Intel Corporation

Silego Technology Inc.

Airmagnet, Inc.

Chen Wang

Yi-Jen Chiu

Kuang-Yu Chen

Huan Dou

Lidong Xu

Ximin Zhang

Jianguo Li

Xiaoxia Cai

Joe Froniewski

Sang-hee Lee

Ya-Ti Peng

Ke Chen

Jie Chen

Ting-Yen Chiang

Terrin Eager

Yalun Li

Hyunbae Kim

Bin Robin Wang

An apparatus for super resolution imaging includes a convolutional neural network () to receive a low resolution frame () and generate a high resolution illuminance component frame. The apparatus also includes a hardware scaler () to receive the low resolution frame () and generate a second high resolution chrominance component frame. The apparatus further includes a combiner () to combine the high resolution illuminance component frame and the high resolution chrominance component frame to generate a high resolution frame ().

Super resolution using convolutional neural network

A method for image content classification is described herein. The method includes counting a number of distinct color numbers in an image. The method also includes clustering blocks with a same distinct color number into a same class and determining a block occupancy rate of each color number for the image. Finally, the method includes classifying the image according to the block occupancy rate via a plurality of classifiers communicatively coupled in series.

Image content classification

An example apparatus for enhancing video includes a decoder to decode a received 360-degree projection format video bitstream to generate a decoded 360-degree projection format video. The apparatus also includes a viewport generator to generate a viewport from the decoded 360-degree projection format video. The apparatus further includes a convolutional neural network (CNN)-based filter to remove an artifact from the viewport to generate an enhanced image. The apparatus further includes a displayer to send the enhanced image to a display.

Enhancing 360-degree video using convolutional neural network (CNN)-based filter

Techniques related to accelerated video enhancement using deep learning selectively applied based on video codec information are discussed. Such techniques include applying a deep learning video enhancement network selectively to decoded non-skip blocks that are in low quantization parameter frames, bypassing the deep learning network for decoded skip blocks in low quantization parameter frames, and applying non-deep learning video enhancement to high quantization parameter frames.

Video codec assisted real-time video enhancement using deep learning

In one exemplary embodiment, a process for detecting a phone includes monitoring wirelessly transmitted traffic between first and second stations. Next, the process determines whether the traffic sent in both directions between the first and second stations are close to each other in term of traffic volume. The process identifies a total frames count of a number of frames of an identical frame size transmitted, where the number of frames is greater than any number of frames of a same size. The process calculates the percentage of the count that was just collected out of the count of the total frames. The process identifies the first station as a phone if the calculated percentage is over a first threshold and the total frames count is over a second threshold.

Methods to detect wireless stations in a wireless local area network

A clock driving circuit and a method of driving a plurality of output lines for a PC architecture are disclosed. The clock driving circuit includes a clock generating circuit coupled to an output buffer for the PC having a plurality of output lines connected to a plurality of output loads having output load impedances. The output lines are driven differentially at an output voltage lower than a supply voltage. The circuit includes a voltage node having a voltage node impedance. The voltage node is maintained at substantially the output voltage. The circuit includes a current sinking transistor that sinks current from the voltage node. The current sinking transistor is operated in a linear region characterized by an ohmic resistance determined by the size of the current sinking transistor. The impedance of the voltage node is matched to one of the load impedances by sizing the current sinking transistor.

Reduced power output buffer

In one exemplary embodiment, voice quality of Voice over IP data in a wireless network is measured by first receiving at a detector in the wireless network a set of wireless frames transmitted between a first wireless device and a second wireless device in the wireless network in a predetermined time period. The wireless frames in the set carry Voice over Internet Protocol data. A rating value indicative of voice quality is determined based on the loss rate and burst rate that are determined only using frames received by the detection during monitoring.

Voice quality measurement for voice over IP in a wireless local area network

A line driver and a method for driving a line are disclosed. The line driver includes a first current device configured to initiate a change in the state of the line and a second current device configured to substantially complete the change. The first current device provides a first current and the second current device provides a second current that is smaller than the first current.

Growing community of inventors

San Jose, CA, United States of America

Chen Wang