Tencent Technology (shenzhen) Company Limited

Tsinghua University

Beijing University of Posts and Telecommunications

Huazhong University of Science and Technology

The Hong Kong Polytechnic University

Shenzhen Tencent Computer Systems Company Limited

Tencent Technology Company Limited

Juhong Wang

Tingting Liu

Jie Jiang

Yue Ming

Wei Chen

Li Yao

Tingting Huang

Xuan Zheng

Jun Zhao

Hao Liu

Xing Zhang

Chao Li

Feiyue Huang

Bin Hua Liu

Chuan Chen

Xiaowei Guo

Bin Liu

Cong Yao

Shimin Hu

Junzhou Huang

Yuezhi Zhou

Ruixin Zhang

Dafu Deng

Kun Xu

Yanxiong Lu

Xianneng Zou

Xiapu Luo

Yaoxue Zhang

Zhiwei Liu

Huaijun Liu

Lei Xue

Jun Yin

Jingang Hou

Wenyu Liu

Xiang Bai

Baoguang Shi

Longjun Sun

Kang Liu

Weigang Wu

Wenhao Zhang

Zhizhi Zhou

Pengyuan Lv

Liheng Xu

Yajuan Tang

Hongzhi Liu

Mingfeng Qiu

Zhengchan Chen

Pengpeng Zhao

Gang Guan

Zhiyong Wu

Yongkun Li

Xinggang Wang

Zhonghai Wu

Dongyuan Ma

This application relates to a target object detection method and apparatus, a non-transitory computer-readable storage medium, and a computer device. The method includes: obtaining a to-be-detected image; inputting the to-be-detected image into a target object detection model; generating, by the target object detection model, a prediction diagram corresponding to the to-be-detected image, the prediction diagram describing a relation degree to which pixels of the to-be-detected image belong to a target detection object; and performing region segmentation on the prediction diagram to obtain a target detection object region. In addition, a method and an apparatus for training an object detection model into the target object detection model, a non-transitory computer-readable storage medium, and a computer device are also provided.

Method for training object detection model and target object detection method

A method for obtaining a binocular panoramic image is performed at an electronic apparatus, including: obtaining first and second panoramic images acquired by two panoramic cameras; obtaining at least one group of a first pixel located in the first panoramic image and a second pixel located in the second panoramic image; calculating a distance between the first pixel and the second pixel in each group, and obtaining depth information corresponding to the two panoramic image according to the distance between the first pixel and the second pixel; converting the first panoramic image and the second panoramic image into a first monocular panoramic image and a second monocular panoramic image, respectively in accordance with the corresponding depth information and a preset pupil distance between a first eye and a second eye; and combining a display of the first monocular panoramic image and the second monocular panoramic image in corresponding display regions.

Method and apparatus for obtaining binocular panoramic image, and storage medium

This disclosure relates to an account filtering method and apparatus. The method includes obtaining user accounts of a social activity network and user activity information; constructing a hypergraph of the social activity network comprising nodes and hyperedges according to the user accounts and the user activity information, wherein a node in the hypergraph comprises the user account in the social activity network, and a hyperedge in the hypergraph comprises a set of user accounts that participates in a user activity of an activity type, or a friendship relation between one user account and another user account; for each node in the hypergraph, calculating a probability that another node of the hypergraph would walk to the node when performing a random walk along the hyperedge in the hypergraph, and obtaining an influence value of the node in the social activity network according to the probability; and sequentially filtering nodes of the hypergraph to obtain a sequence of nodes having a maximum influence by using an iteration algorithm, to form a seed node set.

Social media account filtering method and apparatus

Aspects of the disclosure provide an information processing apparatus that includes interface circuitry and processing circuitry. The interface circuitry is configured to obtain a text authored by a person. The processing circuitry is configured to analyze the text to obtain measurements of language features of the person, input the measurements of the language features into an evaluation model that is trained to predict a score as a function of the language features, determine a specific score for the person based on the evaluation model and output the specific score of the person for predicting a behavior of the person.

Evaluation method and apparatus based on text analysis, and storage medium

A method for obtaining a binocular panoramic image is performed at an electronic apparatus. The method includes: obtaining first and second panoramic images acquired by two panoramic cameras; obtaining at least one group of a first pixel located in the first panoramic image and a second pixel located in the second panoramic image; calculating a distance between the first pixel and the second pixel in each group, and obtaining depth information corresponding to the two panoramic image according to the distance between the first pixel and the second pixel; obtaining a second monocular panoramic image through mapping by using one of the two panoramic images as a first monocular panoramic image, in combination with the corresponding depth information and a preset pupil distance between a first eye and a second eye; and displaying the first monocular panoramic image and the second monocular panoramic image in corresponding display regions.

An image classification method is provided. The method includes: inputting a to-be-classified image into a plurality of neural network models; obtaining data output by multiple non-input layers specified by each neural network model to generate a plurality of image features corresponding to the plurality of neural network models; respectively inputting the plurality of corresponding image features into linear classifiers, each of the linear classifiers being trained by one of the plurality of neural network models for determining whether an image belongs to a preset class; obtaining, using each neural network model, a corresponding probability that the to-be-classified image comprises an object image of the preset class; and determining, according to each obtained probability, whether the to-be-classified image includes the object image of the preset class.

Image classification method, electronic device, and storage medium

Embodiments of this disclosure belong to the field of computer technologies and disclose a method and an apparatus for recognizing a character string in an image. The method includes: according to image data of a pre-stored sample image block including a character string, and based on a convolutional neural network algorithm, constructing an expression of a probability set corresponding to a character string recognition result of the sample image block, the expression of the probability set being constituted by a to-be-determined parameter; based on a training target of maximizing a probability that the character string recognition result determined according to the probability set is the character string included in the pre-stored sample image block, training the plurality of to-be-determined parameters to obtain a training value for each to-be-determined parameter; and when a to-be-recognized target image block is obtained, determining, based on the convolutional neural network algorithm and the training values of the plurality of to-be-determined parameters, a target probability set corresponding to the target image block, and determining, according to the target probability set, a character string recognition result of the target image block. By means of the embodiments of this disclosure, correctness of recognizing a character string can be improved.

Method and apparatus for recognizing character string in image

A hand motion identification method includes: obtaining a to-be-identified video; performing area-locating and tracking of a hand for the to-be-identified video, and extracting a red-green-blue (RGB) video and a depth information video of the hand; detecting the RGB video and the depth information video of the hand, to obtain a feature point; representing the feature point by using a 3D Mesh motion scale-invariant feature transform (MoSIFT) feature descriptor; and comparing the 3D Mesh MoSIFT feature descriptor of the feature point with a 3D Mesh MoSIFT feature descriptor in a positive sample obtained through beforehand training, to obtain a hand motion category in the to-be-identified video.

Hand motion identification method and apparatus

An information processing method and apparatus, the method including: training a Deep Neural Network (DNN) by using an evaluation object seed, an evaluation term seed and an evaluation relationship seed (); at a first input layer, connecting vectors corresponding to a candidate evaluation object, a candidate evaluation term and a candidate evaluation relationship to obtain a first input vector (); at a first hidden layer, compressing the first input vector to obtain a first middle vector, and at a first output layer, decoding the first middle vector to obtain a first output vector (); and determining a first output vector whose decoding error value is less than a decoding error value threshold, and determining a candidate evaluation object, a candidate evaluation term and a candidate evaluation relationship corresponding to the determined first output vector as first opinion information (). By use of the technical solution, precision of extracting opinion information from an evaluation text can be enhanced.

Information processing method and apparatus

The present disclosure provides a three-dimensional facial recognition method and system. The method includes: performing pose estimation on an input binocular vision image pair by using a three-dimensional facial reference model, to obtain a pose parameter and a virtual image pair of the three-dimensional facial reference model with respect to the binocular vision image pair; reconstructing a facial depth image of the binocular vision image pair by using the virtual image pair as prior information; detecting, according to the pose parameter, a local grid scale-invariant feature descriptor corresponding to an interest point in the facial depth image; and generating a recognition result of the binocular vision image pair according to the detected local grid scale-invariant feature descriptor and training data having attached category annotations. The present disclosure can reduce computational costs and required storage space.

Three-dimensional facial recognition method and system

It is described an information processing method and device. It is received a request for service data from a client device. In response to the request for service data, it is sent at least two probing packets which contain the service data to the client device on a forward path which is from a server to the client device. It is obtained timing information, which includes: a time stamp corresponding to the service data, a time stamp corresponding to the request for the service data, and time stamps corresponding to at least two backward-path packets sent by the client device on a backward path, the backward path being from the client device to the server. It is determined according to the timing information a one-way path metric.

Information processing method and device

A method for extracting a characteristic of a three-dimensional face image includes: performing face area division, to obtain a group of face areas; projecting each face area onto a corresponding regional bounding sphere; obtaining an indication of the corresponding face area according to the regional bounding sphere, and recording the indication as a regional bounding spherical descriptor of the face area; calculating a weight of the regional bounding spherical descriptor of the face area for each face area; and obtaining a characteristic of a three-dimensional face image according to the indication of the face area and the corresponding weight.

Method and system for extracting characteristic of three-dimensional face image

Embodiments of the present invention provide a microblog-based document file sharing method and device. The method comprises: converting a document file into an swf file; performing format confusion on the swf file; and publishing the swf file after the format confusion through a microblog platform. After the embodiments of the present invention are applied, information transmission and the audience size are expanded through sharing via microblog technologies. In addition, the format confusion is performed on the swf file, so that the possibility of directly obtaining the original of the document file through a link is eliminated, and therefore, the information security of the document is also enhanced.

Microblog-based document file sharing method and device

A method for positioning an IP location and a server are provided. The method comprises: obtaining location data of mobile terminals used by a plurality of users in a preset period to generate a first geographic location data set; pre-processing the first geographic location data set to obtain a second geographic location data set; obtaining a first selected location and a second selected location of each user according to the second geographic location data set; obtaining IP address data corresponding to fixed terminals used by the plurality of users to generate an IP address data set; pre-processing the IP address data set to obtain a plurality of IP sections; obtaining a plurality of first selected locations and second selected locations corresponding to the users of each IP section; and clustering the plurality of first selected locations and second selected locations to obtain the IP location of the IP section. The present disclosure achieves an IP positioning precision on a street level and has advantageous of simple arrangement and fast response speed.

Method for positioning IP location and server

Growing community of inventors

Shenzhen, China

Juhong Wang