Patents by Inventor Yogesh Balaji

Yogesh Balaji 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).

  • Multi-scale text filter conditioned generative adversarial networks
    Patent number: 11170256
    Abstract: Systems and methods for processing video are provided. The method includes receiving a text-based description of active scenes and representing the text-based description as a word embedding matrix. The method includes using a text encoder implemented by neural network to output frame level textual representation and video level representation of the word embedding matrix. The method also includes generating, by a shared generator, frame by frame video based on the frame level textual representation, the video level representation and noise vectors. A frame level and a video level convolutional filter of a video discriminator are generated to classify frames and video of the frame by frame video as true or false. The method also includes training a conditional video generator that includes the text encoder, the video discriminator, and the shared generator in a generative adversarial network to convergence.
    Type: Grant
    Filed: September 20, 2019
    Date of Patent: November 9, 2021
    Inventors: Renqiang Min, Bing Bai, Yogesh Balaji
  • MULTI-SCALE TEXT FILTER CONDITIONED GENERATIVE ADVERSARIAL NETWORKS
    Publication number: 20200097766
    Abstract: Systems and methods for processing video are provided. The method includes receiving a text-based description of active scenes and representing the text-based description as a word embedding matrix. The method includes using a text encoder implemented by neural network to output frame level textual representation and video level representation of the word embedding matrix. The method also includes generating, by a shared generator, frame by frame video based on the frame level textual representation, the video level representation and noise vectors. A frame level and a video level convolutional filter of a video discriminator are generated to classify frames and video of the frame by frame video as true or false. The method also includes training a conditional video generator that includes the text encoder, the video discriminator, and the shared generator in a generative adversarial network to convergence.
    Type: Application
    Filed: September 20, 2019
    Publication date: March 26, 2020
    Inventors: Renqiang Min, Bing Bai, Yogesh Balaji