Alibaba Group Holding Limited

Shenzhen China Star Optoelectronics Technology Co., Ltd.

Huawei Technologies Co., Limited

Boe Technology Group Co., Ltd.

Beijing Xiaomi Mobile Software Co., Ltd.

Abb Schweiz Ag

Abb Research Ltd.

Tcl China Star Optoelectronics Technology Co., Ltd.

Ordos Yuansheng Optoelectronics Co., Ltd.

The Boeing Company

Sz Dji Technology Co., Ltd.

Ge Precision Healthcare LLC

Honor Device Co., Ltd.

O2micro International Limited

State Grid Corporation of China

Zhao Wang

Yan Ye

Jiancong Luo

Siwei Ma

Hang Yin

Haitao Yang

Jun Xiao

Shiqi Wang

Jian Zhang

Lei Zhang

Gang Wang

Jiangbing Xie

Dan Cao

Ying Li

Yafang Zhang

Dong Wang

Qiang Zhang

Jinfeng Liu

Yao Liang Chen

Shan Gao

Bernhard Deck

RongRong Yu

Mingjong Jou

Fengcheng Xu

Haiyan Xu

Huan Tang

Fuyi Wang

Xianhui Dong

Wenlong Zhao

Hyunjin Kim

Shurun Wang

Wenbo Tian

Bolin Chen

Lin Ma

Xiaozhen Zheng

Jun Li

Ru-Ling Liao

Rui Zhang

Yu Wu

Xiquan Zhang

Yu-Yeh Chen

Jianping Wang

Yongchuan Lai

Zhe Yang

Le Sun

Zhuoyi Lv

Qing Yu

Cong Chen

Hector Zelaya De La Parra

Robert Saers

Yin-hung Chen

Lingsong Zhou

Xin Jiang

Pengfei Lu

Jianbo Zhu

Xianglong Li

Xiaoling Li

Chengbin Liu

Lei Jing

Dave Xiao Dong Yang

Ruiqing Xu

Pengshuai Wang

Xiaoxia Yang

Xiaobing Dong

Jukka Kinnunen

Yifeng Ding

Zhencao Zhang

Fulin Cheng

Lianjie Tao

Shuyan Guo

Ding Yu

Yini Wang

Shuang Zeng

Anqi Liang

Mingquan Qiu

Ping Chen

Qijing Xing

Dapeng Duan

Huanna Niu

Xuwu Ge

Zongsheng Li

Hanbei Zhang

Changyue Ma

Xiaoqiang Cui

Li Dongsheng

Ji Shengcheng

Jun Lin

Qi Ge

Hongming Liang

Xunqiang Wang

Dave Xiaodong Yang

David Xiao Dong Yang

Jinfeng Zhou

Jialin Zhu

Wenxiao Ma

Methods and apparatuses are provided for compressing video data based on keypoint features. An exemplary video compression method includes: receiving a video sequence; encoding one or more pictures of the video sequence; and generating a bitstream; wherein the encoding includes: representing a first picture by a first set of keypoints and a second set of keypoints, the second set comprising less keypoints than the first set; and compressing the video sequence based on the first set and second set of keypoints.

Keypoints based video compression

Methods and apparatuses are provided for processing video data. An exemplary method includes: decompressing a compressed frame to generate a key frame representing a face; generating, for the key frame, a first set of parameters associated with a 3-dimensional (3D) face representation of the face; reconstructing, for each of one or more inter frames, a second set of parameters associated with a 3D face representation of the face according to compressed inter-predicted residuals of the second set of parameters; and generating a video comprising the face based on the key frame, the first set of parameters, and the second set of parameters.

Method and apparatus for talking face video compression

The present disclosure provides methods for convolutional-neural-network (CNN) based filter for video coding. An exemplary method includes: applying motion estimation to a target coding block, to determine a reference block of the target coding block; inputting, to a convolutional neural network (CNN) filter, image data associated with the target coding block and the reference block; and executing the CNN filter to determine a residual associated with the target coding block based on the input image data.

Convolutional-neutral-network based filter for video coding

The disclosure relates to a method for manufacturing a tray table containing plant fiber and a tray table made therefrom. The manufacturing method comprises: a) homogenizing a halogen-free flame retardant to obtain a homogeneous halogen-free flame retardant; b) melting a thermoplastic resin and uniformly blending the molten thermoplastic resin with a plant fiber, the homogeneous halogen-free flame retardant, and a compatibilizer to obtain a plant fiber composite material; c) extruding and granulating the plant fiber composite material to obtain a granular composite material; and d) mixing the granular composite material with a foaming agent and injection molding to obtain the tray table. The tray table manufactured according to the method herein is green and environmentally friendly, non-toxic and harmless, and also has high flame-retardant effect and weight reduction effect.

Tray tables comprising plant fibers and methods for manufacturing tray tables comprising plant fibers

The present invention relates to use of a pyrrolopyrimidine compound for treating hemophagocytic syndrome, and particularly relates to use of a compound of formula (I), a stereoisomer thereof, or a pharmaceutically acceptable salt thereof, and a pharmaceutical composition thereof for treating hemophagocytic syndrome.

Use of pyrrolopyrimidine compound for treating hemophagocytic syndrome

A video processing method is provided. The method includes inserting a set of spatial merge candidates to a first merge candidate list of a coding block, wherein the first merge candidate list is constructed by: adding a top neighboring block Bto the first merge candidate list when the top neighboring block Bis available; adding a left neighboring block Ato the first merge candidate list when the left neighboring block Ais available; adding a top neighboring block Bto the first merge candidate list when the top neighboring block Bis available; adding a left neighboring block Ato the first merge candidate list when the left neighboring block Ais available; and adding an above-left neighboring block Bto the first merge candidate list when the above-left neighboring block Bis available.

Methods for constructing a merge candidate list

Provided in embodiments of the present invention are a magnetic resonance image processing method and device, and a computer-readable storage medium. The method includes: determining a central angle; converting, on the basis of the central angle, a radio-frequency field pattern of a radio-frequency transmitting coil into an angular pattern; acquiring, on the basis of a trigonometric function value of the angular pattern, a radio-frequency transmitting field pattern of the radio-frequency transmitting coil; and correcting, on the basis of the radio-frequency transmitting field pattern, a magnetic resonance image to be corrected.

Magnetic resonance image processing method and device, and computer readable storage medium

The present disclosure provides methods and systems for motion compensation. The method can include: determining a plurality of intermediate interpolation coefficients of an interpolation filter, the determining of the plurality of intermediate interpolation coefficients being: based on positions of a plurality of integer samples respectively, and based on fractional reference positions of a plurality of fractional samples respectively; determining a plurality of integer interpolation coefficients of the interpolation filter by rounding the plurality of intermediate interpolation coefficients to a plurality of integers respectively; and applying the plurality of integer interpolation coefficients on a picture to perform motion compensation prediction.

Motion compensation methods for video coding

An image data encoding method is provided. The image data encoding method includes receiving an input image and a quantization parameter (QP); performing pre-analysis of the input image based on the QP to obtain input image data for machine version; determining at least one of a temporal redundancy or a spatial redundancy of the input image data; determining, based on the at least one of temporal redundancy or spatial redundancy, whether to perform at least one of temporal down-sampling or spatial down-sampling; performing down-sampling of the input image data according to the determination, wherein the down-sampling includes at least one of temporal down-sampling or spatial down-sampling; and encoding the down-sampled image data based on the QP.

Methods and non-transitory computer readable storage medium for pre-analysis based resampling compression for machine vision

The present disclosure provides methods for performing training and executing of a multi-density neural network in video processing. An exemplary method comprises: receiving a video stream comprising a plurality of pictures; processing the plurality of pictures using a first branch of a first block in the neural network, wherein the neural network is configured to reduce blocking artifacts in video compression of the video stream and the first branch comprises one or more residual blocks; and processing the plurality of pictures using a second branch of the first block in the neural network, wherein the second branch comprises a down-sampling processing, an up-sampling processing, and one or more residual blocks.

Neural network based in-loop filtering for video coding

The present invention discloses a method for making an aspheric vision correction lens with controlled peripheral defocus. The present invention also discloses a vision correction lens worn outside the eye, an orthokeratology lens and an intraocular lens made according to the method. The present invention further discloses a diagnosis and treatment method that utilizes myopic peripheral defocus to control and retard myopia growth.

Vision correction lens and method for preparation of the same

A delivery site and delivery method are provided, the delivery site includes: a building having a storage space configured to store an article and a drone apron configured to allow a drone to land thereon, an article receiving device at least partially arranged in the building and configured to receive an article unloaded from the drone on the drone apron, and an article sorting device arranged in the building, and configured to sort a received article into the storage space.

Delivery site and delivery method

An unmanned aerial vehicle airport, an unmanned aerial vehicle system, a tour inspection system and an unmanned aerial vehicle cruise system. The unmanned aerial vehicle airport comprises a support base, a parking apron, a protective cover and a protective cover opening and closing driving device. The parking apron is installed on the top of the support base; the protective cover covers the top of the apron; the protective cover opening and closing driving device is installed between the support base and the protective cover, and the protective cover opening and closing driving device is configured to cause a bar linkage mechanism to drive the protective cover to switch between an open position and a closed position. The unmanned aerial vehicle airport is provided with the protective cover for the parking apron. If the protective cover is open, the unmanned aerial vehicle is parked on the parking apron, and takes off from the parking apron.

Unmanned aerial vehicle airport, unmanned aerial vehicle system, tour inspection system and unmanned aerial vehicle cruise system

A video processing method is provided. The method includes inserting a set of spatial merge candidates to a first merge candidate list of a coding block, wherein the first merge candidate list is constructed by: adding a top neighboring block B1 to the first merge candidate list when the top neighboring block B1 is available; adding a left neighboring block A1 to the first merge candidate list when the left neighboring block A1 is available; adding a top neighboring block B0 to the first merge candidate list when the top neighboring block B0 is available; adding a left neighboring block A0 to the first merge candidate list when the left neighboring block A0 is available; and adding an above-left neighboring block B2 to the first merge candidate list when the above-left neighboring block B2 is available.

Growing community of inventors

Beijing, China

Zhao Wang