Patents by Inventor Jingwei SONG

Jingwei SONG 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).

  • MUTANT IDH1 AND IDH2 INHIBITOR AND APPLICATION THEREOF
    Publication number: 20250051301
    Abstract: Disclosed are a compound represented by formula (I) as a mutant isocitrate dehydrogenase 1 and 2 (IDH1 and IDH2) inhibitor, a preparation method therefor, and a pharmaceutical composition thereof. Also disclosed is a use of the described compound or the pharmaceutical composition thereof in the treatment of mutant IDH1 and IDH2-mediated diseases.
    Type: Application
    Filed: March 14, 2023
    Publication date: February 13, 2025
    Inventors: Yabin Li, Xiaofeng Xu, Xizhen Song, Jingwei Ding, Yunlai Zhang, Jie Chen, Xiangyong Liu, Lieming Ding, Jiabing Wang
  • Fusing deep learning and geometric constraint for image-based localization
    Patent number: 11227406
    Abstract: A computer-implemented method, comprising applying training images of an environment divided into zones to a neural network, and performing classification to label a test image based on a closest zone of the zones; extracting a feature from retrieved training images and pose information of the test image that match the closest zone; performing bundle adjustment on the extracted feature by triangulating map points for the closest zone to generate a reprojection error, and minimizing the reprojection error to determine an optimal pose of the test image; and for the optimal pose, providing an output indicative of a location or probability of a location of the test image at the optimal pose within the environment.
    Type: Grant
    Filed: February 28, 2020
    Date of Patent: January 18, 2022
    Assignee: FUJIFILM Business Innovation Corp.
    Inventors: Miteshkumar Patel, Jingwei Song, Andreas Girgensohn, Chelhwon Kim
  • FUSING DEEP LEARNING AND GEOMETRIC CONSTRAINT FOR IMAGE-BASED LOCALIZATION
    Publication number: 20210272317
    Abstract: A computer-implemented method, comprising applying training images of an environment divided into zones to a neural network, and performing classification to label a test image based on a closest zone of the zones; extracting a feature from retrieved training images and pose information of the test image that match the closest zone; performing bundle adjustment on the extracted feature by triangulating map points for the closest zone to generate a reprojection error, and minimizing the reprojection error to determine an optimal pose of the test image; and for the optimal pose, providing an output indicative of a location or probability of a location of the test image at the optimal pose within the environment.
    Type: Application
    Filed: February 28, 2020
    Publication date: September 2, 2021
    Inventors: Miteshkumar PATEL, Jingwei SONG, Andreas GIRGENSOHN, Chelhwon KIM