Tencent Technology (Shenzhen) Company Limited

Zte Corporation

Fu Tai Hua Industry (Shenzhen) Co., Ltd.

Byd Company Limited

Huawei Technologies Co., Limited

Hon Hai Precision Industry Co., Ltd.

Shenzhen Goodix Technology Co., Ltd.

The South China University of Technology

Hong-Fu Jin Precision Industry (Shenzhen) Co., Ltd.

Tcl China Star Optoelectronics Technology Co., Ltd.

Sanechips Technology Co., Ltd.

Luxshare Precision Industry Company Limited

Orbbec Inc.

Nanyang Technological University

Fudan University

Wei Yang

Zhaohua Lu

Bo Gao

Yu Ngok Li

Yijian Chen

Zhongqian Sun

Wei Dong Chen

Qing Zhang

Xingang Huang

Chuangxin Jiang

Shujuan Zhang

Jian Zhang

Xin Liu

Lei Li

Jie Liu

Liquan Yuan

Wei-Jun Wang

Xing Hu

Mingyu Chen

Kai Yang

Bo Han

Chen Chen

Junfeng Zhao

Yuangang Wang

Feng Yang

Xinghui Fu

Hong Shang

Chen Cheng

Siyuan Liu

Ke Xu

Dehui Kong

Junbiao Peng

Yibo Zhang

Bo Yang

Shihai Xiao

Zhihua Wang

Han Zheng

Yuan Ruan

Liu-Bin Hu

Aimin Chen

Yinyin Lin

Florian Longnos

Ke Hu

Shiying Yang

Chaoxian Chen

Yusho Nakase

Hao Chen

Hao Yu

Jing You

Jianhua Tang

Xiaowen Dong

Zijian Zhang

Xue Wei

Yong Cao

Hongliang Tian

Le Chang

Kanwen Wang

Zhiwei Liu

Zhulin Wei

Yarong Fu

Haikuan Jiang

Xiangrong Chen

Hsiu-Lung Chang

Xiong Zhou

Guangdong Yang

Wingho Pang

Songsong Liu

Lianghe Zhang

Lusheng Wu

Kaiwen Xiao

Feng Peng

Jisong Ai

Huannan Ma

Jiangyan He

RenHua Yang

Xiaoning Wang

Xiaolong Liu

Guoshuai Liu

Yufeng Li

Chengqiang Liu

Shangling Jui

Zi Jian Zhang

Zhao Chen

Cheng Zeng

Yuhao Wang

Linfen Yu

Leibin Ni

Liming Zhang

Ting Guo

Qi Pan

Zhongzheng Liu

Limin He

Gengxing Huang

Cilang Wang

Borui Yu

Tianyue Lu

Zhong Qian Sun

Xing Hui Fu

Zejia Huang

A multi-directional input detection apparatus includes: a seat; a housing provided above the seat, the housing being provided with an inner cavity and an opening communicated with the inner cavity; a circuit board provided between the housing and the seat, an induction pin being provided on a surface of the circuit board towards the opening; a rotating assembly provided in the inner cavity; and a rocker assembly including a rod body and a conductor. One end of the rod body is slidably connected to the rotating assembly, and the other end of the rod body is configured to extend to an outside of the opening; one end of the conductor is connected to a part of the rod body outside the opening and is exposed on an outer surface of the rod body, and the other end of the conductor is configured to extend into the inner cavity.

Multi-directional input detection apparatus

Provided is a sound generating apparatus including a rear housing, a speaker assembly, a front housing, and a vent frame. The rear housing is provided with an accommodation groove and a rear chamber groove. The outer wall of the rear housing is provided with a vent hole. The speaker assembly is disposed in the notch of the rear chamber groove and covers the rear chamber groove to form a rear sound chamber. A front sound chamber is formed on the side of the front housing. The vent frame and the rear housing are assembled to form a rear vent channel whose two ends communicate with the rear sound chamber and the vent hole. The vent frame and the front housing are assembled to form a front vent channel whose two ends communicate with the front sound chamber and the vent hole.

Sound generating apparatus

The present disclosure provides an endoscopic image processing method and system, and a computer device. The method can include acquiring a current endoscopic image of a to-be-examined user, and predicting the current endoscopic image by using a deep convolutional network based on a training parameter. The training parameter can be determined according to at least one first endoscopic image and at least one second endoscopic image transformed from the at least one first endoscopic image, where the at least one endoscopic image corresponds to a human body part. The method can further include determining an organ category corresponding to the current endoscopic image. The method provided in the present disclosure can make a prediction process more intelligent and more robust, thereby improving resource utilization of a processing apparatus.

Endoscopic image processing

Laser profiler

A video processing method is provided, including obtaining an original video sequence, the original video sequence comprising P video frames obtained through rendering, P being an integer greater than or equal to 2; obtaining a target video sequence according to the original video sequence, the target video sequence comprising the P video frames and Q unrendered video frames interpolated based on at least two video frames of the P video frames, Q being an integer greater than or equal to 1; encoding the target video sequence to obtain a video encoding sequence; and transmitting the video encoding sequence to a terminal device, the terminal device decoding the video encoding sequence to obtain a video sequence that needs to be rendered.

Video processing method, related apparatus, storage medium, and program product

Provided are information transmission method and apparatus. The information transmission method includes that: D control channel resource groups are determined, control information is detected in the D control channel resource groups, and transmission of a channel and/or signal is performed according to control information which is detected.

Information transmission method and apparatus

A tissue adhesive membrane and a preparation method thereof are provided. The tissue adhesive membrane includes a supramolecular polymer and an enhancer; the supramolecular polymer is prepared by copolymerization of lipoic acid and a biocompatible stabilizer; and the enhancer includes at least one selected from the group consisting of a cationic compound, a cationic polymer, and a metal particle. The tissue adhesive membrane of the present invention can achieve rapid adhesion, seal wounds continuously and effectively, and maintain long-lasting mechanical strength. The components of the tissue adhesive membrane come from natural components of animals and plants, have good biocompatibility, and possess the functions of antibacterial and inhibiting inflammation. The tissue adhesive membrane of the present invention is a hydrophobic adhesive membrane where hydrogen bonding and high surface energy can provide strong adhesion energy and no adverse active groups that may cause irritation or discomfort are contained.

Tissue adhesive membrane and preparation method thereof

An intention identification model learning method includes receiving positive data that corresponds to a first skill, generating, based on the positive data that corresponds to the first skill, negative data that corresponds to the first skill, determining a second skill similar to the first skill, obtaining data that corresponds to each second skill, generating a second base model based on the data that corresponds to the second skill and a first base model stored on the server, and performing learning based on the second base model, the positive data, and the negative data that correspond to the first skill, and generating an intention identification model.

Intention identification model learning method, apparatus, and device

A device to detect and analyze defects in a finished surface includes a supporting mechanism, a transmitting mechanism, a detecting mechanism, and a processor. The transmitting mechanism carries and transmits the product. The detecting mechanism includes a detecting frame, a light source assembly. The processor is used to connect to a first camera module and a second camera module, and preprocess the first image and the second image to obtain a detection and analysis of any defects of the front of the product.

Device for recognizing defects in finished surface of product

A medical endoscope image recognition method is provided. In the method, endoscope images are received from a medical endoscope. The endoscope images are filtered with a neural network, to obtain target endoscope images. Organ information corresponding to the target endoscope images is recognized via the neural network. An imaging type of the target endoscope images is identified according to the corresponding organ information with a classification network. A lesion region in the target endoscope images is localized according to an organ part indicated by the organ information. A lesion category of the lesion region in an image capture mode of the medical endoscope corresponding to the imaging type is identified.

Medical endoscope image recognition method and system, and endoscopic imaging system

This application relates to an image recognition model training method, an image recognition method, apparatus, and system. The method includes: obtaining a to-be-recognized image; extracting image feature information of the to-be-recognized image; and obtaining a lesion category recognition result of the to-be-recognized image by using the image feature information of the to-be-recognized image as an input parameter of a preset image recognition model, the image recognition model being trained by using a training image sample set comprising at least one strong-label training image sample, to determine the lesion category recognition result; and the strong-label training image sample representing an image sample having strong-label information, and the strong-label information comprising at least annotation information of a lesion category and a lesion position in the strong-label training image sample. According to the lesion position, image feature information of a specific lesion category may be more accurately positioned, thereby improving reliability and accuracy.

Image recognition model training method and apparatus, and image recognition method, apparatus, and system

In a medical image recognition method, applied to a computer device, a to-be-recognized medical image set is obtained, where the to-be-recognized medical image set includes at least one to-be-recognized medical image. A to-be-recognized area corresponding to each to-be-recognized medical image in the to-be-recognized medical image set is extracted. The to-be-recognized area is a part of the to-be-recognized medical image. A recognition result of each to-be-recognized area through a medical image recognition model is determined. The medical image recognition model is obtained through training according to a medical image sample set. The medical image sample set includes at least one medical image sample, and each medical image sample carries corresponding annotation information. The annotation information is used for representing a type of the medical image sample, and the recognition result is used for representing the a of the to-be-recognized medical image.

Medical image recognition method, model training method, and computer device

A device to detect and analyze defects in magnified scale images of a surface of a finished product illuminated with a blue light source and viewed by multiple image-capturing devices each focused on their own spot includes a supporting mechanism, a transmitting mechanism, a detecting mechanism, and a processor. The transmitting mechanism carries and transmits the product. The detecting mechanism includes a detecting frame, a blue light source assembly. The processor is used to connect to a camera assembly, and preprocess the image of the front of the product to obtain a detection and analysis of any defects of the front of the product.

Solar fan

Embodiments of this application include an image processing method and apparatus, a non-transitory computer-readable storage medium, and an electronic device. In the image processing method a to-be-predicted medical image is input into a multi-task deep convolutional neural network model. The multi-task deep convolutional neural network model includes an image input layer, a shared layer, and n parallel task output layers. One or more lesion property prediction results of the to-be-predicted medical image is output through one or more of the n task output layers. The multi-task deep convolutional neural network model is trained with n types of medical image training sets, n being a positive integer that is greater than or equal to 2.

Image processing method and apparatus, computer-readable medium, and electronic device

Growing community of inventors

Shenzhen, China

Wei Yang