-
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.
Inventor： Joaquin Delgado , Roger Henry Castillo , Boris Lerner , Ramesh Maddula , Emma Sawin , Alvaro Viloria , Jikai Lei
IPC: G06F16/2457 , G06N5/04 , G06N20/00
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.
-
公开(公告)号：US12278949B2
公开(公告)日：2025-04-15
申请号：US18321426
申请日：2023-05-22
Inventor： Li Zhang , Jizheng Xu , Kai Zhang , Hongbin Liu , Weijia Zhu , Yue Wang
IPC: H04N19/105 , H04N19/176 , H04N19/186 , H04N19/189
Abstract: A method of video processing includes determining, for a conversion between a video component of a video comprising a current video block and a bitstream representation of the video, that a first coding tool is used based on a rule for the current video block; and performing the conversion according to the determining, wherein the first coding tool includes transforming a representation of a visual signal between two color spaces, and where the rule specifies that a first quantization parameter (QP) offset for a luma channel of the current video block is equal to K1 and a second QP offset for a first chroma channel of the current video block is K1+O, where K1 and O are integers.
-
公开(公告)号：US12273525B2
公开(公告)日：2025-04-08
申请号：US17652204
申请日：2022-02-23
Inventor： Jizheng Xu , Li Zhang , Kai Zhang , Hongbin Liu , Yue Wang
IPC: H04N19/00 , H04N19/105 , H04N19/132 , H04N19/169 , H04N19/176 , H04N19/52 , H04N19/56 , H04N19/70
Abstract: A method of video processing is described. The method of video processing includes: performing a conversion between a video comprising video blocks and a coded representation of the video; wherein the coded representation conforms to a format rule, wherein the format rule specifies that context adaptive coding of a block vector predictor (BVP) index of a first video block coded using a block vector (BV) prediction mode and an index for inter mode coding used for coding a second video block is performed by sharing a same context; wherein the BVP index is to an entry in a history-based motion vector predictor list used for generating a block vector predictor for the first video block.
-
公开(公告)号：US12271353B2
公开(公告)日：2025-04-08
申请号：US17809606
申请日：2022-06-29
Applicant: Bytedance Inc.
Inventor： David Alan Johnston , Andrew James , Pradhee Tandon , Sivaramakrishnan Natarajan
IPC: G06F16/215 , G06F3/0481 , G06F16/28 , G06F16/951
Abstract: In general, embodiments of the present invention provide systems and computer readable media for implementing a single data integration platform that supports multiple data access interfaces to a single corpus of stored dynamic data collected from multiple data sources. In embodiments, the data integration platform includes a record tables layer that stores a group of data records and supports a CRUD interface for accessing the data records; a resolution mapping layer that stores a set of entities generated by a many-to-one mapping of data records to entities using entity resolution; and an entities layer that stores resolved entities which may be accessed via either a search interface based on search criteria or a hybrid search interface that supports “get via record id” queries.
-
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.
-
Patent Agency Ranking
公开(公告)号：US12256107B2
公开(公告)日：2025-03-18
申请号：US18516493
申请日：2023-11-21
Inventor： Zhipin Deng , Li Zhang , Ye-kui Wang , Kai Zhang , Jizheng Xu
IPC: H04N19/70 , H04N19/117 , H04N19/169 , H04N19/186
Abstract: The video processing may include video encoding, video decoding, or video transcoding. One example method of video processing includes performing a conversion between a video and a bitstream of the video according to a format rule. The format rule specifies that constraints on values of one or more first syntax elements in an adaptation parameter set are defined based on semantics of second syntax elements in a picture header and/or a slice header when a picture or a slice refers to the adaptation parameter set.
-
公开(公告)号：US12254500B2
公开(公告)日：2025-03-18
申请号：US18502356
申请日：2023-11-06
Applicant: Bytedance Inc.
Inventor： Nathaniel Blake Scholl , Andrew David Miner , Jason Alan Crawford
IPC: G06Q30/00 , G06Q30/0601
Abstract: Merchandise content is aggregated from numerous merchant sources and presented on computing devices of individual users. Users are able to purchase select individual merchandise items by performing a simplified action, such as a screen tap on a touchscreen device. When the user performs the action, a series of actions are performed programmatically and/or automatically on behalf of the user to initiate and complete the transaction for the selected merchandise item from the merchant source.
-
公开(公告)号：US12238306B2
公开(公告)日：2025-02-25
申请号：US18528017
申请日：2023-12-04
Inventor： Kai Zhang , Li Zhang , Hongbin Liu , Yue Wang
IPC: H04N19/52 , H04N19/119 , H04N19/136 , H04N19/176 , H04N19/186 , H04N19/55
Abstract: Devices, systems and methods for sub-block based prediction are described. In a representative aspect, a method for video encoding includes partitioning, based on a first rule, a luma component of a block of video data into a first set of sub-blocks. The method also includes partitioning, based on a second rule, a first chroma component of the block of video data into a second set of sub-blocks. The first and the second set of sub-blocks include different numbers of sub-blocks. The method also includes performing a subsequent motion prediction based on the first and the second set of sub-blocks.
-
公开(公告)号：US12238305B2
公开(公告)日：2025-02-25
申请号：US18492937
申请日：2023-10-24
Inventor： Li Zhang , Kai Zhang , Hongbin Liu , Jizheng Xu , Yue Wang
IPC: H04N19/00 , H04N19/117 , H04N19/159 , H04N19/186 , H04N19/70
Abstract: A method for video processing is provided to include: performing a conversion between a current video block of a video and a coded representation of current video block, wherein the conversion uses a coding mode in which the current video block is constructed based on a first domain and a second domain and/or chroma residue is scaled in a luma-dependent manner, and wherein information used for the coding mode is signaled in a parameter set that is different from a sequence parameter set (SPS), a video parameter set (VPS), a picture parameter set (PPS), or an adaptation parameter set (APS) used for carrying adaptive loop filtering (ALF) parameters.
-
公开(公告)号：US20250063192A1
公开(公告)日：2025-02-20
申请号：US18913903
申请日：2024-10-11
Inventor： Na ZHANG , Jizheng XU , Kai ZHANG , Mehdi SALEHIFAR , Li ZHANG
IPC: H04N19/513 , H04N19/105 , H04N19/139 , H04N19/196 , H04N19/58
Abstract: Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: determining, for a conversion between a current video block of a video and a bitstream of the video, that a first prediction mode is applied to the current block, reordering, in the first prediction mode, at least a first set of block vector difference (BVD) candidates of multiple BVD candidates corresponding to a first base candidate according to at least one criterion; deriving, based on the reordered BVD candidates, a block vector for the current video block; and performing the conversion based on the motion information.
-
-
-
-
-
-
-
-
-
Search Results
2206
records
(took 0.025 seconds)
