-
公开(公告)号：US20230403407A1
公开(公告)日：2023-12-14
申请号：US18451951
申请日：2023-08-18
Inventor： Zhipin Deng , Kai Zhang , Li Zhang , Na Zhang , Yang Wang
IPC: H04N19/563 , H04N19/117 , H04N19/159 , H04N19/176
CPC classification number: H04N19/563 , H04N19/117 , H04N19/159 , H04N19/176
Abstract: A method for coding video data implemented by a video coding apparatus. The method includes filtering padding samples within an extended area disposed around a video unit, and converting between the video unit of the video and a bitstream in accordance with the one or more padding samples in the extended area as filtered.
-
公开(公告)号：US11812030B2
公开(公告)日：2023-11-07
申请号：US17976189
申请日：2022-10-28
Inventor： Yang Wang , Li Zhang , Zhipin Deng , Kai Zhang , Hongbin Liu
IPC: H04N19/137 , H04N19/119 , H04N19/176 , H04N19/189 , H04N19/70
CPC classification number: H04N19/137 , H04N19/119 , H04N19/176 , H04N19/189 , H04N19/70
Abstract: Systems, methods and apparatus for video processing are described. The video processing may include video encoding, video decoding, or video transcoding. One example method of video processing includes performing a conversion between a block of a video and a bitstream of the video according to a rule. The conversion is based on an adaptive motion vector difference resolution (AMVR) tool, and the rule specifies that selection of a context for a first bin within a bin string of a first syntax element that specifies the resolution of the motion vector difference associated with an AMVR shift is derived based on usage of a coding mode for the block.
-
公开(公告)号：US20230345007A1
公开(公告)日：2023-10-26
申请号：US18343335
申请日：2023-06-28
Inventor： Ye-Kui Wang , Yang Wang , Li Zhang
IPC: H04N19/132 , H04N19/12
CPC classification number: H04N19/132 , H04N19/12
Abstract: A mechanism for processing video data is disclosed. A description of Cross Random Access Point Referencing (CRR) samples is signaled in a visual media data file in International Organization for Standardization (ISO) base media file format (ISOBMFF). A conversion is performed between a visual media data and the visual media data file based on the CRR sample group.
-
公开(公告)号：US20230336753A1
公开(公告)日：2023-10-19
申请号：US18339038
申请日：2023-06-21
Inventor： Ye-Kui Wang , Kai Zhang , Li Zhang , Yang Wang , Jizheng Xu , Zhipin Deng
IPC: H04N19/196 , H04N19/70 , H04N19/184
CPC classification number: H04N19/197 , H04N19/70 , H04N19/184
Abstract: A mechanism for processing video data is disclosed. Video decoder initialization information is signaled between an encoder to a decoder. The video decoder initialization information contains a range of initialization parameters. A conversion is performed between a visual media data and a visual media data file based on the range of initialization parameters.
-
公开(公告)号：US11659180B2
公开(公告)日：2023-05-23
申请号：US17824304
申请日：2022-05-25
Inventor： Zhipin Deng , Li Zhang , Hongbin Liu , Kai Zhang , Jizheng Xu , Yang Wang , Yue Wang
IPC: H04N19/119 , H04N19/132 , H04N19/137 , H04N19/176 , H04N19/70
CPC classification number: H04N19/119 , H04N19/132 , H04N19/137 , H04N19/176 , H04N19/70
Abstract: A method of video processing is provided to comprise: performing a conversion between a current video block of a video and a bitstream representation of the video, wherein, during the conversion, a use of a geometric partitioning mode is allowed for the current video block, and wherein parameters of the geometric partitioning mode are computed using a set of angles including a first number of angles that is less than a first threshold value and/or a set of distances including a second number of distances that is less than a second threshold value.
-
Patent Agency Ranking
公开(公告)号：US20230036581A1
公开(公告)日：2023-02-02
申请号：US17950037
申请日：2022-09-21
Inventor： Yang Wang , Li Zhang , Kai Zhang , Hongbin Liu , Yue Wang
IPC: H04N19/132 , H04N19/105 , H04N19/186 , H04N19/176 , H04N19/46
Abstract: A method of video processing is provided. The method includes: determining, for a conversion between a video block of a video and a bitstream of the video, a selected neighboring sample list according to an order, wherein the order specifies that above neighboring samples are added to the selected neighboring sample list before left neighboring samples, and performing the conversion based on a cross-component linear model, wherein parameters of a cross-component linear model is derived using a derivation method that is based on samples from the selected neighboring sample list.
-
公开(公告)号：US20220394306A1
公开(公告)日：2022-12-08
申请号：US17888238
申请日：2022-08-15
Inventor： Kai Zhang , Li Zhang , Yang Wang , Ye-kui Wang , Zhipin Deng , Jizheng Xu , Hongbin Liu
IPC: H04N19/70 , H04N19/46 , H04N19/186 , H04N19/174
Abstract: A method includes performing a conversion between a video unit of a video and a bitstream of the video, wherein the bitstream conforms to a format rule, and wherein the format rule specifies that a syntax element indicating whether an in-loop filtering operation is performed across slice boundaries is selectively included in the bitstream based on whether or how the video unit is partitioned into slices.
-
公开(公告)号：US20220394282A1
公开(公告)日：2022-12-08
申请号：US17882359
申请日：2022-08-05
Inventor： Jizheng Xu , Li Zhang , Ye-kui Wang , Kai Zhang , Weijia Zhu , Yue Wang , Yang Wang , Hongbin Liu
IPC: H04N19/186 , H04N19/96 , H04N19/132 , H04N19/176 , H04N19/159
Abstract: Video processing methods, systems and appratrus are described. One example method includes performing a conversion between a video block of a video and a bitstream of the video using a palette mode in which samples of the video block are represented using a palette of representive color values. A size of the palette of the video block is determined based on whether a local dual tree is applied for the conversion.
-
公开(公告)号：US20210026860A1
公开(公告)日：2021-01-28
申请号：US16980897
申请日：2018-09-07
IPC: G06F16/2457 , G06F16/248 , G06N5/00 , G06F17/18
Abstract: The embodiment of the present application discloses a method and a device for generating a ranking model. A specific embodiment of the method includes: acquiring a sample set, executing following training steps: for the samples in the sample set, inputting the query information, the first position document and the second position document in the sample into an initial model, respectively obtaining scores of the input documents, and determining a target value of the sample based on the obtained scores, a clicked bias of a first position and an unclicked bias of a second position, updating the initial model based on the target value of each sample; determining whether the initial model is completely trained; and in response to determining that the initial model is completely trained, determining the updated initial model as the ranking model.
-
公开(公告)号：US12262006B2
公开(公告)日：2025-03-25
申请号：US17824386
申请日：2022-05-25
IPC: H04N19/117 , H04N19/119 , H04N19/176 , H04N19/186
Abstract: A method of video processing, including performing a conversion between a video block of a video component of a video and a bitstream of the video, where the video block includes sub-blocks, where a filtering tool is used during the conversion according to a rule, and where the rule specifies that the filtering tool is applied by using a single offset for all samples of each sub-block of the video block.
-
-
-
-
-
-
-
-
-
Search Results
103
records
(took 0.027 seconds)
