Patents Assigned to Tencent America LLC
  • Patent number: 11935271
    Abstract: A method, computer program, or computer system is provided for compressing a neural network model. One or more blocks are identified from among a superblock corresponding to a multi-dimensional tensor associated with a neural network. A set of weight coefficients associated with the superblock is unified. A model of the neural network is compressed based on the unified set of weight coefficients.
    Type: Grant
    Filed: November 2, 2020
    Date of Patent: March 19, 2024
    Assignee: TENCENT AMERICA LLC
    Inventors: Wei Jiang, Wei Wang, Shan Liu
  • Patent number: 11936891
    Abstract: A method and system for decoding a coded video sequence may include obtaining the coded video sequence, and decoding the coded video sequence. A value of a temporal sublayer identifier of a video coding layer (VCL) network abstraction layer (NAL) unit in the coded video sequence is constrained to be less than or equal to a value of vps_max_sublayers_minus1, that specifies a maximum number of temporal sublayers that may be present in a layer in each coded video sequence referring to the video parameter set (VPS), in the VPS referred to by the VCL NAL unit.
    Type: Grant
    Filed: January 24, 2022
    Date of Patent: March 19, 2024
    Assignee: TENCENT AMERICA LLC
    Inventors: Byeongdoo Choi, Shan Liu, Stephan Wenger
  • Publication number: 20240089481
    Abstract: A method and device identify a maximum number of temporal sublayers that is allowed in a coded video sequence referring to a parameter set. A coded video sequence is decoded based on the identified maximum number of temporal sublayers that is allowed in the coded video sequence referring to the parameter set.
    Type: Application
    Filed: November 17, 2023
    Publication date: March 14, 2024
    Applicant: TENCENT AMERICA LLC
    Inventors: Byeongdoo CHOI, Shan LIU, Stephan WENGER
  • Publication number: 20240087173
    Abstract: A method of encoding includes receiving a polygon mesh comprising a plurality of original vertices. The method further includes deriving an initial base mesh from the polygon mesh, the initial base mesh including a first set of base mesh vertices. The method further includes performing a symmetrize process on the initial base mesh to generate a symmetrical base mesh that includes a first side having the first set of base mesh vertices and a second side having a second set of base mesh vertices, each base mesh vertex in the first set of base mesh vertices having a corresponding symmetric vertex in the second set of base mesh vertices. The method further includes determining a first displacement between each original vertex in the polygon mesh located on the second side of the symmetrical base mesh and a nearest vertex included in the second set of base mesh vertices.
    Type: Application
    Filed: May 4, 2023
    Publication date: March 14, 2024
    Applicant: TENCENT AMERICA LLC
    Inventors: Thuong NGUYEN CANH, Xiaozhong Xu, Xiang Zhang, Shan Liu
  • Publication number: 20240089461
    Abstract: A method of video coding, executable by a processor, includes receiving video data having a coding tree unit size, determining whether the coding tree unit size is greater than a predetermined threshold, and in response to the coding tree unit size being greater than the predetermined threshold, signaling, in a sequence parameter set (SPS), a first flag indicating whether a maximum transform size in luma samples is equal to 64. The first flag being equal to 1 specifies that the maximum transform size in luma samples is equal to 64, the first flag equal to 0 specifies that the maximum transform size in luma samples is equal to 32, and when not present, the first flag is inferred to be equal to 0.
    Type: Application
    Filed: November 16, 2023
    Publication date: March 14, 2024
    Applicant: TENCENT AMERICA LLC
    Inventors: Yixin DU, Byeongdoo CHOI, Xiang LI, Xin ZHAO, Stephen WENGER, Shan LIU
  • Publication number: 20240089499
    Abstract: A method and apparatus comprising computer code configured to cause a processor or processors to obtain volumetric data of at least one three-dimensional (3D) visual content, derive a mesh from a frame of the volumetric data, the mesh including a plurality of base mesh vertices, determine a displacement of at least one vertex, that is not of the base mesh vertices, based on a series of projections from at least one of the plurality of base mesh vertices that is a neighboring one of the plurality of base mesh vertices to the at least one vertex, predicting the at least one vertex based at least on the determined displacement, and encode the volumetric data based on the predicted at least one vertex.
    Type: Application
    Filed: May 10, 2023
    Publication date: March 14, 2024
    Applicant: TENCENT AMERICA LLC
    Inventors: Thuong NGUYEN CANH, Xiaozhong XU, Chao HUANG, Xiang ZHANG, Shan LIU
  • Publication number: 20240086320
    Abstract: A method for modifying engine files, the method performed by at least one processor in one or more servers at a cloud based location, the method comprising receiving, by the one or more servers at the cloud based location from at least one host device, a derived data cache (DDC) generated by the at least one host device; distributing the DDC from the one or more servers at the cloud based location to one or more client locations, the one or more client locations performing at least one modification to the DDC; and receiving the modified DDC, by the one or more servers at the cloud based location from the one or more client locations.
    Type: Application
    Filed: September 8, 2022
    Publication date: March 14, 2024
    Applicant: TENCENT AMERICA LLC
    Inventors: Haitao WU, Xin Wang, Zhong WANG, Kexue WEI
  • Publication number: 20240089472
    Abstract: A method of decoding an encoded video bitstream using at least one processor, including obtaining a first flag indicating whether a constant picture size is used in a coded video sequence including a current picture; based on the first flag indicating that the constant picture size is used, decoding the current picture without performing reference picture resampling; based on the first flag indicating that the constant picture size is not used, obtaining a second flag indicating whether a conformance window size is signaled; based on the second flag indicating that the conformance window size is signaled: obtaining the conformance window size, determining a resampling ratio between the current picture and a reference picture based on the conformance window size, and performing the reference picture resampling on the current picture using the resampling ratio.
    Type: Application
    Filed: November 20, 2023
    Publication date: March 14, 2024
    Applicant: TENCENT AMERICA LLC
    Inventors: Byeongdoo CHOI, Stephan WENGER, Shan LIU
  • Publication number: 20240089426
    Abstract: A method of and device for controlling multi-line intra prediction using a non-zero reference line. The method includes determining whether an intra prediction mode of a first neighboring block of a current block is an angular mode, determining whether an intra prediction mode of a second neighboring block of the current block is an angular mode, and generating a Most Probable Mode (MPM) list of the current block.
    Type: Application
    Filed: November 17, 2023
    Publication date: March 14, 2024
    Applicant: TENCENT AMERICA LLC
    Inventors: Liang ZHAO, Xin ZHAO, Xiang LI, Shan LIU
  • Publication number: 20240086637
    Abstract: Methods and devices to efficiently normalize text by processing inputted text based on a text normalization model that includes processing the input text in a first stage including a statistical model as a first output, processing the first output in a second stage including a rule based model as a normalized text, and outputting the normalized text.
    Type: Application
    Filed: September 8, 2022
    Publication date: March 14, 2024
    Applicant: Tencent America LLC
    Inventors: Jia Cui, Dong Yu
  • Publication number: 20240089502
    Abstract: A method of decoding may be performed by at least one processor, and may comprise: receiving an entropy coded bitstream comprising compressed video data; generating one or more dequantized blocks, determining whether at least one of a height and a width of the one or more dequantized blocks is greater than or equal to a predefined threshold, and responsive to the at least one of the height or the width of the one or more dequantized blocks being greater than or equal to the predefined threshold, transform coding a dequantized block using a tuned line graph transform (LGT) core to perform direct matrix multiplications for each of the horizontal and vertical dimensions of the one or more dequantized blocks.
    Type: Application
    Filed: November 10, 2023
    Publication date: March 14, 2024
    Applicant: TENCENT AMERICA LLC
    Inventors: Madhu Peringassery KRISHNA, Xin ZHAO, Shan LIU
  • Patent number: 11930217
    Abstract: A method, computer program, and computer system is provided for video coding. The method may include decoding coded syntax elements corresponding to a wrap-around padding process based on shifting a reference block by a width value that is determined based on luma samples in the reference block; and reconstructing at least one coded current picture using the wrap-around padding process, wherein the wrap-around padding process is applied at boundaries of subpictures.
    Type: Grant
    Filed: May 31, 2022
    Date of Patent: March 12, 2024
    Assignee: TENCENT AMERICA LLC
    Inventors: Byeongdoo Choi, Stephan Wenger, Shan Liu
  • Patent number: 11930254
    Abstract: There is included a method and apparatus comprising computer code configured to cause a processor or processors to perform obtaining media content from a first content server, determining whether a manifest indicates presence of a remote element, resolving the remote element, manipulating an updated remote element, and streaming at least one of the media content from the first content server and another media content from a second content server based on manipulating the updated remote element.
    Type: Grant
    Filed: April 1, 2021
    Date of Patent: March 12, 2024
    Assignee: TENCENT AMERICA LLC
    Inventor: Iraj Sodagar
  • Patent number: 11930177
    Abstract: This disclosure relates generally to video coding and particularly to cross component level reconstruction. For example, a method is disclosed for processing video data which may include extracting a first transform block of a first color component and a second transform block of a second color component from a bitstream of a video block; determining that transform coefficients in the first transform block are all zero; determining that a CCLR is applied to the first transform block; refining one or more of the transform coefficients in the first transform block, to obtain a refined first transform block; determining a target transform kernel for the refined first transform block; performing a reverse transform on the refined first transform block based on the target transform kernel to obtain a target block; and reconstructing the first color component of the video block based on at least the target block.
    Type: Grant
    Filed: October 14, 2022
    Date of Patent: March 12, 2024
    Assignee: Tencent America LLC
    Inventors: Madhu Peringassery Krishnan, Xin Zhao, Shan Liu
  • Patent number: 11930064
    Abstract: Aspects of the disclosure provide methods, apparatuses, and a non-transitory computer-readable storage medium for receiving media data. One apparatus includes processing circuitry that receives a media presentation description (MPD) file. The MPD file includes key-value pair information for a session-based description (SBD) file. The SBD file includes a plurality of session-based parameters. The processing circuitry determines which of the plurality of session-based parameters in the SBD file is to be included in a query based on the key-value pair information in the MPD file. The processing circuitry further generates the query based on the determination of which of the plurality of session-based parameters in the SBD file is to be included in the query.
    Type: Grant
    Filed: September 23, 2022
    Date of Patent: March 12, 2024
    Assignee: TENCENT AMERICA LLC
    Inventor: Iraj Sodagar
  • Patent number: 11930167
    Abstract: A method for video decoding is provided. The method includes determining an intra prediction angle that corresponds to an intra prediction mode of a plurality of intra prediction modes, a subset of the plurality of intra prediction modes being mapped to a plurality of wide-angle intra prediction modes based on a ratio of a width of a block and a height of the block not being equal to 1, a number of the subset of the intra prediction modes mapped to the plurality wide-angle intra prediction modes being based on the ratio of the width of the block and the height of the block. At least one sample of the block is reconstructed based on the intra prediction angle that is determined to correspond to the intra prediction mode.
    Type: Grant
    Filed: September 8, 2022
    Date of Patent: March 12, 2024
    Assignee: TENCENT AMERICA LLC
    Inventors: Xin Zhao, Liang Zhao, Shan Liu, Xiang Li
  • Patent number: 11930164
    Abstract: A method for video encoding includes determining whether coding of a current block in an IBC prediction mode is performed in an explicit mode or an implicit mode based on whether a difference exists between a block vector and a corresponding block vector predictor. The current block is part of a current picture to be coded. The method further includes constructing a block vector predictor candidate list for the current block, the block vector predictor candidate list having a first number of block vector predictor candidates in the implicit mode, and having a second number of block vector predictor candidates in the explicit mode. The method further includes selecting a block vector predictor candidate from the constructed block vector predictor candidate list and encoding the current block according to the selected block vector predictor candidate.
    Type: Grant
    Filed: September 13, 2022
    Date of Patent: March 12, 2024
    Assignee: TENCENT AMERICA LLC
    Inventors: Xiaozhong Xu, Shan Liu, Xiang Li
  • Patent number: 11930214
    Abstract: A method of utilizing an 8-bit primary transform core matrix to decode compressed video or image data or encode uncompressed video or image data. The method may include determining whether to use a first transform core matrix that is of a first size type or a second transform core matrix that is of a second size type that is smaller than the first size type. When a result of the determination is to use the first transform core matrix, encoding or decoding the target file using the 8-bit primary transform core matrix that has the size that is 64-point or larger. If not, the method may include extracting the second transform core matrix of the second size type from the first transform matrix and encoding or decoding the target file using the extracted second transform core matrix.
    Type: Grant
    Filed: September 9, 2022
    Date of Patent: March 12, 2024
    Assignee: TENCENT AMERICA LLC
    Inventors: Xin Zhao, Xiang Li, Shan Liu
  • Patent number: 11930059
    Abstract: Packaging media for optimizing immersive media distribution of a media steam performed by at least one processor, is provided, including: receiving immersive media data for an immersive presentation; acquiring asset information associated with media assets corresponding to a set of scenes included in the immersive media data for the immersive presentation; analyzing characteristics of the media assets based on the asset information, the characteristics comprising an asset type associated with a respective media asset and a frequency that indicates a number of times the respective media asset is used among the set of scenes included in the immersive presentation; ordering the media assets in a sequence based on the asset type and the frequency associated with each of the media assets; and streaming the immersive media data for the immersive presentation based on the ordered sequence of the media assets.
    Type: Grant
    Filed: October 21, 2022
    Date of Patent: March 12, 2024
    Assignee: TENCENT AMERICA LLC
    Inventors: Arianne Hinds, Rohit Abhishek, Stephan Wenger
  • Patent number: 11930499
    Abstract: A method of a service enabler architecture layer (SEAL) can include receiving a monitoring event subscription request for network connection status information at a network resource management server in the SEAL from a vertical application layer (VAL) server. The monitoring event subscription request can indicate a target VAL user equipment (UE), a type of the network connection status information, and a timeout period indicating an amount of time lapsed after the monitoring event subscription request was transmitted. The requested network connection status information is not transmitted after the timeout period. The network connection status information of the target VAL UE can be obtained from a wireless network system. A network connection status information response message can be transmitted from the network resource management server in the SEAL to the VAL server. The network connection status information response message can include the network connection status information of the target VAL UE.
    Type: Grant
    Filed: October 12, 2021
    Date of Patent: March 12, 2024
    Assignee: TENCENT AMERICA LLC
    Inventors: Shuai Zhao, Stephan Wenger, Shan Liu