Patents by Inventor Yonglong Tian

Yonglong Tian 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).

  • Publication number: 20230153629
    Abstract: The present disclosure provides an improved training methodology that enables supervised contrastive learning to be simultaneously performed across multiple positive and negative training examples. In particular, example aspects of the present disclosure are directed to an improved, supervised version of the batch contrastive loss, which has been shown to be very effective at learning powerful representations in the self-supervised setting Thus, the proposed techniques adapt contrastive learning to the fully supervised setting and also enable learning to occur simultaneously across multiple positive examples.
    Type: Application
    Filed: April 12, 2021
    Publication date: May 18, 2023
    Inventors: Dilip Krishnan, Prannay Khosla, Piotr Teterwak, Aaron Yehuda Sarna, Aaron Joseph Maschinot, Ce Liu, Philip John Isola, Yonglong Tian, Chen Wang
  • Patent number: 11347975
    Abstract: The present disclosure provides an improved training methodology that enables supervised contrastive learning to be simultaneously performed across multiple positive and negative training examples. In particular, example aspects of the present disclosure are directed to an improved, supervised version of the batch contrastive loss, which has been shown to be very effective at learning powerful representations in the self-supervised setting. Thus, the proposed techniques adapt contrastive learning to the fully supervised setting and also enable learning to occur simultaneously across multiple positive examples.
    Type: Grant
    Filed: April 21, 2021
    Date of Patent: May 31, 2022
    Assignee: GOOGLE LLC
    Inventors: Dilip Krishnan, Prannay Khosla, Piotr Teterwak, Aaron Yehuda Sarna, Aaron Joseph Maschinot, Ce Liu, Phillip John Isola, Yonglong Tian, Chen Wang
  • Publication number: 20210326660
    Abstract: The present disclosure provides an improved training methodology that enables supervised contrastive learning to be simultaneously performed across multiple positive and negative training examples. In particular, example aspects of the present disclosure are directed to an improved, supervised version of the batch contrastive loss, which has been shown to be very effective at learning powerful representations in the self-supervised setting. Thus, the proposed techniques adapt contrastive learning to the fully supervised setting and also enable learning to occur simultaneously across multiple positive examples.
    Type: Application
    Filed: April 21, 2021
    Publication date: October 21, 2021
    Inventors: Dilip Krishnan, Prannay Khosla, Piotr Teterwak, Aaron Yehuda Sarna, Aaron Joseph Maschinot, Ce Liu, Phillip John Isola, Yonglong Tian, Chen Wang
  • Publication number: 20190188533
    Abstract: A method for pose recognition includes storing parameters for configuration of an automated pose recognition system for detection of a pose of a subject represented in a radio frequency input signal. The parameters having been determined by a first process including accepting training data including a number of images including poses of subjects and a corresponding number of radio frequency signals and executing a parameter training procedure to determine the parameters. The parameter training procedure including, receiving features characterizing the poses in each of the images, and determining the parameters that configure the automated pose recognition system to match the features characterizing the poses from the corresponding radio frequency signals.
    Type: Application
    Filed: December 19, 2018
    Publication date: June 20, 2019
    Inventors: Dina Katabi, Antonio Torralba, Hang Zhao, Mingmin Zhao, Tianhong ` Li, Mohammad Abualsheikh, Yonglong Tian