Patents by Inventor Ruijie Xu

Ruijie Xu 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: 10694216
    Abstract: Separate pathways for filtering and for machine learning are introduced within a video coder. A first pathway filters a first copy of a reconstructed frame to produce a filtered frame, which is included in an output video stream for display at a user device. A second pathway processes a second copy of the reconstructed frame using a learning model, such as for training and/or inference. The first and second pathways are introduced after the reconstruction stage of an encoder or decoder. The input to each of the first and second pathways is thus produced without using a non-injective function, and, while the first pathway includes at least one non-injective function, the second pathway does not. As a result, training the learning model using the second copy of the reconstructed frame results in a greater classification accuracy upper bound than training the learning model using the filtered frame.
    Type: Grant
    Filed: September 11, 2018
    Date of Patent: June 23, 2020
    Assignee: GOOGLE LLC
    Inventors: Ruijie Xu, Dake He
  • Publication number: 20200084478
    Abstract: Separate pathways for filtering and for machine learning are introduced within a video coder. A first pathway filters a first copy of a reconstructed frame to produce a filtered frame, which is included in an output video stream for display at a user device. A second pathway processes a second copy of the reconstructed frame using a learning model, such as for training and/or inference. The first and second pathways are introduced after the reconstruction stage of an encoder or decoder. The input to each of the first and second pathways is thus produced without using a non-injective function, and, while the first pathway includes at least one non-injective function, the second pathway does not. As a result, training the learning model using the second copy of the reconstructed frame results in a greater classification accuracy upper bound than training the learning model using the filtered frame.
    Type: Application
    Filed: September 11, 2018
    Publication date: March 12, 2020
    Inventors: Ruijie Xu, Dake He
  • Publication number: 20190045226
    Abstract: Systems and methods are disclosed for entropy coding of blocks of image data. For example, methods may include partitioning a block of video data into a plurality of groups of elements; decoding, using an entropy decoder, data from an encoded bitstream to obtain, using a first scan order, elements of a first group from the plurality of groups of elements, wherein the first group includes elements forming a triangle in a corner of the block, and wherein the triangle includes elements of a first row and elements of a first column of the block; determining, based on the elements of the first group, a second scan order for a second group from the plurality of groups of elements; and decoding, using the entropy decoder, data from the encoded bitstream to obtain, using the second scan order, elements of the second group from the plurality of groups of elements.
    Type: Application
    Filed: August 8, 2017
    Publication date: February 7, 2019
    Inventors: Ruijie Xu, Dake He
  • Publication number: 20190045225
    Abstract: Systems and methods are disclosed for entropy coding of blocks of image data. For example, methods may include partitioning a block of video data into a plurality of groups of elements; decoding, using an entropy decoder, data from an encoded bitstream to obtain elements of a first group from the plurality of groups of elements; determining a category based on the elements of the first group; based on the category, selecting a context for an element from a second group from the plurality of groups of elements; and decoding, using the entropy decoder using the context, data from the encoded bitstream to obtain the element of the second group from the plurality of groups of elements.
    Type: Application
    Filed: August 4, 2017
    Publication date: February 7, 2019
    Inventors: Ruijie Xu, Dake He