-
公开(公告)号：US12166968B2
公开(公告)日：2024-12-10
申请号：US17895511
申请日：2022-08-25
Inventor： Zhipin Deng , Kai Zhang , Li Zhang , Hongbin Liu , Jizheng Xu
IPC: H04N19/132 , H04N19/105 , H04N19/159 , H04N19/176 , H04N19/70
Abstract: Devices, systems and methods for digital video coding, which includes matrix-based intra prediction methods for video coding, are described. In a representative aspect, a method for video processing includes performing a conversion between a current video block of a video and a bitstream representation of the current video block according to a rule, where the rule specifies a relationship between samples of the current video block and matrices or offset values applied in a matrix weighted intra prediction (MIP) mode during the conversion, and where the MIP mode includes determining a prediction block of the current video block by performing, on previously coded samples of the video, a boundary downsampling operation, followed by a matrix vector multiplication operation, and selectively followed by an upsampling operation.
-
公开(公告)号：US12155957B2
公开(公告)日：2024-11-26
申请号：US18528745
申请日：2023-12-04
Inventor： Xiaoqi Li , Jingjin Zhou
Abstract: The embodiments of the disclosure disclose a video effect processing method and a video effect processing device. The method includes: detecting audio of a video; acquiring a video frame in the video when the audio is detected at a preset rhythm; performing effect processing on the target object in the video frame to obtain an effect processed video frame; and displaying and playing the effect processed video frame.
-
53.发明申请公开(公告)号：US20240386640A1
公开(公告)日：2024-11-21
申请号：US18693899
申请日：2022-10-25
Inventor： Peng ZHANG , Bingchuan LI
IPC: G06T11/60 , G06V10/26 , G06V10/774 , G06V10/82 , G06V40/16
Abstract: Embodiments of the disclosure provide a method, apparatus, device and storage medium for generating character style profile image. The method includes: inputting an original character profile image into a first feature encoder to obtain first character profile feature code; determining an attribute increment between the original character profile image and a template image; inputting the attribute increment and the first character profile feature code into a second feature encoder to obtain a second character profile feature code; inputting the second character profile feature code into a style profile generative model to obtain an initial character style profile image; and merging the initial character style profile image into the template image to obtain a target character style profile image.
-
公开(公告)号：US20240386639A1
公开(公告)日：2024-11-21
申请号：US18693737
申请日：2022-09-16
Inventor： Zongcai Du , Haowei Lu , Zhiqiang Lang , Xiaoxia Hou
Abstract: Disclosed are a video cover generation method, apparatus, electronic device, and readable medium. The at least one method comprises: extracting at least two key frames in the video, wherein the key frame comprises feature information displayed in a cover; according to an action relevance of the at least two key frames, fusing the feature information in the at least two key frames in a single image to generate a cover of the video, wherein the action relevance comprises being relevant or being irrelevant.
-
-
Patent Agency Ranking
公开(公告)号：US12149494B2
公开(公告)日：2024-11-19
申请号：US17818661
申请日：2022-08-09
Inventor： Yudong Liao
IPC: H04L51/56 , G06Q10/107 , H04L51/04 , H04L51/42
Abstract: An information display method and apparatus, an electronic device, and a storage medium are provided. The method includes: on the basis of an email sharing operation triggered by a sharer, sharing, according to sharee information, a target email to a sharee corresponding to the sharee information; obtaining a first identifier corresponding to the sharee; and displaying, on an email display interface of the target email on an email client of the sharer, the first identifier corresponding to the sharee. The technical solution can simplify user viewing operations, thus increasing information viewing efficiency and improving user experience.
-
公开(公告)号：US20240380904A1
公开(公告)日：2024-11-14
申请号：US18778813
申请日：2024-07-19
Inventor： Semih ESENLIK , Yaojun WU , Zhaobin ZHANG , Yue LI , Kai ZHANG , Li ZHANG
IPC: H04N19/189 , H04N19/119 , H04N19/124 , H04N19/132 , H04N19/436
Abstract: Embodiments of the present disclosure provide a solution for data processing. A method for data processing is proposed. The method comprises: processing, during a conversion between data and a bitstream of the data, a first set of samples of a reconstructed latent representation of the data and a second set of samples of the reconstructed latent representation by using a model, the first set of samples being associated with a first sample of the reconstructed latent representation and the second set of samples being associated with a second sample of the reconstructed latent representation; and performing the conversion based on a result of the processing.
-
公开(公告)号：US20240377929A1
公开(公告)日：2024-11-14
申请号：US18657496
申请日：2024-05-07
Inventor： Beichuan YU , Zhaoyu WANG
IPC: G06F3/0484 , G06F3/0482
Abstract: A label display method and apparatus, an electronic device, and a computer-readable medium. The method includes: displaying a label selection control on a feed display interface in a process of displaying a feed stream, where the label selection control corresponds to at least one label; receiving selection information inputted by a user through performing a selection operation on the at least one label; acquiring a recommended feed corresponding to the selection information; and displaying the recommended feed on the feed display interface. This method realizes flexible control of the timing of label display.
-
公开(公告)号：US20240370274A1
公开(公告)日：2024-11-07
申请号：US18689803
申请日：2022-10-09
Inventor： Zhenghao Gu , Shijian Ge , Yongji Xie , Lei Yu , Shuai Yuan , Xiaohan Xu , Xiaobo Yan , Yongsu Zhang , Yu Zhang , Jian Wang
IPC: G06F9/4401
Abstract: Embodiments of the present disclosure provide an operating system startup method, apparatus and electronic device. A specific implementation of the method comprises: determining at least one target mirror server from a mirror server cluster based on a LinuxBoot on a diskless server, wherein a mirror file stored in a mirror server comprises a system kernel and a file system; downloading mirror file fragments from a target mirror server of the at least one target mirror server based on the LinuxBoot; assembling a plurality of downloaded mirror file fragments into a target mirror file; and booting an operating system of the diskless server based on a target system kernel and a target file system comprised in the target mirror file. Therefore, the efficiency and success rate of diskless boot-up of an operating system of the diskless server can be improved when booting the operating system based on the LinuxBoot.
-
公开(公告)号：US12137257B2
公开(公告)日：2024-11-05
申请号：US17389179
申请日：2021-07-29
Inventor： Kai Zhang , Li Zhang , Hongbin Liu , Jizheng Xu , Yue Wang
IPC: H04N19/96 , H04N19/119 , H04N19/12 , H04N19/122 , H04N19/13 , H04N19/132 , H04N19/136 , H04N19/157 , H04N19/172 , H04N19/176 , H04N19/184 , H04N19/186 , H04N19/46 , H04N19/70
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.
-
-
-
-
-
-
-
-
-
Search Results
2981
records
(took 0.038 seconds)
