding the second foreground region and dirty blocks of the background image corresponding to the uncovered region without encoding static blocks of the background image, the static blocks not corresponding to the uncovered region, and store the updated frame portion in the at least one memory.

Methods and apparatus to perform dirty region reads and writes to reduce memory bandwidth usage

Techniques related to implementing an always on face detection architecture at ultra low power are discussed. Such techniques include updating a face detection model at a host processor using positive and/or negative validation of face detection results from an always on microcontroller operating at ultra low power.

Real time adaptive training face detection for ultra low power always on architecture

Growing community of inventors

San Jose, CA, United States of America

Charu Srivastava