Patents by Inventor Kai Zhang

Kai Zhang 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).

  • DERIVATION OF LINEAR PARAMETER IN CROSS-COMPONENT VIDEO CODING
    Publication number: 20230073705
    Abstract: A method of video processing includes deriving, for a conversion between a chroma block of a video and a bitstream representation of the video, parameters of a cross-component linear model by using downsampled luma samples that are generated from N above neighboring lines of a collocated luma block of the chroma block using a downsampling filter, where N is a positive integer; and performing the conversion using a predicted chroma block generated using the cross-component linear model.
    Type: Application
    Filed: November 3, 2022
    Publication date: March 9, 2023
    Inventors: Yang Wang, Li Zhang, Kai Zhang, Hongbin Liu, Yue Wang
  • MEASURING TAPE WITH IMPROVED ROLL-OVER PREVENTION
    Publication number: 20230072940
    Abstract: A measuring assembly for a measuring tape device may include a blade, an end hook and an anti-rollover attachment. The blade may include a first end configured to extend from an aperture in a housing of the measuring tape device and a second end configured to be wound on a reel assembly. The end hook may be disposed at the first end of the blade to engage an object for measurement, and may extend substantially perpendicular to a longitudinal centerline of the blade to extend away from an underside of the blade. The anti-rollover attachment may be disposed proximate to the end hook at the first end of the blade such that a center of gravity of the anti-rollover attachment is spaced apart from the underside of the blade. A combined weight of the end hook and the anti-rollover attachment may be in a range between about 10 grams and about 55 grams.
    Type: Application
    Filed: March 9, 2021
    Publication date: March 9, 2023
    Inventors: Kai Zhang, Charles Wang
  • SYNTAX FOR SIGNALING CROSS-COMPONENT VIDEO CODING
    Publication number: 20230075048
    Abstract: A method of video processing is provided to include determining, for a conversion between a video block of a video and a bitstream of the video, a parameter of a cross-component linear model (CCLM) for the video block according to a rule, and performing the conversion based on the determining, and wherein the rule specifies to use a variable representing a neighbouring luma sample in the determining of the parameter of the CCLM only in case that the variable has a certain value.
    Type: Application
    Filed: October 18, 2022
    Publication date: March 9, 2023
    Inventors: Yang Wang, Li Zhang, Kai Zhang, Hongbin Liu, Yue Wang
  • ADAPTIVE LOOP FILTERING
    Publication number: 20230071955
    Abstract: Methods, systems and apparatus for video processing are described. One example video processing method includes performing a conversion between a video including a video region and a bitstream of the video according to a rule, wherein the rule specifies that an adaptive loop filtering operation is allowed for the video region in response to an absence of one or more adaptation parameter set (APS) network abstraction layer (NAL) units that include adaptive loop filtering data.
    Type: Application
    Filed: September 12, 2022
    Publication date: March 9, 2023
    Inventors: Zhipin DENG, Ye-Kui WANG, Li ZHANG, Kai ZHANG
  • Signaling usage of adaptive loop filter in video coding
    Patent number: 11601686
    Abstract: Methods, systems and devices for signaling the usage of adaptive loop filtering in image and video coding are described. An example method of video processing includes determining, for a conversion between a current region of a video and a bitstream representation of the video, whether a luma adaptive loop filter is used during the conversion and whether luma adaptive loop filter coefficients are included in the bitstream representation, wherein a single syntax element in the bitstream representation is indicative of use of the luma adaptive loop filter and signaling of the luma adaptive loop filter coefficients, and performing, based on the determining, the conversion.
    Type: Grant
    Filed: March 16, 2022
    Date of Patent: March 7, 2023
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD., BYTEDANCE INC.
    Inventors: Li Zhang, Hongbin Liu, Kai Zhang, Yue Wang
  • Multifunction mouse
    Patent number: 11599207
    Abstract: A computer mouse include a base; a cover assembly releasably secured to the base and including an opening; and a rotational device disposed in the opening to rotatably secure to the base. The rotational device includes a disc-shaped external rotational member including a circular flange on one surface, the circular flange disposed through the opening to rotatably secure to the base, the circular flange having a through hole; and a disc-shaped internal rotational member partially disposed in the through hole.
    Type: Grant
    Filed: July 8, 2022
    Date of Patent: March 7, 2023
    Inventor: Kai Zhang
  • Coding mode determination based on color format
    Patent number: 11601652
    Abstract: A method of video processing is described. The method includes determining, for a conversion between a video region of a video and a coded representation of the video, an intra coding characteristic of the video region based on a color format of the video according to a rule; and performing the conversion according to the intra coding characteristic.
    Type: Grant
    Filed: March 2, 2022
    Date of Patent: March 7, 2023
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD., BYTEDANCE INC.
    Inventors: Jizheng Xu, Zhipin Deng, Li Zhang, Hongbin Liu, Kai Zhang
  • Methods and systems for integrating model development control systems and model validation platforms
    Patent number: 11599444
    Abstract: Methods and systems are described herein for integrating model development control systems and model validation platforms. For example, the methods and systems discussed herein recite the creation and use of a model validation platform. This platform operates outside of the environment of the independently validated models as well as the native platform into which the independently validated models may be incorporated. The model validation platform may itself include a model that systematically validates other independently validated models. The model validation platform may then provide users substantive analysis of a model and its performance through one or more user interface tools such as side-by-side comparisons, recommended adjustments, and/or a plurality of adjustable model attributes for use in validating an inputted model.
    Type: Grant
    Filed: February 3, 2022
    Date of Patent: March 7, 2023
    Assignee: Capital One Services, LLC
    Inventors: Yu Lin, Qian Shen, Zhenyu Liu, Kai Zhang, Kangning Li, Yanni Ding, Jie Tang, Piero Monteverde
  • Use Restrictions For Cross-Component Prediction
    Publication number: 20230063736
    Abstract: A method of video processing is provided. The method includes determining, for a conversion between a video comprising a video unit and a bitstream of the video, whether a first coding tool is enabled for the video unit according to a rule. The rule specifies that the first coding tool and a second coding tool are mutually exclusively enabled. The first coding tool or the second coding tool comprises a sign data hiding tool. The method also includes performing the conversion according to the determining.
    Type: Application
    Filed: October 18, 2022
    Publication date: March 2, 2023
    Inventors: Yang Wang, Li Zhang, Kai Zhang, Hongbin Liu, Yue Wang
  • PRESENCE OF ADAPTATION PARAMETER SET UNITS
    Publication number: 20230066409
    Abstract: Systems, methods and apparatus for video processing are described. The video processing may include video encoding, video decoding, or video transcoding. One example method of video processing includes performing a conversion between a video comprising one or more pictures comprising one or more slices and a bitstream of the video. The bitstream conforms to a predefined order between a position of a first NAL (network abstraction layer) unit in a picture unit carrying an adaptation parameter set information and a second NAL unit that is a last video coding layer (VCL) NAL unit in the picture unit.
    Type: Application
    Filed: October 17, 2022
    Publication date: March 2, 2023
    Inventors: Zhipin Deng, Li Zhang, Ye-kui Wang, Kai Zhang
  • MODE DETERMINING FOR PALETTE MODE IN PREDICTION PROCESS
    Publication number: 20230060824
    Abstract: Devices, systems and methods for video processing are described. An example method for video processing includes performing a conversion between a video comprising luma blocks and corresponding chroma blocks and a bitstream representation of the video according to a rule that specifies that, for a case that a current luma block is coded using a palette coding mode and a corresponding current chroma block coded with a derived mode, the current luma block is treated as having a default intra prediction mode and the current chroma block is coded with the default intra prediction mode.
    Type: Application
    Filed: January 20, 2022
    Publication date: March 2, 2023
    Inventors: Weijia ZHU, Li ZHANG, Jizheng XU, Kai ZHANG, Hongbin LIU, Yue WANG
  • Coding Of Instantaneous Decoding Refresh Subpictures
    Publication number: 20230063887
    Abstract: Methods and apparatus for video processing are described. The processing may include video encoding, video decoding, or video transcoding. An example video processing method includes performing a conversion between a video including one or more pictures including one or more subpictures and a bitstream of the video. The one or more pictures and/or the one or more subpictures are included into the bitstream according to an order rule. The order rule specifies a relationship between a position of a current instantaneous decoder refresh (IDR) picture or a current IDR subpicture in the bitstream with respect to another picture referred to by an entry in a reference picture list for a current slice of the current IDR picture or the current IDR subpicture.
    Type: Application
    Filed: October 12, 2022
    Publication date: March 2, 2023
    Inventors: Ye-kui Wang, Li Zhang, Kai Zhang
  • CROSS-COMPONENT CODING OF 4:2:0 OR 4:2:2 VIDEO
    Publication number: 20230069756
    Abstract: A method of video processing is provided to include determining, for a conversion between a video block of a video having a 4:2:2 color format and a bitstream of the video, a parameter of a cross-component linear model for the video block according to a rule and performing the conversion based on the determining, wherein a syntax element indicates whether chroma samples of the video are vertically shifted relative to luma samples of the video and wherein the rule specifies that the parameter is determined independent of a value of the syntax element.
    Type: Application
    Filed: October 18, 2022
    Publication date: March 2, 2023
    Inventors: Yang Wang, Li Zhang, Kai Zhang, Hongbin Liu, Yue Wang
  • INTERACTION BETWEEN LUT AND AMVP
    Publication number: 20230064498
    Abstract: A method of video decoding is provided to include maintaining tables, wherein each table includes a set of motion candidates and each motion candidate is associated with corresponding motion information; and performing a conversion between a first video block and a bitstream representation of a video including the first video block, the performing of the conversion including using at least some of the set of motion candidates as a predictor to process motion information of the first video block.
    Type: Application
    Filed: October 27, 2022
    Publication date: March 2, 2023
    Inventors: Li Zhang, Kai Zhang, Hongbin Liu, Yue Wang
  • TRANSFORM SKIP RESIDUAL CODING
    Publication number: 20230063674
    Abstract: Several techniques for video encoding and video decoding are described. One example method includes performing a conversion between a block of a video and a bitstream of the video according to a rule. The rule specifies that whether a syntax flag indicating whether transform skip residual coding is enabled at a video unit level is present in the bitstream is based on values of a first syntax element indicating usage of sign data hiding in the video unit and a second syntax element indicating usage of dependent quantization in the video unit.
    Type: Application
    Filed: October 19, 2022
    Publication date: March 2, 2023
    Inventors: Ye-Kui Wang, Li Zhang, Kai Zhang, Zhipin Deng
  • WEIGHTED PREDICTION IN VIDEO CODING
    Publication number: 20230067372
    Abstract: A video processing method includes generating, for a conversion between a current block of a video and a bitstream representation of the video, a motion vector for the current block; invoking a weighted prediction processing tool or a second processing tool in a mutually exclusive manner; and performing the conversion according to the invoking. The invoking of the second processing tool comprises refining the motion vector.
    Type: Application
    Filed: October 27, 2022
    Publication date: March 2, 2023
    Inventors: Hongbin Liu, Li Zhang, Kai Zhang, Yue Wang
  • Geometric partitioning mode in video coding
    Patent number: 11595649
    Abstract: A method of visual media processing, including: determining, fora conversion between a current video block of a visual media data and a bitstream representation of the visual media data, that a partitioning mode coding tool is disabled for the conversion based on a rule that depends on a dimension of the current video block; and performing the conversion based on the determining.
    Type: Grant
    Filed: March 28, 2022
    Date of Patent: February 28, 2023
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD., BYTEDANCE INC.
    Inventors: Li Zhang, Kai Zhang, Hongbin Liu, Yue Wang
  • Context-based intra prediction
    Patent number: 11595687
    Abstract: A method for video processing is provided. The method includes performing downsampling on chroma and luma samples of a neighboring block of the current video block; determining, for a conversion between a current video block of a video that is a chroma block and a coded representation of the video, parameters of cross-component linear model (CCLM) based on the downsampled chroma and luma samples obtained from the downsampling; applying the CCLM on luma samples located in a luma block corresponding to the current video block to derive prediction values of the current video block; and performing the conversion based on the prediction values.
    Type: Grant
    Filed: June 3, 2021
    Date of Patent: February 28, 2023
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD., BYTEDANCE INC.
    Inventors: Kai Zhang, Li Zhang, Hongbin Liu, Jizheng Xu, Yue Wang
  • Alternative interpolation filters in video coding
    Patent number: 11595641
    Abstract: A method of video processing is provided to include: deciding a coding mode used for representing a current video block of a video in a coded representation of the video; and coding the current video block into the coded representation according to the coding mode, wherein use of alternative half-pel accuracy filters in addition to a default half-pel accuracy filter for representing motion information is disabled for the current video block due to use of the coding mode.
    Type: Grant
    Filed: September 24, 2021
    Date of Patent: February 28, 2023
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD., BYTEDANCE INC.
    Inventors: Hongbin Liu, Li Zhang, Kai Zhang, Jizheng Xu, Yue Wang
  • Priority-based non-adjacent merge design
    Patent number: 11595683
    Abstract: Devices, systems and methods for constructing low-complexity non-adjacent merge candidates. In a representative aspect, a method for video processing includes receiving a current block of video data, selecting, based on a rule, a first non-adjacent block that is not adjacent to the current block, constructing a first merge candidate comprising motion information based on the first non-adjacent block, identifying a second non-adjacent block that is not adjacent to the current block and different from the first non-adjacent block, based on determining that the second non-adjacent block fails to satisfy the rule, refraining adding a second merge candidate derived from the second non-adjacent block, constructing a merge candidate list based on the first non-adjacent block, and decoding the current block based on the merge candidate list.
    Type: Grant
    Filed: December 31, 2020
    Date of Patent: February 28, 2023
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD., BYTEDANCE INC.
    Inventors: Li Zhang, Kai Zhang, Hongbin Liu, Yue Wang