Patents by Inventor Dengpan FU

Dengpan FU 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).

  • Subject identification based on iterated feature representation
    Patent number: 11810385
    Abstract: A computer-vision method includes recognizing a feature representation of a query image depicting an unknown subject. A similarity score is computed between the representation of the query image and feature representations of a plurality of gallery images collectively depicting two or more different subjects with at least two or more gallery images for each subject, and each gallery image having a label identifying which of the subjects is depicted. One or more updated feature representations of the query image are sequentially iterated based on one or more of the computed similarity scores. For each of the one or more updated feature representations, an updated similarity score is computed between the updated feature representation and the feature representations of each of the gallery images. The unknown subject is identified based on a gallery image having a highest updated similarity score.
    Type: Grant
    Filed: December 28, 2020
    Date of Patent: November 7, 2023
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Dongdong Chen, Dengpan Fu, Jingdong Wang, Jianmin Bao
  • SUBJECT IDENTIFICATION BASED ON ITERATED FEATURE REPRESENTATION
    Publication number: 20220207264
    Abstract: A computer-vision method includes recognizing a feature representation of a query image depicting an unknown subject. A similarity score is computed between the representation of the query image and feature representations of a plurality of gallery images collectively depicting two or more different subjects with at least two or more gallery images for each subject, and each gallery image having a label identifying which of the subjects is depicted. One or more updated feature representations of the query image are sequentially iterated based on one or more of the computed similarity scores. For each of the one or more updated feature representations, an updated similarity score is computed between the updated feature representation and the feature representations of each of the gallery images. The unknown subject is identified based on a gallery image having a highest updated similarity score.
    Type: Application
    Filed: December 28, 2020
    Publication date: June 30, 2022
    Applicant: Microsoft Technology Licensing, LLC
    Inventors: Dongdong CHEN, Dengpan FU, Jingdong WANG, Jianmin BAO