Peking University

Nuctech Company Limited

Schering Corporation

Tsinghua University

Pharmacopeia Inc.

Pharmacopeia Drug Discovery, Inc.

Other

Columbia University

Ping an Technology (shenzhen) Co., Ltd.

National Institute of Clean-and-low-carbon Energy

China Energy Investment Corporation Limited

Wuhu Jiahong New Material Co., Ltd.

Guangzhou Micnano Biotech Co., Ltd

Guangzhou Novaken Pharmaceutical Co., Ltd.

China University of Mining and Technology

Ge Li

Wen Gao

Yuanjing Li

Qingjun Zhang

Ronggang Wang

John J Baldwin

Qiufeng Ma

Zhiqiang Chen

Wenmin Wang

Biao Cao

Yaohong Liu

Zhenyu Wang

Ying Li

Shengfu Dong

Ziran Zhao

Yinong Liu

Hui Zhao

Yiting Shao

Arthur G Taveras

Jianmin Li

Weiping Zhu

John C Reader

Lili Yan

Jianping Chao

J Robert Merritt

Ronald J Doll

Michael P Dwyer

Younong Yu

Jianhua Chao

Johan A Ferreira

Lawrence Wayne Dillard

Purakkattle J Biju

Cynthia J Aki

Wenguang Zeng

Viyyoor Moopil Girijavallabhan

F George Njoroge

Alan K Mallams

Qi Zhang

Adriano Afonso

Dinanath F Rane

W Clark Still

Peng Gao

Kui Fan

Randall R Rossman

Nan Bai

Gaifa Lai

Bernd Kaiser

Neng-Yang Shih

Robert G Aslanian

Stuart B Rosenblum

Alan B Cooper

Kevin D McCormick

Pauline C Ting

Rong Wang

Daniel M Solomon

Jing Wang

Qingbei Zeng

Wei Gao

Chia-Yu Huang

Henry A Vaccaro

Chuang Ma

Jianhua Cao

Guotong Xie

Nei Yang

Wei Wang

Yan Wang

Ashit K Ganguly

Rui Wang

Timothy J Guzi

Shangmin Sun

Yu Hu

Guohua Cao

Yuxing Peng

Jing Yan Ma

Gang Shen

Qian Zhang

Xiang Zou

Patrick A Pinto

Hao Lu

Yang Guo

Kartik M Keertikar

Carmen S Alvarez

Tiejun Huang

Ray Anthony James

Jagdish A Desai

Songyong Liu

Yanchun Wang

Bancha Vibulbhan

James J-s Wang

Jonathan J Burbaum

Hugh Y Zhu

Daniel Lundell

Keith P Minor

Bama Santhanam

Jay S Fine

Hongyan Wang

Xianghua Li

The present invention provides a point cloud attribute entropy encoding method and device, and a point cloud attribute entropy decoding method and device. The encoding method comprises: if an overall encoding processing condition of point cloud attribute residual coefficients is satisfied, performing overall encoding processing on the point cloud attribute residual coefficients, and then ending the encoding; and if not, performing local one-by-one encoding processing on the point cloud attribute residual coefficients until the encoding is ended. The entropy decoding method comprises: if an overall decoding processing condition of the point cloud attribute residual coefficients is satisfied, performing overall decoding processing on the point cloud attribute residual coefficients, and then ending the decoding; and if not, performing local one-by-one decoding processing on the point cloud attribute residual coefficients until the decoding is ended. The present invention better utilizes redundant information in a point cloud and improves compression performance.

Point cloud attribute entropy encoding method and device, and point cloud attribute entropy decoding method and device

A method for determining a task-driven pruning module includes: obtaining an input task and a task quantity of a neural network to be pruned, and output information of a component module of the neural network to be pruned; determining a task correlation degree of the component module according to the input task, the task quantity and the output information; determining an input information retention degree of the component module according to the task quantity and the output information; determining an importance index value of the component module according to the task correlation degree and the input information retention degree; and determining the pruning module in the neural network to be pruned according to the importance index value.

Method and device for determining task-driven pruning module, and computer readable storage medium

A trace detection device including: an ion mobility tube; a sampling gas path module; a sample injection gas path module configured to introduce a sample carrier gas containing a sample collected by the sampling gas path module toward the ion mobility tube; and a gas chromatography apparatus capable of pre-separating the sample carrier gas, so as to form a pre-separated sample carrier gas; wherein the sample injection gas path module is further configured to be capable of switching between a first mode and a second mode, in the first mode, the sample injection gas path module introduces the sample carrier gas into the ion mobility tube; and in the second mode, the sample injection gas path module introduces the sample carrier gas into the gas chromatography apparatus to pre-separate the sample carrier gas, and the pre-separated sample carrier gas is introduced into the ion mobility tube.

Trace detection device

Disclosed is an optimization method for constructing a target detection network. The method includes: obtaining high-quality visual media data, low-quality visual media data corresponding to the high-quality visual media data, and a corresponding true label, extracting a first backbone network side output feature generated by a preset prior network for the high-quality visual media data, and extracting a second backbone network side output feature generated by a preset target detection network to be trained for the low-quality visual media data; constructing a feature correlation loss, a salient target position loss and a salient prediction loss based on the first backbone network side output feature, the second backbone network side output feature, and the true label; and optimizing the preset target detection network to be trained based on the feature correlation loss, the salient target position loss, and the salient prediction loss to obtain the target detection network.

Optimization method, apparatus, device for constructing target detection network, medium and product

The present invention provides a point cloud intra prediction method and device based on weights optimization of neighbors. The invention relates to intra prediction for point cloud attribute compression, by optimizing the weights of the neighboring points on the basis of the density of the point cloud in three directions, i.e. x, y and z directions, and specifically, calculating the optimized weight of each neighboring point by optimizing corresponding coefficients of three coordinate components, i.e. x, y and z coordinate components of distances. The invention can improve the accuracy of intra prediction by means of enhancing the utilization of the overall geometric information of the point cloud, and then transformation, quantification and entropy are carried out on the prediction residuals, such that a better point cloud attribute compression performance is achieved.

Point cloud intra prediction method and device based on weights optimization of neighbors

A memory network method based on automatic addressing and recursive information integration. The method is based on a memory neural network framework integrating automatic addressing and recursive information, and is an efficient and lightweight memory network method. A memory is read and written by means of an automatic addressing operation having low time and space complexity, and memory information is effectively utilized by a novel computing unit. The whole framework has the characteristics of high efficiency, high speed and high universality. The method is suitable for various time sequence processing tasks, and shows the performance superior to that of the conventional LSTM and the previous memory network.

Memory network method based on automatic addressing and recursive information integration

The application relates to the technical field of artificial intelligence, and provides a method, device, electronic equipment and storage medium for positioning macular center in fundus images. The method comprises: acquiring a detection result of the fundus image detection model, wherein the detection result includes an optic disc area, and a first detection block and a first confidence score corresponding to the optic disc area, and a macular area, and a second detection block and a second confidence score corresponding to the macular area; calculating a center point coordinate of the optic disc area according to the first detection block, and calculating a center point coordinate of the macular area according to the second detection block; identifying whether the to-be-detected fundus image is a left eye fundus image or a right eye fundus image, and correcting a center point of the macular area using different correction models.

Method, device, electronic equipment and storage medium for positioning macular center in fundus images

The present disclosure relates to an artificial intelligence field using a neural network, and publishes a method for confirming a cup-disc ratio based on a neural network, an apparatus, a computer device, and a computer readable storage medium. The method includes: obtaining a retinal image, and detecting an optical disc region in the retinal image to obtain the optical disc region; inputting the optical disc region into a pre-trained neural network to obtain a prediction cup-disc ratio and segment images of an optical cup and an optical disc; computing a cup-disc ratio based on the segment images of the optical cup and the optical disc; and confirming a practical cup-disc ratio based on the prediction cup-disc ratio and the computed cup-disc ratio.

Method for confirming cup-disc ratio based on neural network, apparatus, device, and computer readable storage medium

Provided are a point cloud attribute prediction method and prediction device based on a filter. The method comprises a coding method and a decoding method, and the device comprises a coding device and a decoding device. The method comprises: determining K nearest neighbor points of the current point; determining a filter matrix; and determining an attribute prediction value of the current point according to the filter matrix. Therefore, the compression performance of a point cloud attribute can be improved by means of selecting an appropriate filter.

Point cloud attribute prediction method and device based on filter

An attribute-based point cloud strip division method. The method comprises: first, performing spatial division of a certain depth on a point cloud to obtain a plurality of local point clouds; and then, sorting the attribute values in the local point clouds, and on the basis of such, further performing point cloud strip division so as to obtain point cloud strips that have low geometric overhead and a uniform number of points. By means of comprehensively using the spatial position and attribute information of the point clouds, the points having similar attributes and related spatial positions are gathered as much as possible in one strip during strip division, which is convenient for making full use of the redundancy of the attribute information between adjacent points, and improving the performance of point cloud attribute compression. At the same time, independent coding between strips supports random access, improves coding efficiency, and prevents the accumulation and spread of coding errors, thus enhancing the fault tolerance of the system.

Attribute-based point cloud strip division method

The present disclosure provides a gas analysis device and a method for detecting sample gas. The gas analysis device includes: an ion mobility spectrometer including an ion mobility tube, an ion gate, a plurality of electrodes, a suppression grid, and a Faraday plate sequentially disposed in the ion mobility tube, wherein the Faraday plate is configured to receive sample ions discharged from the suppression grid, and the Faraday plate is provided with a through hole; a mass spectrometer; a gate valve disposed between the Faraday plate and an ion inlet of the mass spectrometer; and a controller configured to control an opening or closing of the gate valve to allow the sample ions discharged from the suppression grid to flow into the mass spectrometer through the through hole of the Faraday plate when the gate valve is opened.

Gas analysis device and method for detecting sample gas

The present disclosure provides a method of positioning vertebra in a CT image, an apparatus, a computer device, and a computer readable storage medium. The method includes: pre-processing vertebra CT image data; inputting the pre-processed vertebra CT image data into a pre-trained neural network to obtain regression results of heat maps of key points corresponding to the pre-processed vertebra CT image data; regressing of 3D heat maps corresponding to the positions of the key points of the vertebra mass center based on the regression results of the heat maps of the key points and the pre-processed vertebra CT image data; serving 3D heat maps corresponding to the positions of the key points of the vertebra mass center as labels, and networked regressing 3D heat map information to position the vertebra. Effects caused by scanning machine difference and scanning noise are avoided, and the vertebra with complex forms is accurately positioned.

Method for positioning vertebra in CT image, apparatus, device, and computer readable storage medium

A self-adaptive point cloud stripe division method. The method comprises: firstly, carrying out space division with a certain depth on a point cloud to obtain a plurality of local point clouds; then, counting the number of points in each of the local point clouds, comparing same with an upper and lower limit for the number of stripe points, and determining whether the number of points satisfies a requirement; and after a series of re-segmentation or re-fusion operations on the local point clouds, adjusting the number of points in each of the local point clouds until the number of points satisfies a range, thereby obtaining a final point cloud stripe. A plurality of local structures capable of being independently coded and decoded are obtained by means of division of a point cloud stripe, and this supports parallel processing, enhances system fault tolerance, and improves coding efficiency. Moreover, in consideration of the fact that the size of a point cloud stripe often has a limited range due to realistic factors of a large-scale point cloud, such as a limited transmission bandwidth, the method can satisfy such a requirement and make it possible to generate a plurality of point cloud stripes with a rational number of points while supporting parallel processing.

Self-adaptive point cloud stripe division method

The present disclosure discloses an ethylene degradation catalyst and a preparation method and a use thereof.

Ethylene degradation catalyst and preparation method and use thereof

The invention discloses a point cloud geometric compression method based on a depth auto-encoder, which comprises the following steps of: (1) point cloud preprocessing: collecting a type of point cloud to be compressed as a training set, and normalizing the training set into a unit circle; (2) point cloud down-sampling: down-sampling the point clouds in the training set so that each point cloud have the same point number m and each point in the point cloud has (x, y, z) three-dimensional coordinates; and adopting a farthest point down-sampling method by randomly selecting a point for the first time and then selecting the point farthest away from the selected point set every time to add into the selected point set until the selected point number meets the requirement; (3) training a compression model: inputting the point cloud sampled in step (2) into a point cloud geometric compression framework based on a depth auto-encoder for training; and (4) geometric compression of the point cloud: applying the trained compression framework to the geometric compression of all the point clouds of the type. The method can not only obtain a good compression effect but also adapt to a new point cloud type more quickly.

Point cloud geometric compression method based on depth auto-encoder

Growing community of inventors

Shenzhen, China

Ge Li