Patents Assigned to Tencent America LLC
  • Publication number: 20210067805
    Abstract: There is included a method and apparatus comprising computer code configured to cause a processor or processors to perform obtaining a leaf node of geometry based point cloud compression (G-PCC) data, splitting the leaf node into a plurality of cuboids, deriving separate triangle soups for each of the cuboids, and coding a plurality of flags respectively for each of the edges of each of the cuboids, where the plurality of flags indicate whether vertices of the separate triangle soups are present on ones of the edges.
    Type: Application
    Filed: August 27, 2020
    Publication date: March 4, 2021
    Applicant: TENCENT AMERICA LLC
    Inventors: Arash VOSOUGHI, Sehoon Yea, Stephan Wenger, Shan Liu
  • Publication number: 20210067809
    Abstract: There is included a method and apparatus comprising computer code configured to cause a processor or processors to perform obtaining a coding tree unit (CTU) from video data, partitioning the CTU by a quadtree structure, partitioning leaf nodes of the partitioned CTU by at least one of a binary tree structure and a ternary tree structure, and signaling a difference, in base 2 logarithm, between at least one value and a size of a sample resulting from at least one of partitioning the CTU by the quadtree structure and partitioning leaf nodes of the partitioned CTU by the at least one of the binary tree structure and the ternary tree structure.
    Type: Application
    Filed: August 21, 2020
    Publication date: March 4, 2021
    Applicant: TENCENT AMERICA LLC
    Inventors: Yixin DU, Xiang Li, Xin ZHAO, Shan LIU, Byeongdoo CHOI, Stephan WENGER
  • Publication number: 20210067806
    Abstract: Aspects of the disclosure provide methods, apparatuses, and non-transitory computer-readable storage mediums for video encoding/decoding. In a method, prediction information of a current block of a coding unit tree in a coded bit stream is decoded. The prediction information indicates at least one allowed block partitioning structure for the current block. A sub-block transform (SBT) mode is determined for the current block based on the prediction information indicating that SBT is used for the current block. A partition of the current block based on the SBT mode is different from a partition of the current block based on the at least one allowed block partitioning structure. The current block is reconstructed based on the SBT mode.
    Type: Application
    Filed: August 21, 2020
    Publication date: March 4, 2021
    Applicant: TENCENT AMERICA LLC
    Inventors: Xiang LI, Xin Zhao, Liang Zhao, Shan Liu
  • Publication number: 20210059595
    Abstract: A method and user device for determining a unified Parkinson's disease rating scale (UPDRS) value associated with a user of the user device include obtaining video data associated with a movement of a body part of the user. The UPDRS value is determined using a model and the video data associated with the movement of the body part of the user. The UPDRS value is provided to permit an evaluation of the user based on the UPDRS value.
    Type: Application
    Filed: August 28, 2019
    Publication date: March 4, 2021
    Applicant: TENCENT AMERICA LLC
    Inventors: Lianyi HAN, Hui TANG, Yusheng XIE, Shih-Yao LIN, Qian ZHEN, Zhimin HUO, Wei FAN
  • Publication number: 20210067790
    Abstract: An apparatus for video decoding includes processing circuitry. The processing circuitry can be configured to receive data of a current block coded with an intra block copy (IBC) mode in a bitstream. A block vector of the current block can be determined based on a history-based block vector prediction (HBVP) table that includes one or more entries each corresponding to a previously decoded block. Each entry can include a block vector of the corresponding previously decoded block and a location of the corresponding previously decoded block. The current block can be reconstructed based on the determined block vector of the current block.
    Type: Application
    Filed: June 25, 2020
    Publication date: March 4, 2021
    Applicant: Tencent America LLC
    Inventors: Xiaozhong XU, Shan Liu
  • Publication number: 20210067800
    Abstract: A method, computer program, and computer system is provided for video coding. Video data comprising one or more blocks is received. One or more samples are identified from one or more references images corresponding to the received video data. One or more motion vectors associated with the video data are refined based on interpolating the one or more samples by applying a decoder-side motion vector refinement (DMVR) motion vector offset value to a motion vector associated with a current block from among the one or more blocks.
    Type: Application
    Filed: August 27, 2020
    Publication date: March 4, 2021
    Applicant: TENCENT AMERICA LLC
    Inventors: Guichun LI, Xiang Li, Xiaozhong Xu, Shan Liu
  • Publication number: 20210067792
    Abstract: A method of video decoding at a video decoder can include partitioning a coding tree block (CTB) into coding blocks, determining whether an intra sub-partition (ISP) mode is allowable for a current block based on a first block size of the current block that is one of the coding blocks, and decoding the current block according to the ISP mode when the ISP mode is allowed for the current block.
    Type: Application
    Filed: August 21, 2020
    Publication date: March 4, 2021
    Applicant: TENCENT AMERICA LLC
    Inventors: Liang ZHAO, Xin Zhao, Xiang Li, Shan Liu
  • Publication number: 20210067789
    Abstract: A method, computer program, and computer system is provided for coding a video sequence. Video data comprising one or more luma samples is received. A YUV format associated with the received video data is determined. A height setting value and a width setting value corresponding to the one or more luma samples are restricted based on the determined YUV format. The YUV format may include a YUV4:4:4 format, a YUV4:2:2 format, a YUV4:2:0 format, and a YUV4:0:0 format.
    Type: Application
    Filed: August 21, 2020
    Publication date: March 4, 2021
    Applicant: TENCENT AMERICA LLC
    Inventors: Liang ZHAO, Xin ZHAO, Xiang LI, Byeongdoo CHOI, Shan LIU
  • Publication number: 20210065876
    Abstract: A method of performing electrocardiography (ECG) analysis by at least one processor, the method including receiving ECG data that is from multiple leads; grouping the ECG data into groups of data; generating, from each group of the groups of data, a feature vector using a respective machine learning model; and performing ECG analysis using the feature vectors generated from each of the groups of data.
    Type: Application
    Filed: August 30, 2019
    Publication date: March 4, 2021
    Applicant: TENCENT AMERICA LLC
    Inventors: Kun WANG, Tao YANG, Min TU, Yaliang LI, Hui TANG, Wei FAN
  • Publication number: 20210067797
    Abstract: A method, computer program, and computer system for video coding is provided. Video data including at least two frames is received. A motion vector difference is calculated between two frames from among the at least two frames. An adaptive motion vector resolution usage flag is checked. The adaptive motion vector resolution flag may correspond to a precision value and an adaptive motion vector resolution usage value corresponding to whether adaptive motion vector resolution is enabled or disabled. The video data is encoded based on the adaptive motion vector resolution usage value, whereby the motion vector difference is encoded based on the precision value.
    Type: Application
    Filed: August 21, 2020
    Publication date: March 4, 2021
    Applicant: TENCENT AMERICA LLC
    Inventors: Guichun Li, Xiang Li, Xiaozhong Xu, Shan Liu
  • Publication number: 20210064957
    Abstract: Provided are a method and an apparatus for receiving a query including a sequence of words. The sequence of words is converted into a sequence of feature vectors. A semantic meaning of the sequence of words is generated using a bi-directional long-short term memory (LSTM). The LSTM is regularized using a Gaussian mixed model (GMM) based on the generated semantic meaning of the sequence of feature vectors.
    Type: Application
    Filed: September 4, 2019
    Publication date: March 4, 2021
    Applicant: TENCENT AMERICA LLC
    Inventors: Zeyu YOU, Tao YANG, Yusheng XIE, Shangqing ZHANG, Min TU, Wei FAN
  • Patent number: 10939101
    Abstract: Aspects of the disclosure provide method and apparatus for video coding. In some examples, an apparatus includes receiving circuitry and processing circuitry. The processing circuitry decodes prediction information of a block from a coded video bitstream. The prediction information is indicative of a reference line selected from a plurality of potential reference lines and an intra prediction mode selected from a set of potential intra prediction modes that is associated with the reference line. Then the processing circuitry reconstructs at least one sample of the block according to the intra prediction mode and at least one reference sample in the reference line.
    Type: Grant
    Filed: August 7, 2019
    Date of Patent: March 2, 2021
    Assignee: Tencent America LLC
    Inventors: Xin Zhao, Xiang Li, Shan Liu, Liang Zhao
  • Publication number: 20210058621
    Abstract: Aspects of the disclosure provide method and apparatus for video coding. In some examples, an apparatus includes receiving circuitry and processing circuitry. The processing circuitry decodes, from a coded video bitstream, a syntax element for an adjusted version of an initial quantization parameter (QP) value at a picture level for a picture. The adjusted version is in a range with an upper boundary that is changed with a maximum QP value. Then, the processing circuitry determines the initial QP value of a segment (such as a slice, a tile, a group of tiles and the like) in the picture based on the syntax element and determines a QP value for a block in the segment according to the initial QP value of the segment and adjustments associated with the block. Then, the processing circuitry performs an inverse quantization on quantized data of the block according to the determined QP value.
    Type: Application
    Filed: November 9, 2020
    Publication date: February 25, 2021
    Applicant: TENCENT AMERICA LLC
    Inventors: Xiang LI, Xiaozhong XU, Shan LIU
  • Publication number: 20210058634
    Abstract: Aspects of the disclosure provide a method and an apparatus for video coding. The apparatus includes processing circuitry. The processing circuitry is configured to decode prediction information of a current block in a current picture from a coded video bitstream. The prediction information can indicate a subblock-based merge mode for a plurality of subblocks in the current block. The processing circuitry is configured to determine whether to apply decoder-side motion vector refinement (DMVR) to one of the plurality of subblocks based on at least a mode type of the subblock-based merge mode. In response to the DMVR being determined to be applied to the one of the plurality of subblocks, the processing circuitry is configured to reconstruct the one of the plurality of subblocks according to the subblock-based merge mode with the DMVR. In an example, the mode type of the subblock-based merge mode is not an affine merge mode.
    Type: Application
    Filed: August 13, 2020
    Publication date: February 25, 2021
    Applicant: Tencent America LLC
    Inventors: Guichun LI, Xiang LI, Xiaozhong XU, Shan LIU
  • Publication number: 20210056759
    Abstract: A method of displaying an augmented reality (AR) image includes controlling an AR display to display the AR image as being at least partially overlaid over a view through a microscope while the view is visible to a user of the microscope, wherein the AR image includes a cursor; receiving a user input from a user interface; setting an anchor point based on the user input; updating the AR image to include the anchor point; controlling the AR display to display the updated AR image; detecting a motion of a slide of the microscope; adjusting the AR image by moving at least one from among the cursor and the anchor point within the AR image based on the detected motion; and controlling the AR display to display the adjusted AR image.
    Type: Application
    Filed: August 23, 2019
    Publication date: February 25, 2021
    Applicant: TENCENT AMERICA LLC
    Inventor: Hanbo CHEN
  • Publication number: 20210058615
    Abstract: Aspects of the disclosure provide methods and apparatuses for video encoding/decoding. In some examples, an apparatus for video decoding includes receiving circuitry and processing circuitry. The processing circuitry receives first data of picture segments of a first picture in a video sequence. The picture segments of the first picture include a first segment of the first picture that is intra coded, and at least a second segment of the first picture. The second segment can be intra coded or inter coded. Further, the processing circuitry receives second data of the first segment of the first picture that is intra coded. The second data corresponds to a re-transmission of a subset of the picture segments. The processing circuitry reconstructs samples of the first segment of the first picture based on the second data when a decoding of the first segment of the first picture based on the first data fails.
    Type: Application
    Filed: August 21, 2019
    Publication date: February 25, 2021
    Applicant: Tencent America LLC
    Inventors: Shan LIU, Xiaozhong XU
  • Publication number: 20210056949
    Abstract: A method and apparatus include receiving a text input that includes a sequence of text components. Respective temporal durations of the text components are determined using a duration model. A spectrogram frame is generated based on the duration model. An audio waveform is generated based on the spectrogram frame. Video information is generated based on the audio waveform. The audio waveform is provided as an output along with a corresponding video.
    Type: Application
    Filed: August 23, 2019
    Publication date: February 25, 2021
    Applicant: TENCENT AMERICA LLC
    Inventors: Heng LU, Chengzhu YU, Dong YU
  • Publication number: 20210058638
    Abstract: A method and apparatus for encoding of a video sequence in an encoder or decoding of the video sequence in a decoder includes parsing an initial motion vector from the video sequence associated with a block. A plurality of samples are determined and pre-fetched to permit both motion vector refinement and motion compensation based on parsing the initial motion vector. Motion vector refinement is performed to determine a final motion vector using a first subset of the plurality of samples, and motion compensation is performed using a second subset of the plurality of samples.
    Type: Application
    Filed: November 6, 2020
    Publication date: February 25, 2021
    Applicant: TENCENT AMERICA LLC
    Inventors: Xiang LI, Stephan WENGER, Shan LIU
  • Publication number: 20210058643
    Abstract: A method of video decoding can include determining a prediction mode of a current coding unit (CU), and determining values of a transform unit (TU) coded block flag (CBF) of a Cb transform block, denoted tu_cbf_cb, and a TU CBF of a Cr transform block, denoted tu_cbf_cr, determining a context index, denoted ctxIdx, based on the prediction mode of the current CU and the values of the tu_cbf_cb, and the tu_cbf_cr, and performing an arithmetic decoding process according to a context model indicated by the ctxIdx to determine a bin of a joint Cb Cr residual (JCCR) flag indicating whether residual samples for both Cb and Cr chroma components of the current CU are coded as a single transform block.
    Type: Application
    Filed: August 20, 2020
    Publication date: February 25, 2021
    Applicant: TENCENT AMERICA LLC
    Inventors: Liang ZHAO, Xiang LI, Xin ZHAO, Shan LIU
  • Patent number: 10931963
    Abstract: Aspects of the disclosure provide methods and a decoder device for video decoding. In some embodiments, the decoder device for video decoding includes processing circuitry. The processing circuitry selects a motion vector of a neighboring sub-block that is a neighbor of a current block under reconstruction. The current block is in a coded picture that is a part of a coded video bitstream. The processing circuitry determines, from the motion vector, motion vector predictors for a plurality of sub-blocks included in the current block. The neighboring sub-block and the plurality of sub-blocks are in a first one of a single row and a single column of the coded picture.
    Type: Grant
    Filed: September 28, 2018
    Date of Patent: February 23, 2021
    Assignee: Tencent America LLC
    Inventors: Xiaozhong Xu, Shan Liu, Stephan Wenger