Patents by Inventor Boyuan DENG

Boyuan DENG has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Action recognition method and apparatus, computer storage medium, and computer device
    Patent number: 11928893
    Abstract: An action recognition method includes: obtaining original feature submaps of each of temporal frames on a plurality of convolutional channels by using a multi-channel convolutional layer; calculating, by using each of the temporal frames as a target temporal frame, motion information weights of the target temporal frame on the convolutional channels according to original feature submaps of the target temporal frame and original feature submaps of a next temporal frame, and obtaining motion information feature maps of the target temporal frame on the convolutional channels according to the motion information weights; performing temporal convolution on the motion information feature maps of the target temporal frame to obtain temporal motion feature maps of the target temporal frame; and recognizing an action type of a moving object in image data of the target temporal frame according to the temporal motion feature maps of the target temporal frame on the convolutional channels.
    Type: Grant
    Filed: November 18, 2021
    Date of Patent: March 12, 2024
    Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
    Inventors: Donghao Luo, Yabiao Wang, Chenyang Guo, Boyuan Deng, Chengjie Wang, Jilin Li, Feiyue Huang, Yongjian Wu
  • ACTION RECOGNITION METHOD AND APPARATUS, COMPUTER STORAGE MEDIUM, AND COMPUTER DEVICE
    Publication number: 20220076002
    Abstract: An action recognition method includes: obtaining original feature submaps of each of temporal frames on a plurality of convolutional channels by using a multi-channel convolutional layer; calculating, by using each of the temporal frames as a target temporal frame, motion information weights of the target temporal frame on the convolutional channels according to original feature submaps of the target temporal frame and original feature submaps of a next temporal frame, and obtaining motion information feature maps of the target temporal frame on the convolutional channels according to the motion information weights; performing temporal convolution on the motion information feature maps of the target temporal frame to obtain temporal motion feature maps of the target temporal frame; and recognizing an action type of a moving object in image data of the target temporal frame according to the temporal motion feature maps of the target temporal frame on the convolutional channels.
    Type: Application
    Filed: November 18, 2021
    Publication date: March 10, 2022
    Inventors: Donghao LUO, Yabiao WANG, Chenyang GUO, Boyuan DENG, Chengjie WANG, Jilin LI, Feiyue HUANG, Yongjian WU