Patents by Inventor Khoi-Nguyen C. Mac

Khoi-Nguyen C. Mac 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 detection by exploiting motion in receptive fields
    Patent number: 11521044
    Abstract: Techniques regarding action detection based on motion in receptive fields of a neural network model are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise a motion component that can extract a motion vector from a plurality of adaptive receptive fields in a deformable convolution layer of a neural network model. The computer executable components can also comprise an action detection component that can generate a spatio-temporal feature by concatenating the motion vector with a spatial feature extracted from the deformable convolution layer.
    Type: Grant
    Filed: May 17, 2018
    Date of Patent: December 6, 2022
    Assignees: INTERNATIONAL BUSINESS MACHINES CORPORATION, THE BOARD OF TRUSTEES OF THE UNIVERSITY OF ILLINOIS
    Inventors: Khoi-Nguyen C. Mac, Raymond Alexander Yeh, Dhiraj Joshi, Minh N. Do, Rogerio Feris, Jinjun Xiong
  • ACTION DETECTION BY EXPLOITING MOTION IN RECEPTIVE FIELDS
    Publication number: 20190354835
    Abstract: Techniques regarding action detection based on motion in receptive fields of a neural network model are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise a motion component that can extract a motion vector from a plurality of adaptive receptive fields in a deformable convolution layer of a neural network model. The computer executable components can also comprise an action detection component that can generate a spatio-temporal feature by concatenating the motion vector with a spatial feature extracted from the deformable convolution layer.
    Type: Application
    Filed: May 17, 2018
    Publication date: November 21, 2019
    Inventors: Khoi-Nguyen C. Mac, Raymond Alexander Yeh, Dhiraj Joshi, Minh N. Do, Rogerio Feris, Jinjun Xiong