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).

  • NETWORK MODEL MANAGEMENT METHOD AND APPARATUS
    Publication number: 20240022470
    Abstract: This application provides a network model management method applied to a first device. The method includes obtaining first information of a network model, determining second information based on the first information, and sending the first and second information to a second device. The first information describes the network model. The second information indicates a network analysis function, and the network analysis function is allowed to use the network model. The foregoing method is used, so that the second device can establish an association relationship between the network model and the network analysis function, to implement real-time management for the network model.
    Type: Application
    Filed: September 27, 2023
    Publication date: January 18, 2024
    Applicant: HUAWEI TECHNOLOGIES CO., LTD.
    Inventors: Ruiyue XU, Lan ZOU, Kai ZHANG
  • Partition Signaling In Video Coding
    Publication number: 20240022723
    Abstract: Systems, methods, apparatus for video processing are described. A video processing method includes indicating, in a syntax element of a bitstream, a partitioning scheme of a plurality of partitioning schemes, wherein the partitioning scheme is applied to partition a current block in a video block, and performing a conversion between a visual media data and the bitstream based on partitioning scheme indicated in the syntax element.
    Type: Application
    Filed: September 28, 2023
    Publication date: January 18, 2024
    Inventors: Kai Zhang, Li Zhang, Zhipin Deng, Na Zhang, Yang Wang
  • Size selective application of decoder side refining tools
    Patent number: 11876932
    Abstract: One example method of video processing includes implementing, by a processor, a decoder-side motion vector derivation (DMVD) scheme for motion vector refinement during a conversion between a current video block and a bitstream representation of the current video block by deriving parameters based on a deriving rule. The conversion may include compressing the current video block into the bitstream representation or uncompressing the bitstream representation into pixel values of the current video block.
    Type: Grant
    Filed: December 21, 2021
    Date of Patent: January 16, 2024
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD, BYTEDANCE INC.
    Inventors: Hongbin Liu, Li Zhang, Kai Zhang, Jizheng Xu, Yue Wang
  • Interactions among multiple intra coding methods
    Patent number: 11876971
    Abstract: A video processing method includes determining, for a conversion between a block of a video and a bitstream representation of the video, a manner in which information for a Matrix-based Intra Prediction (MIP) coding technique is coded in the bitstream representation. A prediction block of the block is determined using the MIP coding technique based on performing a matrix vector multiplication operation on previously coded samples of the video. The method also includes performing the conversion based on the determining.
    Type: Grant
    Filed: August 25, 2022
    Date of Patent: January 16, 2024
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD., BYTEDANCE INC.
    Inventors: Li Zhang, Kai Zhang, Hongbin Liu, Yue Wang
  • Update of look up table: FIFO, constrained FIFO
    Patent number: 11877002
    Abstract: A method of video processing is provided to include maintaining one or more tables, wherein each table includes one or more motion candidates and each motion candidate is associated with corresponding motion information; performing a conversion between a current block and a bitstream representation of a video including the current block by using motion information in a table; and updating, after performing of the conversion, one or more tables based on M sets of additional motion information associated with the current block, M being an integer.
    Type: Grant
    Filed: December 6, 2021
    Date of Patent: January 16, 2024
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD, BYTEDANCE INC.
    Inventors: Li Zhang, Kai Zhang, Hongbin Liu, Yue Wang
  • Signaling of combined intra-inter prediction
    Patent number: 11876993
    Abstract: The present application relates to signaling of combined intra-inter prediction. A method for processing video includes: coding, during a conversion between a current video block in a video data and a bitstream representation of the current video block, a combined inter-intra prediction (CIIP) flag for the current video block by a context model based coding without referring to a CIIP flag of one or more neighboring video blocks to the current video block, and performing, at least by applying the combined inter-intra prediction (CIIP) flag of the current video block, the conversion.
    Type: Grant
    Filed: June 23, 2021
    Date of Patent: January 16, 2024
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD, BYTEDANCE INC.
    Inventors: Hongbin Liu, Li Zhang, Kai Zhang, Jizheng Xu, Yue Wang, Na Zhang
  • Affine prediction in video coding
    Patent number: 11877001
    Abstract: A device for video decoding can be configured to obtain, from a syntax structure in a bitstream comprising an encoded representation of the video data, a syntax element indicating whether 6-parameter affine prediction is enabled for blocks corresponding to the syntax structure, wherein the blocks corresponding to the syntax structure comprise a first block; based on the syntax element indicating that the 6-parameter affine prediction is enabled for the blocks corresponding to the syntax structure, use the 6-parameter affine prediction to generate a predictive block for the first block; and use the predictive block and residual data to reconstruct the first block.
    Type: Grant
    Filed: October 9, 2018
    Date of Patent: January 16, 2024
    Assignee: QUALCOMM Incorporated
    Inventors: Kai Zhang, Jianle Chen, Xin Zhao, Marta Karczewicz
  • SYNTAX REUSE FOR AFFINE MODE WITH ADAPTIVE MOTION VECTOR RESOLUTION
    Publication number: 20240015320
    Abstract: A method for video processing is disclosed to include: determining, for a conversion between a coded representation of a current block of a video and the current block, a motion vector difference (MVD) precision to be used for the conversion from a set of allowed multiple MVD precisions applicable to a video region containing the current video block; and performing the conversion based on the MVD precision.
    Type: Application
    Filed: July 11, 2023
    Publication date: January 11, 2024
    Inventors: Hongbin Liu, Li Zhang, Kai Zhang, Yue Wang
  • SINGLE-LINE CROSS COMPONENT LINEAR MODEL PREDICTION MODE
    Publication number: 20240015298
    Abstract: Devices, systems, and methods for digital video coding that include cross-component prediction are described. In a representative aspect, a method for video coding includes receiving a bitstream representation of a current block of video data comprising a luma component and a chroma component, determining parameters of a linear model based on a first set of samples that are generated by down-sampling a second set of samples of the luma component, and processing, based on the parameters of the linear model, the bitstream representation to generate the current block.
    Type: Application
    Filed: September 26, 2023
    Publication date: January 11, 2024
    Inventors: Kai Zhang, Li Zhang, Hongbin Liu, Yue Wang
  • SELECTIVE USE OF ADAPTIVE IN-LOOP COLOR-SPACE TRANSFORM AND OTHER VIDEO CODING TOOLS
    Publication number: 20240015328
    Abstract: A method of video processing is provided. The method includes: determining, for a conversion between a current video unit of a video and a coded representation of the video, that applicability of a first coding tool and a second coding tool is mutually exclusive; and performing the conversion based on the determining, wherein the first coding tool corresponds to an adaptive color space transformation (ACT) tool; wherein use of the ACT tool comprises: converting, during encoding, a representation of a visual signal from a first color domain to a second color domain, or converting, during decoding, a representation of a visual signal from the second color domain to the first color domain.
    Type: Application
    Filed: September 21, 2023
    Publication date: January 11, 2024
    Inventors: Li Zhang, Jizheng Xu, Kai Zhang, Hongbin Liu, Weijia Zhu, Yue Wang
  • BIDIRECTIONAL SWITCHING DEVICES, ITS TERMINAL STRUCTURES, AND ELECTRONIC DEVICES
    Publication number: 20240014274
    Abstract: A terminal structure of a bidirectional switching device, where the terminal structure can include: a field plate located on a top surface of a well region and between a first voltage-withstand region and a second voltage-withstand region, where the bidirectional switching device comprises the well region, and the first and second voltage-withstand regions located in the well region; and where a potential is connected to the field plate, in order to decrease an electrical leakage of a parasitic transistor, where the parasitic transistor is formed by the first voltage-withstand region, the well region, and the second voltage-withstand region.
    Type: Application
    Filed: June 26, 2023
    Publication date: January 11, 2024
    Inventors: Nan Chen, Yicheng Du, Pengfei Yin, Meng Wang, Kai Zhang, Hao Zhu, Xi Zhou, Yunjiao He
  • Interactive Animation Generation
    Publication number: 20240013461
    Abstract: An interactive animation generation method is provided. The method includes: in response to receiving an instruction for viewing a comment by a first user, obtaining information about a comment section and information about an animation material based on the instruction; in response to receiving an interaction instruction of the first user for a second user in the comment section, obtaining first information of the first user and second information of the second user; and generating an interactive animation in the comment section based on the first information, the second information, and the information about the animation material.
    Type: Application
    Filed: July 7, 2023
    Publication date: January 11, 2024
    Inventors: Zhicong ZANG, Kai ZHANG, Shuqi QUAN, Liangchao LU
  • Method for extracting kansei adjective of product based on principal component analysis and explanation (PCA-E)
    Patent number: 11868432
    Abstract: A method for extracting a kansei adjective of a product based on principal component analysis and explanation (PCA-E) includes constructing a product kansei evaluation vector matrix through original kansei adjectives; performing dimensionality reduction through PCA; and determining, based on principal component load factors, kansei adjectives representing principal components. In this way, the kansei adjectives extracted are explanatory to help users understand the selected kansei adjectives and make accurate evaluation.
    Type: Grant
    Filed: June 2, 2023
    Date of Patent: January 9, 2024
    Assignee: SICHUAN UNIVERSITY
    Inventors: Wu Zhao, Xin Guo, Miao Yu, Kai Zhang, Wei Jiang, Chong Jiang, Bing Lai, Yiwei Jiang, Jun Li, Bo Wu, Xingyu Chen
  • Interplay between subpictures and in-loop filtering
    Patent number: 11870989
    Abstract: An example method of video processing includes determining, for a conversion between a block of a first sub-picture of a video and a bitstream representation of the video, whether to apply a deblocking process across an edge between the block and a neighboring block of a second sub-picture based on whether a loop filtering process is allowed across subpicture boundaries. The method also includes performing the conversion based on the determining.
    Type: Grant
    Filed: April 18, 2022
    Date of Patent: January 9, 2024
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD, BYTEDANCE INC.
    Inventors: Kai Zhang, Zhipin Deng, Hongbin Liu, Li Zhang, Jizheng Xu
  • Prediction precision improvements in video coding
    Patent number: 11871006
    Abstract: Devices, systems and methods for digital video coding, which includes inter prediction with refinement, are described. An exemplary method of video processing includes determining to use, for a conversion between a current block of a video and a bitstream representation of the video, a first linear optimization model for the conversion using a first coding mode, the first linear optimization model being derived from a second linear optimization model that is used for the conversion using a second coding mode, and performing, based on the determining, the conversion. Another exemplary method of video processing includes determining to use, for a conversion between a current block of a video and a bitstream representation of the video, a gradient value computation algorithm for a bi-directional optical flow tool, and performing, based on the determining, the conversion.
    Type: Grant
    Filed: October 19, 2021
    Date of Patent: January 9, 2024
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD, BYTEDANCE INC.
    Inventors: Kai Zhang, Li Zhang, Hongbin Liu, Yue Wang
  • Selection of adjacent neighboring block for intra coding
    Patent number: 11870980
    Abstract: Devices, systems and methods for digital video processing, which includes selection of adjacent neighboring block for intra coding, are described. In a representative aspect, a method for video processing includes selecting, for a conversion between a current block of visual media data and a bitstream representation of the current block, an intra prediction mode based on at least one of spatial neighboring blocks to the current block, and performing the conversion based on the intra prediction mode. The at least one of the spatial neighboring blocks is different from a first block that is located to a left of a first row of the current block and a second block that is located above a first column of the current block.
    Type: Grant
    Filed: March 18, 2021
    Date of Patent: January 9, 2024
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD, BYTEDANCE INC.
    Inventors: Li Zhang, Kai Zhang, Hongbin Liu, Yue Wang
  • Blending method for inter prediction with geometry partition
    Patent number: 11870987
    Abstract: Devices, systems and methods for digital video coding, which includes using default motion candidates for video coding, are described. An exemplary method for video processing includes determining, for a conversion between a block of a video and a bitstream representation of the video, weights to use for a weighted average of prediction samples along an edge of two partitions of the block. The two partitions are generated according to a geometry partition mode, and the weights are selected from a first weighting factor group that at least one of the weights is equal to 0 or 1. The method also includes performing the conversion based on the determining.
    Type: Grant
    Filed: May 11, 2021
    Date of Patent: January 9, 2024
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD, BYTEDANCE INC.
    Inventors: Li Zhang, Kai Zhang, Hongbin Liu, Jizheng Xu, Yue Wang
  • Concept of interweaved prediction
    Patent number: 11871022
    Abstract: Methods, systems, and devices related to sub-block based motion prediction in video coding are described. In one representative aspect, a video processing method includes partitioning a video block into a first set of sub-blocks according to a first pattern, partitioning the video block into a second set of sub-blocks according to a second pattern, wherein at least one sub-block in the second set has a different size than a sub-block in the first set, and determining a prediction block corresponding to a combination of a first intermediate prediction block that is predictively generated from the first set of sub-blocks and a second intermediate prediction block that is predictively generated from the second set of sub-blocks.
    Type: Grant
    Filed: November 18, 2020
    Date of Patent: January 9, 2024
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD, BYTEDANCE INC.
    Inventors: Kai Zhang, Li Zhang, Hongbin Liu, Yue Wang
  • Multiple-hypothesis affine mode
    Patent number: 11870974
    Abstract: A method, a video processing apparatus and computer-readable program medium for video process is disclosed. The method of video processing includes deriving, during a conversion between a current block of video and a bitstream representation of the current block, a new affine model using multiple original affine models with control point motion vectors; and performing the conversion by using the new affine model.
    Type: Grant
    Filed: March 5, 2021
    Date of Patent: January 9, 2024
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD, BYTEDANCE INC.
    Inventors: Kai Zhang, Li Zhang, Hongbin Liu, Yue Wang
  • Reference picture resampling activation in video coding
    Patent number: 11870979
    Abstract: Methods, apparatus, systems for video processing, including video encoding or video decoding are described. One example method includes performing a conversion between a video comprising a video picture that includes a video slice and a bitstream of the video. The bitstream conforms to a format rule specifying that, in case a slice type of the video slice is type P and temporal motion vector prediction is enabled, usage of reference picture resampling (RPR) for a reference picture in a collocated reference picture list is disabled. The reference picture is indicated by a reference index of a collocated picture of the video slice used for the temporal motion vector prediction.
    Type: Grant
    Filed: August 11, 2022
    Date of Patent: January 9, 2024
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD., BYTEDANCE INC.
    Inventors: Zhipin Deng, Li Zhang, Kai Zhang, Ye-kui Wang, Kui Fan