Tencent Technology (shenzhen) Company Limited

Haoyuan Li

Feng Li

Jun Cheng

Xiaoxiang Zuo

Shundong Gao

Xingshi Bai

Xingjun Xiao

Haibao Shang

Ying Zhu

Tong Ai

Qifeng Chen

Hongrui Chen

Wenran Liu

This disclosure provides a method and a system for detecting and recognizing a target object in a real-time video. The method includes: determining whether a target object recognition result Rof a previous frame of image of a current frame of image is the same as a target object recognition result Rof a previous frame of image of the previous frame of image; performing target object position detection in the current frame of image by using a first-stage neural network to obtain a position range Cof a target object in the current frame of image when the two recognition results Rand Rare different; or determining a position range Cof a target object in the current frame of image according to a position range Cof the target object in the previous frame of image when the two recognition results Rand Rare the same; and performing target object recognition in the current frame of image according to the position range Cby using a second-stage neural network. Therefore, the operating frequency of the first-stage neural network used for position detection is reduced, the recognition speed is accelerated, and the usage of CPU and internal memory resources is reduced.

Method and system for detecting and recognizing target in real-time video, storage medium, and device

An image data processing method is provided. In the method, a first image data set that includes image data arranged according to a first data format is acquired. The first data format has a first number of dimensions. Interleaving and rearrangement are performed on the image data in the first image data set based on a convolution operation to obtain a second image data set. The image data in the second image data set is arranged according to a second data format. The second data format has a second number of dimensions. The second number of dimensions of the second data format is less than first number of dimensions of the first data format. A target output result is generated based on the convolution operation performed on the second image data set and a second weight data set. Apparatus and non-transitory computer-readable storage medium counterpart embodiments are also contemplated.

Interleaving and rearrangement to reduce a number of dimensions of image

A method and an apparatus for data calculation in a neural network model, and an image processing method and apparatus. The method for data calculation includes: reading weight data shared by a group of data processing of a data processing layer in a neural network model, into a GroupShared variable of a thread group of a graphics processing unit (GPU), dividing input data of the data processing layer based on the number of threads in the thread group, reading, for each group of input data, weight data corresponding to the group of input data for a data processing in the group of data processing from the GroupShared variable, and performing, by each thread in the thread group, the data processing by using a group of read input data and weight data corresponding to the group of input data, to obtain a calculation result corresponding to the group of input data.

Method and apparatus for data calculation in neural network model, and image processing method and apparatus

A method for performing a conference communication by an intelligent is disclosed. The method includes sending, via a conference link to a conference server, an access request specifying a mapping character string and an identifier of an operating system running in the intelligent terminal; receiving a protocol string from the conference server generated according to the mapping character string and the identifier in the access request, the protocol string comprising a conference attendance credential; automatically initiating an instant message (IM) client in the operating system according to the protocol string; and sending an IM user identifier associated with the intelligent terminal and the conference attendance credential to the conference server to add the IM user identifier to a temporary IM user group corresponding to the conference attendance credential and establishing an Internet channel for the temporary IM user group to perform the conference communication via the IM client.

Method, device, and system for facilitating group conference communication

This application relates to an image processing method and apparatus, a storage medium, and a computer device. The method includes obtaining acquired image frames; identifying, in each obtained image frame, a target area and a reference area that are obtained through image semantic segmentation; detecting, when a location relationship between the target area and the reference area in an obtained first image frame meets an action start condition and a location relationship between the target area and the reference area in an obtained second image frame meets an action end condition, an action to trigger adding an additional element, the second image frame being acquired after the first image frame; obtaining the additional element when the triggering action is detected; and adding the additional element to image frames acquired after the second image frame.

Image processing method, apparatus, and storage medium

A method for recognizing object nodes in an image includes: performing image detection on an original image, to determine a target image region that comprises a target image object, the original image being a two-dimensional image; performing image cropping on the original image according to the target image region, to obtain a subimage comprising the target image object; and performing node recognition on the subimage based on a preset node recognition model, to obtain image position information of each node of the target image object in the original image.

Method and terminal for recognizing object node in image, and computer-readable storage medium

A conferencing communication method is disclosed, including: sending a protocol string to an intelligent terminal, so that the intelligent terminal invokes a corresponding instant messaging client according to the protocol string; receiving an instant messaging user identifier that has logged in and that is sent by the instant messaging client and an attendance credential included in the protocol string; adding the instant messaging user identifier to an instant messaging user group corresponding to the attendance credential; and establishing an Internet channel that is based on the instant messaging user group to the instant messaging client, the Internet channel being used for transmitting communication data of a member in the instant messaging user group.

Growing community of inventors

Shenzhen, China

Haoyuan Li