Patents by Inventor Li Zhang

Li 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).

  • Patent number: 12137257
    Abstract: A method for processing a video includes determining a valid splitting type for a current video block; determining whether or how to signal a splitting type to be used for the current video block based on the determination of the valid splitting type; and performing a conversion between the current video block and a bitstream representation of the current video block in accordance with the determining results.
    Type: Grant
    Filed: July 29, 2021
    Date of Patent: November 5, 2024
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD, BYTEDANCE INC.
    Inventors: Kai Zhang, Li Zhang, Hongbin Liu, Jizheng Xu, Yue Wang
  • Publication number: 20240364911
    Abstract: Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: performing a conversion between a current video block of a video and a bitstream of the video based on at least one flag of: a first flag indicating whether a merge mode with motion vector difference (MMVD) is used for the current video block, or a second flag indicating whether an affine MMVD is used for the current video block, wherein the at least one flag is bypass coded or is coded with at least one context determined from a plurality of contexts. Thereby, the proposed method can advantageously improve coding efficiency and coding quality.
    Type: Application
    Filed: July 3, 2024
    Publication date: October 31, 2024
    Inventors: Mehdi SALEHIFAR, Yuwen HE, Kai ZHANG, Na ZHANG, Li ZHANG
  • Publication number: 20240364879
    Abstract: Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: determining, during a conversion between a video unit of a video and a bitstream of the video unit, a chroma interpolation filter for the video unit, wherein the number of taps of the chroma interpolation filter is larger than a predetermined number; obtaining a chroma prediction block by applying the chroma interpolation filter to a chroma component of the video unit; and performing the conversion based on the chroma prediction block.
    Type: Application
    Filed: July 3, 2024
    Publication date: October 31, 2024
    Inventors: Kai ZHANG, Xi Xie, Li Zhang
  • Publication number: 20240364927
    Abstract: Embodiments of the present disclosure provide a solution for point cloud coding. A method for point cloud coding is proposed. The method comprises: determining, during a conversion between a current frame of a point cloud sequence and a bitstream of the point cloud sequence, an occupancy state of a first node of the current frame, a node representing a spatial partition of the current frame, the occupancy state of the first node representing whether the first node is occupied by a point; determining a prediction of an occupancy indication of a second node of the current frame, the occupancy indication indicating an occupancy state of the second node; and performing the conversion based on the prediction of the occupancy indication.
    Type: Application
    Filed: July 3, 2024
    Publication date: October 31, 2024
    Inventors: Wenyi WANG, Yingzhan XU, Kai ZHANG, Li ZHANG
  • Publication number: 20240361257
    Abstract: An inspection system, including: a carrying device; at least one ray source and a detector assembly. When the at least one ray source is located at one of scanning positions relative to the carrying device, the at least one ray source and the detector assembly are lifted or lowered along the rotation axis relative to the carrying device and the at least one ray source emits X-rays. After the at least one ray source and the detector assembly are lifted or lowered a predetermined distance relative to the carrying device, the at least one ray source rotates around the rotation axis relative to the carrying device to another one of scanning positions. The inspection system further reconstructs a three-dimensional scanning image of the object to be inspected based on detection data of the detector assembly.
    Type: Application
    Filed: July 6, 2022
    Publication date: October 31, 2024
    Inventors: Li ZHANG, Zhiqiang CHEN, Qingping HUANG, Hui DING, Yong ZHOU, Xin JIN, Liming Yao
  • Publication number: 20240362460
    Abstract: The technology relates to providing personalized neural network-based models according to user input, which can be generated upon request or otherwise as needed. This may include receiving, by one or more processors of a computing device, input corresponding to a task description. Then the input corresponding to the task description is encoded into a set of text embeddings. Based on this, the system applies mixer prediction to the set of text embeddings to generate a set of mixers and learns a set of basis models according to the set of mixers. The set of basis models are combined to form a single personalized model corresponding to the task description. This personalized model can then be used in video understanding, quality assessment, providing a recommendation, performing a classification, or performing a search.
    Type: Application
    Filed: April 4, 2024
    Publication date: October 31, 2024
    Inventors: Li Zhang, Yandong Li, Yin Cui, Hong-You Chen, Mingda Zhang
  • Publication number: 20240364878
    Abstract: Embodiments of the disclosure provide a solution for video processing. A method for video processing is proposed. The method includes: determining, during a conversion between a video unit of a video and a bitstream of the video unit, information of a previously coded picture associated with the video unit; during a filtering process, filtering at least one sample in a current picture associated with the video unit based on the information; and performing the conversion based on the filtered at least one sample.
    Type: Application
    Filed: June 28, 2024
    Publication date: October 31, 2024
    Inventors: Wenbin YIN, Kai Zhang, Yue Li, Hongbin Liu, Li Zhang
  • Publication number: 20240364865
    Abstract: Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: determining, during a conversion between a video unit of a video and a bitstream of the video unit, a search range of a decoder side motion vector refinement (DMVR) process based on coding information associated with the video unit; determining a set of motion candidates based on an initial motion candidate and the search range; and performing the conversion based on the set of motion candidates.
    Type: Application
    Filed: July 3, 2024
    Publication date: October 31, 2024
    Inventors: Zhipin DENG, Kai Zhang, Li Zhang
  • Publication number: 20240364866
    Abstract: Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: determining, during a conversion be-tween a target video block of a video and a bitstream of the video, at least one group of motion vector prediction (MVP) candidates of the target video block; determining a first MVP candidate list by performing a first pass of reordering process on the at least one group of MVP candidates; determining a second MVP candidate list by performing a second pass of reordering process on the first MVP candidate list; and performing the conversion based on the second MVP candidate list. In this way, a proper MVP candidate list can be determined by using the first and second passes of reordering, and thus the coding effectiveness and coding efficiency can be improved.
    Type: Application
    Filed: July 3, 2024
    Publication date: October 31, 2024
    Inventors: Lei ZHAO, Kai ZHANG, Li ZHANG
  • Publication number: 20240361487
    Abstract: A radiation protection arrangement, including: a housing, the housing including a first port and a second port; and a tray, the tray having an accommodation space. The tray is allowed to pass through a channel within the housing. The tray has a first end wall, a second end wall, and a bottom portion connected between the first end wall and the second end wall. A shape of the first end wall and/or a shape of the second end wall are/is configured to fit with an inner wall of the housing, so as to block a radiation from leaving the channel from the accommodation space through the second port or the first port. Further provided is a security inspection device, including the radiation protection arrangement.
    Type: Application
    Filed: July 22, 2022
    Publication date: October 31, 2024
    Inventors: Li ZHANG, Yunda SUN, Xin JIN, Wuyang LIANG, Ming CHANG, Le SHEN
  • Patent number: 12131543
    Abstract: A semantic-based method and apparatus for retrieving a perspective image, an electronic device and a computer-readable storage medium are provided. An method includes obtaining a perspective image for a space containing an inspected object therein. A semantic division on the perspective image is performed using a first method, to obtain a plurality of semantic region units. A feature extraction network is constructed using a second method. Based on the perspective image and each of the plurality of semantic region units, a feature of each semantic region unit is extracted using the feature extraction network. Based on the feature of each semantic region unit, an image most similar to the semantic region unit is retrieved from an image feature database, to assist in determining an inspected object in the semantic region unit.
    Type: Grant
    Filed: March 15, 2021
    Date of Patent: October 29, 2024
    Assignees: Tsinghua University, Nuctech Company Limited
    Inventors: Li Zhang, Zhiqiang Chen, Yuanjing Li, Yuxiang Xing, Fanhua Meng, Qiang Li, Wei Li, Gang Fu
  • Patent number: 12132899
    Abstract: BV list construction process of IBC blocks under merge estimation region is described. An example method of video processing includes determining, for a conversion between a current video block of a video and a bitstream of the video, one or more block vector (BV) candidates for the current video block based on a merge estimation region (MER) covering the current video block; adding the one or more BV candidates to a BV list associated with the current video block; and performing the conversion based on the BV list.
    Type: Grant
    Filed: August 7, 2022
    Date of Patent: October 29, 2024
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD., BYTEDANCE INC.
    Inventors: Yang Wang, Li Zhang, Hongbin Liu, Kai Zhang, Yue Wang
  • Patent number: 12128370
    Abstract: A raw material mixing apparatus, including mixing drums and a feed pipe, each of the two mixing drums is provided with a feed port and a discharge port, the feed ports of the two mixing drums are both communicated with the feed pipe, and a switching valve is arranged on the feed pipe; a first rotating disc and a second rotating disc are rotatably connected at two ends of each said mixing drum respectively, and a stirring assembly is connected between the first rotating disc and the second rotating disc in the axial direction of each said mixing drum; the stirring assembly includes a central stirring element and a plurality of non-central stirring elements radially arranged between inner side walls of each said mixing drum and outer side walls of the central stirring element.
    Type: Grant
    Filed: August 16, 2021
    Date of Patent: October 29, 2024
    Assignee: CHONGQING DEZHUANG AGRICULTURAL PRODUCTS DEVELOPMENT CO., LTD.
    Inventors: Dejian Li, Shubang Lu, Li Zhang, Decai Zhou, Qinsong Yue, Yangmei Li, Yi Tang
  • Patent number: 12132889
    Abstract: A video coding or decoding method includes using history-based motion vector prediction (HMVP) for conversion between multiple video blocks including a current block of video and a bitstream representation of the multiple video blocks such that for a uni-predicted block that for which a single reference picture is used for motion compensation, refraining from updating a look-up table for HMVP candidates for the uni-predicted block. The video coding or decoding method further includes performing the conversion using look-up tables for the multiple video blocks.
    Type: Grant
    Filed: March 27, 2023
    Date of Patent: October 29, 2024
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD., BYTEDANCE INC.
    Inventors: Li Zhang, Kai Zhang, Hongbin Liu, Yue Wang
  • Patent number: 12132884
    Abstract: Devices, systems and methods for video processing are described. An example method for video processing includes determining, for a conversion between a current block of a video and a bitstream representation of the video, a number of intra-coded neighboring blocks of the current block for a combined inter and intra prediction mode according to a rule that specifies a manner of treating a block coded using a palette coding mode in counting the number of intra-coded neighboring blocks for the combined inter and intra prediction mode. The method also includes performing the conversion based on the determining.
    Type: Grant
    Filed: January 27, 2022
    Date of Patent: October 29, 2024
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD, BYTEDANCE INC.
    Inventors: Weijia Zhu, Li Zhang, Jizheng Xu, Kai Zhang, Hongbin Liu, Yue Wang
  • Patent number: 12132888
    Abstract: A method of visual media processing method includes performing a conversion between a current video block of a current picture of a visual media data and a bitstream representation of the visual media data. The conversion is based on a reference region from the current picture comprising reference samples used for deriving a prediction block of the current video block. A virtual buffer of a defined size is used for tracking availability of the reference samples for deriving the prediction block.
    Type: Grant
    Filed: December 19, 2022
    Date of Patent: October 29, 2024
    Assignees: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD., BYTEDANCE INC.
    Inventors: Jizheng Xu, Li Zhang, Kai Zhang, Hongbin Liu, Yue Wang
  • Publication number: 20240357172
    Abstract: Embodiments of the present disclosure provide a solution for point cloud coding.
    Type: Application
    Filed: July 3, 2024
    Publication date: October 24, 2024
    Inventors: Yingzhan XU, Wenyi Wang, Kai Zhang, Li Zhang
  • Publication number: 20240357102
    Abstract: An example device for filtering a decoded block of video data includes one or more processing units configured to construct a plurality of filters for classes of blocks of a current picture of video data. To construct the plurality of filters for each of the classes, the processing units are configured to determine a value of a flag that indicates whether a fixed filter is used to predict a set of filter coefficients of the class, and in response to the fixed filter being used to predict the set of filter coefficients, determine an index value into a set of fixed filters and predict the set of filter coefficients of the class using a fixed filter of the set of fixed filters identified by the index value.
    Type: Application
    Filed: June 28, 2024
    Publication date: October 24, 2024
    Inventors: Marta Karczewicz, Wei-Jung Chien, Li Zhang
  • Publication number: 20240357157
    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: Application
    Filed: July 3, 2024
    Publication date: October 24, 2024
    Inventors: Hongbin Liu, Li Zhang, Kai Zhang, Jizheng Xu, Yue Wang
  • Publication number: 20240352190
    Abstract: A hydrocarbyl tetralin polyethersulfonate, preparation method therefor and use thereof are provided. The hydrocarbyl tetralin polyethersulfonate is of formula (I-0), The hydrocarbyl tetralin polyethersulfonate has a high surface and interface activity, can be used in an oil reservoir exploitation, especially in a high-temperature and high-salt oil reservoir exploitation, to improve crude oil recovery.
    Type: Application
    Filed: August 19, 2022
    Publication date: October 24, 2024
    Inventors: Xinning BAO, Yingcheng LI, Weidong ZHANG, Jun JIN, Yong MENG, Li ZHANG