Patents by Inventor Akarsh Umesh Zingade

Akarsh Umesh Zingade 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).

  • IDENTIFYING POSITIONS OF OCCLUDED OBJECTS
    Publication number: 20250061729
    Abstract: Apparatuses, systems, and techniques to identify three-dimensional positions of partially occluded objects in images. In at least one embodiment, one or more neural networks identify the three-dimensional positions of occluded portions of objects in a first image based, at least in part, on one or more second images including non-occluded objects.
    Type: Application
    Filed: August 25, 2023
    Publication date: February 20, 2025
    Inventors: Prash Goel, Umar Iqbal, Akarsh Umesh Zingade, Pavlo Molchanov
  • MACHINE LEARNING TECHNIQUES FOR ENHANCING VIDEO CONFERENCING APPLICATIONS
    Publication number: 20230394627
    Abstract: Systems, processes, and techniques to automatically detect and enlarge a speaking one of plurality of participants on one side of a video conference. In at least one embodiment, the speaking participant is identified using one or more heuristics and/or one or more neural networks.
    Type: Application
    Filed: August 21, 2023
    Publication date: December 7, 2023
    Inventors: Akarsh Umesh Zingade, Jianyuan Min, Shuye Han, Rochelle Pereira
  • Machine learning techniques for enhancing video conferencing applications
    Patent number: 11748845
    Abstract: Systems, processes, and techniques to automatically detect and enlarge a speaking one of plurality of participants on one side of a video conference. In at least one embodiment, the speaking participant is identified using one or more heuristics and/or one or more neural networks.
    Type: Grant
    Filed: January 27, 2021
    Date of Patent: September 5, 2023
    Assignee: NVIDIA Corporation
    Inventors: Akarsh Umesh Zingade, Jianyuan Min, Shuye Han, Rochelle Pereira
  • MACHINE LEARNING TECHNIQUES FOR ENHANCING VIDEO CONFERENCING APPLICATIONS
    Publication number: 20220237735
    Abstract: Systems, processes, and techniques to automatically detect and enlarge a speaking one of plurality of participants on one side of a video conference. In at least one embodiment, the speaking participant is identified using one or more heuristics and/or one or more neural networks.
    Type: Application
    Filed: January 27, 2021
    Publication date: July 28, 2022
    Inventors: Akarsh Umesh Zingade, Jianyuan Min, Shuye Han, Rochelle Pereira