DRAP AND EDRAP IN THE ISOBMFF
    1.
    发明申请

    公开(公告)号:US20250168410A1

    公开(公告)日:2025-05-22

    申请号:US19033229

    申请日:2025-01-21

    Applicant: Bytedance Inc.

    Inventor: Ye-Kui Wang

    Abstract: A method of processing media data. The method includes determining, for a dependent random access point (DRAP) sample, a first sequence of samples; and performing a conversion between media data and a media data file based on the determining. The first sequence of samples consists of the following samples in order: 1) a closest preceding stream access point (SAP) sample of type 1, type 2, or type 3; 2) the DRAP sample; and 3) all samples following the DRAP sample in both decoding order and output order in a first track.

    System and method for generating geographic zone information for consumers

    公开(公告)号:US12299725B2

    公开(公告)日:2025-05-13

    申请号:US18339718

    申请日:2023-06-22

    Applicant: Bytedance Inc.

    Inventor: Daniel Langdon

    Abstract: Embodiments provide computer apparatuses, computer systems and computer-executable methods for generating geographic zone information associated with a consumer. A method includes receiving a first geographic location associated with the consumer, and programmatically identifying a first geographic zone associated with the first geographic location. The method also includes programmatically generating a first importance score associated with the first geographic zone and associated with the consumer. The method also includes storing, on a non-transitory computer-readable medium, the first geographic zone and the first importance score associated with the consumer.

    METHOD, APPARATUS, AND MEDIUM FOR POINT CLOUD CODING

    公开(公告)号:US20250142121A1

    公开(公告)日:2025-05-01

    申请号:US19009860

    申请日:2025-01-03

    Abstract: Embodiments of the present disclosure provide a solution for point cloud coding. A method for point cloud coding is proposed. The method comprises: obtaining, for a conversion between a current point cloud (PC) sample of a point cloud sequence and a bitstream of the point cloud sequence, target information regarding whether an attribute inter prediction is enabled for the current PC sample, the target information being determined based on at least one of rate information or distortion information associated with coding at least one target PC sample with the attribute inter prediction, wherein the at least one target PC sample comprises at least one of: the current PC sample, or at least one PC sample of the point cloud sequence coded before the current PC sample; and performing the conversion based on the target information.

    METHOD, APPARATUS, AND MEDIUM FOR VIDEO PROCESSING

    公开(公告)号:US20250142081A1

    公开(公告)日:2025-05-01

    申请号:US19009847

    申请日:2025-01-03

    Applicant: Bytedance Inc.

    Abstract: Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: obtaining, for a conversion between a current video block of a video and a bitstream of the video, values for a set of adjusting parameters associated with values for a set of model parameters of a local illumination compensation (LIC) model for coding the current video block; updating the values for the set of model parameters based on the values for the set of adjusting parameters; and performing the conversion based on the updated values for the set of model parameters.

    MACHINE LEARNING SYSTEMS ARCHITECTURES FOR RANKING

    公开(公告)号:US20250124038A1

    公开(公告)日:2025-04-17

    申请号:US18925438

    申请日:2024-10-24

    Applicant: Bytedance Inc.

    Abstract: Computing systems, computing apparatuses, computing methods, and computer program products are disclosed for machine learning ranking. An example computing method includes receiving a search query and determining a plurality of machine learning model execution engines based on the search query and a plurality of search result types. The example computing method further includes generating a plurality of subsets of search results based on the search query and the plurality of machine learning model execution engines. The example computing method further includes generating a set of search results comprising at least one search result from each of the plurality of subsets of search results.

Patent Agency Ranking