Patents by Inventor Michael Alcorn

Michael Alcorn 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).

  • Patent number: 11645328
    Abstract: Systems and methods for performing image search are described. An image search method may include generating a feature vector for each of a plurality of stored images using a machine learning model trained using a rotation loss term, receiving a search query comprising a search image with object having an orientation, generating a query feature vector for the search image using the machine learning model, wherein the query feature vector is based at least in part on the orientation, comparing the query feature vector to the feature vector for each of the plurality of stored images, and selecting at least one stored image of the plurality of stored images based on the comparison, wherein the at least one stored image comprises a similar orientation to the orientation of the object in the search image.
    Type: Grant
    Filed: March 17, 2020
    Date of Patent: May 9, 2023
    Assignee: ADOBE INC.
    Inventors: Long Mai, Michael Alcorn, Baldo Faieta, Vladimir Kim
  • Publication number: 20210294834
    Abstract: Systems and methods for performing image search are described. An image search method may include generating a feature vector for each of a plurality of stored images using a machine learning model trained using a rotation loss term, receiving a search query comprising a search image with object having an orientation, generating a query feature vector for the search image using the machine learning model, wherein the query feature vector is based at least in part on the orientation, comparing the query feature vector to the feature vector for each of the plurality of stored images, and selecting at least one stored image of the plurality of stored images based on the comparison, wherein the at least one stored image comprises a similar orientation to the orientation of the object in the search image.
    Type: Application
    Filed: March 17, 2020
    Publication date: September 23, 2021
    Inventors: Long Mai, Michael Alcorn, Baldo Faieta, Vladimir Kim
  • Publication number: 20070162418
    Abstract: A method and system for evaluating at least one setting for a database system are disclosed. The method and system includes providing at least one configuration derivative including the at least one setting. The configuration derivative is uncommitted. The method and system also include running the database system for a period of time. The database system is run using a committed configuration including a plurality of settings for the database system. The method and system also include collecting data on performance of the database system based on the at least one configuration derivative during the running of the database.
    Type: Application
    Filed: January 12, 2006
    Publication date: July 12, 2007
    Applicant: International Business Machines Corporation
    Inventors: Michael Alcorn, Upendra Chitnis