Tencent Technology (shenzhen) Company Limited

Hon Hai Precision Industry Co., Ltd.

Hong-fu Jin Precision Industry (shenzhen) Co., Ltd.

Siemens Healthcare Gmbh

Huawei Technologies Co., Limited

Zte Corporation

Aac Technologies Pte. Ltd.

Siemens Aktiengesellschaft

The General Hospital Corporation

Fih (hong Kong) Limited

Byd Company Limited

The UAB Research Foundation (The University of Alabama at Birmingham)

Siemens Healthineers Ag

Xi'an Zhongxing New Software Co., Ltd.

Tsinghua University

Yan Zhang

Lin Ma

Linchao Bao

Yonggen Ling

Kun Zhou

Xudong Yan

Hao Wang

Xiaolong Zhu

Yong Zhang

Yuan Gao

Na Wang

Wenlong Wu

Tao Li

Wei Wu

Jing Wen Wang

Cheng Gong

Jian Hua Liu

Xiao Zhang

Jie Zhou

Tong Zhang

Mario Zeller

Dominik Paul

Dong Yu

Wei Dong Chen

Qian Wang

Yu Zhang

Qi Wang

Xiao Han

Hui Zhang

Wei Wei

Li Qin Shen

Shuo Wang

Xin Wang

Jun Yang

Jianhua Zhu

Xinyu Liu

Yan Huang

Ning Wang

Wenji Tang

Weihong Xiao

Li Tian

Yanping Zhang

Jing He

Yan Zhu

Caixia Qi

Ni Ma

Wenhan Luo

Genchu Tang

Bin Tang

Xiangkai Lin

Haozhi Huang

Shengcai Dong

Xue-Dong Tang

Qiong Zhang

Ting-Ting Zhao

Zhi Feng Li

Pengfei Zhang

Zequn Jie

Yong Luo

Qiong Wang

Yan Wei Zhang

Peng Yang

Jie Fan

Jianping Zhou

Kai Zheng

Hong Xia Li

Chong Wei Zhang

Lei Xie

Yu Deng

Rui Li

Feng Xing

Zhengyou Zhang

Lei Zheng

Jianhua Yao

Zhipei Lu

Qinghua Zhong

Kun Zhang

Jing Wang

He-Li Wang

Zhenwu Hao

Zhiwu Xu

Meng Zhang

Jonathan R Polimeni

Wei Gong

Jinshui Liu

Junlong Liu

Fei Huang

Xiao-Hui Zhou

Dasheng Hu

Min-Li Li

Liqiang Liu

Xuefeng Zhang

Yi Song

Weihua Li

Yitong Wang

Wanchao Chi

Rong Zhang

Xiaolian Zhou

Fang Dong

Jingmin Luo

This application relates to a face image processing method, apparatus, computer device, and storage medium. The method includes acquiring a first face image and a second face image, the first face image and the second face image being images of real faces; generating a first updated face image with non-real face image characteristics based on the first face image; adjusting color distribution of the first updated face image according to color distribution of the second face image to obtain a first adjusted face image; acquiring a target face mask of the first face image, the target face mask being generated by randomly deforming a face region of the first face image; and blending the first adjusted face image and the second face image according to the target face mask to obtain a target face image. Accordingly, a diversity of target face images can be generated.

Face synthesis for forgery detection

An image processing model can more accurately process a face image with an occluded face while reducing calculations and improving operation speed of a processing device, reducing training time and costs. A predicted recognition result of a sample face image and occlusion indication information based on an image processing model is obtained. The occlusion indication information indicates an image feature of a face occlusion area of the sample face image. A recognition error based on the predicted recognition result and a target recognition result is also obtained. A classification error is obtained based on the occlusion indication information and a target occlusion pattern corresponding to the sample face image. An occlusion pattern of the sample face image indicates a position and a size of the face occlusion area. A model parameter of the image processing model is updated based on the recognition error and the classification error.

Method, apparatus, device, and storage medium for training image processing model

A multi-layer porcelain block includes a first zirconia powder layer, a second zirconia powder layer, a third zirconia powder layer, a fourth zirconia powder layer, a fifth zirconia powder layer, a sixth zirconia powder layer, a seventh zirconia powder layer, and an eighth zirconia powder layer laid in sequence. The zirconia powders in the first to eighth zirconia powder layers are doped with yttria. The first zirconia powder layer accounts for 13% to 17% by mass, the second zirconia powder layer accounts for 8% to 12% by mass, the third zirconia powder layer accounts for 10% to 14% by mass, the fourth zirconia powder layer accounts for 10% to 14% by mass, the fifth zirconia powder layer accounts for 10% to 14% by mass, the sixth zirconia powder layer accounts for 10% to 14% by mass.

Multi-layer porcelain block, preparation method thereof and denture

The invention provides a vision-testing method and vision-testing device. The vision-testing method is applied to the vision-testing device. The vision-testing device includes a light-transmitting apparatus, a plurality of vision test marks arranged on one side of the light-transmitting apparatus, and a plurality of light-emitting units arranged on another side of the light-transmitting apparatus for providing the vision test marks with a light source. The vision-testing method comprises the steps of obtaining a vision test command, controlling one of the light-emitting units to emit light according to the vision test command so as to highlight the corresponding vision test mark, obtaining user-response information and outputting a vision test result according to the user-response information and the highlighted vision test mark. The vision-testing method provided by the invention can achieve the vision test without a professional guidance, and the user can obtain real-time vision test information.

Vision-testing method and device thereof

Earphones

An audio acquisition device positioning method is provided. In the method, a first image that includes an audio acquisition device is obtained. The audio acquisition device in the first image is identified. First coordinate data of the identified audio acquisition device in the first image is obtained. First displacement data is determined according to the first coordinate data and historical coordinate data of the audio acquisition device. First coordinates of the audio acquisition device are determined according to the first displacement data.

Microphone detection using historical and cache coordinate databases

Drawer unit

A model training method includes obtaining an image sample set and brief-prompt information; generating a content mask set according to the image sample set and the brief-prompt information; generating a to-be-trained image set according to the content mask set; obtaining, based on the image sample set and the to-be-trained image set, a predicted image set through a to-be-trained information synthesis model, the predicted image set comprising at least one predicted image, the predicted image being in correspondence to the image sample; and training, based on the predicted image set and the image sample set, the to-be-trained information synthesis model by using a target loss function, to obtain an information synthesis model.

Model training method, media information synthesis method, and related apparatuses

Hamper

A speaker core, speaker, and associated electronic device include at least one bent portion of a diaphragm folded ring suspended over a top of a diaphragm frame enclosing an enlarged vibration space.

Speaker core, speaker, and electronic device

This application discloses a video clip positioning method performed at a computer device. In this application, the computer device acquires a plurality of video frame features of a target video and a text feature of a target text using a video recognition model to determine a candidate clip that can be matched with the target text. The candidate clip is finely divided based on a degree of matching between a video frame in the candidate clip and the target text to acquire a plurality of sub-clips, and a sub-clip that has the highest degree of matching with the target text is used as a target video clip. According to this application, the video recognition model does not need to learn a boundary feature of the target video clip, and during model training, or precisely label a sample video, thereby shortening a training period of the video recognition model.

Video clip positioning method and apparatus, computer device, and storage medium

A method is for acquiring a magnetic resonance (MR) image dataset of at least two slices via simultaneous multi-slice excitation. An embodiment of the method includes executing an MR imaging sequence using multi-band radio-frequency excitation pulses to excite the at least two slices simultaneously in at least two repetitions, the repetitions each being executed according to a phase modulation scheme in which each of the simultaneously excited slices is assigned a phase and the phase of at least one of the simultaneously excited slices is changed from one repetition to the next, thereby acquiring an MR dataset of a collapsed image in each repetition; performing a spatial registration between the at least two collapsed images and performing motion correction on at least one of the MR datasets of the collapsed images; and reconstructing MR images of the at least two slices from the corrected MR datasets of the collapsed images.

Method for acquiring an MR-image dataset of at least two slices by means of simultaneous multislice excitation

A model training method and apparatus for image recognition, and a non-transitory storage medium are provided. The model training method includes: obtaining a multi-label image training set including a plurality of training images each annotated with a plurality of sample labels; selecting target training images from the multi-label image training set for training a current model; performing label prediction on each target training image using the current model, to obtain a plurality of predicted labels of the each target training image; obtaining a cross-entropy loss function corresponding to the plurality of sample labels of the each target training image, a positive label loss being greater than a negative label loss and having a weight greater than 1; converging the predicted labels and the sample labels of the each target training image according to the cross-entropy loss function, and updating parameters of the current model, to obtain a trained model.

Model training method and apparatus for image recognition, network device, and storage medium

An artificial intelligence (AI)-based face recognition method includes: obtaining n groups of input video frames, at least one group of video frames including a color video frame and a depth video frame of a target face, n being a positive integer; invoking an interactive liveness detection function to recognize the color video frames in the n groups of video frames; invoking a second three-dimensional (3D) structured-light liveness detection function to recognize the depth video frames in the n groups of video frames; and determining, in response to both detection results of the interactive liveness detection function and the 3D structured-light liveness detection function indicating that a type of the target face being a liveness type, that the target face is a live target face.

AI-based face recognition method and apparatus, device, and medium

A computer device extracts local features of sample images based on a first part of a convolutional neural network (CNN) model. The sample images comprise a plurality of images taken at the same place. The device; aggregates the local features into feature vectors having a first dimensionality based on a second part of the CNN model. The device obtains compressed representation vectors of the feature vectors based on a third part of the CNN model. The compressed representation vectors have a second dimensionality less than the first dimensionality. The device trains the CNN model, and obtains a trained CNN mode satisfying a preset condition in accordance with the training.

Method, apparatus, and electronic device for training place recognition model

Growing community of inventors

Shenzhen, China

Yan Zhang