Patents by Inventor Sheide Chammas

Sheide Chammas 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).

  • Hierarchical Video Encoders
    Publication number: 20240114158
    Abstract: A computer-implemented method for generating video representations utilizing a hierarchical video encoder includes obtaining a video, wherein the video includes a plurality of frames, processing each of the plurality of frames with a machine-learned frame-level encoder model to respectively generate a plurality of frame representations for the plurality of frames, the plurality of frame representations respective to the plurality of frames determining a plurality of segment representations representative of a plurality of video segments including one or more of the plurality of frames, the plurality of segment representations based at least in part on the plurality of frame representations, processing the plurality of segment representations with a machine-learned segment-level encoder model to generate a plurality of contextualized segment representations, determining a video representation based at least in part on the plurality of contextualized segment representations, and providing the video representati
    Type: Application
    Filed: December 5, 2023
    Publication date: April 4, 2024
    Inventors: Vihan Jain, Joonseok Lee, Ming Zhao, Sheide Chammas, Hexiang Hu, Bowen Zhang, Fei Sha, Tze Way Eugene Ie
  • Hierarchical video encoders
    Patent number: 11876986
    Abstract: A computer-implemented method for generating video representations utilizing a hierarchical video encoder includes obtaining a video, wherein the video includes a plurality of frames, processing each of the plurality of frames with a machine-learned frame-level encoder model to respectively generate a plurality of frame representations for the plurality of frames, the plurality of frame representations respective to the plurality of frames determining a plurality of segment representations representative of a plurality of video segments including one or more of the plurality of frames, the plurality of segment representations based at least in part on the plurality of frame representations, processing the plurality of segment representations with a machine-learned segment-level encoder model to generate a plurality of contextualized segment representations, determining a video representation based at least in part on the plurality of contextualized segment representations, and providing the video representati
    Type: Grant
    Filed: November 29, 2022
    Date of Patent: January 16, 2024
    Assignee: GOOGLE LLC
    Inventors: Vihan Jain, Joonseok Lee, Ming Zhao, Sheide Chammas, Hexiang Hu, Bowen Zhang, Fei Sha, Tze Way Eugene Ie
  • Hierarchical Video Encoders
    Publication number: 20230103148
    Abstract: A computer-implemented method for generating video representations utilizing a hierarchical video encoder includes obtaining a video, wherein the video includes a plurality of frames, processing each of the plurality of frames with a machine-learned frame-level encoder model to respectively generate a plurality of frame representations for the plurality of frames, the plurality of frame representations respective to the plurality of frames determining a plurality of segment representations representative of a plurality of video segments including one or more of the plurality of frames, the plurality of segment representations based at least in part on the plurality of frame representations, processing the plurality of segment representations with a machine-learned segment-level encoder model to generate a plurality of contextualized segment representations, determining a video representation based at least in part on the plurality of contextualized segment representations, and providing the video representati
    Type: Application
    Filed: November 29, 2022
    Publication date: March 30, 2023
    Inventors: Vihan Jain, Joonseok Lee, Ming Zhao, Sheide Chammas, Hexiang Hu, Bowen Zhang, Fei Sha, Tze Way Eugene Ie
  • Hierarchical video encoders
    Patent number: 11533495
    Abstract: A computer-implemented method for generating video representations utilizing a hierarchical video encoder includes obtaining a video, wherein the video includes a plurality of frames, processing each of the plurality of frames with a machine-learned frame-level encoder model to respectively generate a plurality of frame representations for the plurality of frames, the plurality of frame representations respective to the plurality of frames determining a plurality of segment representations representative of a plurality of video segments including one or more of the plurality of frames, the plurality of segment representations based at least in part on the plurality of frame representations, processing the plurality of segment representations with a machine-learned segment-level encoder model to generate a plurality of contextualized segment representations, determining a video representation based at least in part on the plurality of contextualized segment representations, and providing the video representati
    Type: Grant
    Filed: January 29, 2021
    Date of Patent: December 20, 2022
    Assignee: GOOGLE LLC
    Inventors: Vihan Jain, Joonseok Lee, Ming Zhao, Sheide Chammas, Hexiang Hu, Bowen Zhang, Fei Sha, Tze Way Eugene Ie
  • Hierarchical Video Encoders
    Publication number: 20220256175
    Abstract: A computer-implemented method for generating video representations utilizing a hierarchical video encoder includes obtaining a video, wherein the video includes a plurality of frames, processing each of the plurality of frames with a machine-learned frame-level encoder model to respectively generate a plurality of frame representations for the plurality of frames, the plurality of frame representations respective to the plurality of frames determining a plurality of segment representations representative of a plurality of video segments including one or more of the plurality of frames, the plurality of segment representations based at least in part on the plurality of frame representations, processing the plurality of segment representations with a machine-learned segment-level encoder model to generate a plurality of contextualized segment representations, determining a video representation based at least in part on the plurality of contextualized segment representations, and providing the video representati
    Type: Application
    Filed: January 29, 2021
    Publication date: August 11, 2022
    Inventors: Vihan Jain, Joonseok Lee, Ming Zhao, Sheide Chammas, Hexiang Hu, Bowen Zhang, Fei Sha, Tze Way Eugene Ie