-
公开(公告)号：US20250047855A1
公开(公告)日：2025-02-06
申请号：US18896281
申请日：2024-09-25
Inventor： Li Zhang , Jizheng Xu , Kai Zhang , Hongbin Liu , Weijia Zhu
IPC: H04N19/13 , H04N19/176 , H04N19/70
Abstract: Method of processing video data is disclosed. A method for video processing includes dividing, for a conversion between a block of a video and a bitstream of the block, syntax elements associated with the block into different groups of syntax elements; applying controls on the different groups of syntax elements separately; and performing the conversion based on the controls.
-
公开(公告)号：US20250046054A1
公开(公告)日：2025-02-06
申请号：US18717239
申请日：2023-03-17
Applicant: Beijing Bytedance Network Technology Co., Ltd. , Lemon Inc.
Inventor： Chong WANG , Lin ZHENG
Abstract: The disclosure relates to a method, an apparatus, a storage medium, an electronic device, a computer program product, and a computer program for feature extraction, device. The method includes: determining target data for a feature to be extracted, and determining, based on the target data, a plurality of query vectors, a plurality of key vectors, and a plurality of value vectors; determining a plurality of key-value pair information corresponding to each of the query vectors; and performing, for each of the query vectors, a random mapping based on the query vector and the plurality of data samples, to obtain a plurality of random query vectors, and determining feature information corresponding to the query vector based on the plurality of random query vectors and the plurality of key-value pair information.
-
公开(公告)号：US20250045262A1
公开(公告)日：2025-02-06
申请号：US18716465
申请日：2023-03-29
IPC: G06F16/22 , G06F16/2457 , G06F16/28
Abstract: Provided are a method and a device for information storage. The method includes: obtaining a plurality of pieces of target data, the target data including a plurality of pairs of key-value data; generating, based on an order of the plurality of pieces of target data, a first column storage file that stores key data included in each piece of target data; and generating, based on the order of the plurality of pieces of target data, a second column storage file that stores value data included in each piece of target data; wherein first position information of key data of each piece of the target data in the first column storage file is same as second position information of corresponding value data in the second column storage file.
-
公开(公告)号：US20250037806A1
公开(公告)日：2025-01-30
申请号：US18717362
申请日：2023-04-20
Applicant: Beijing Bytedance Network Technology Co., Ltd. , Lemon Inc.
Inventor： Xiang GAO , Weihao GAO , Wenzhi XIAO , Zhirui WANG , Liang XIANG , Chong WANG
IPC: G16C20/70
Abstract: According to implementations of the present disclosure, a method, apparatus, device and medium for managing molecular prediction is provided. In the method, an upstream model is obtained from a portion of network layers in a pretrained model, the pretrained model describing an association between a molecular structure and molecular energy. A downstream model is determined based on a molecular prediction purpose, and an output layer of the downstream model is determined based on the molecular prediction purpose. A molecular prediction model is generated based on the upstream model and the downstream model, the molecular prediction model describing an association between a molecular structure and a molecular prediction purpose associated with the molecular structure. Since the upstream model may have extensive knowledge related to molecules, the amount of training data required to train the molecular prediction model that is generated based on the upstream model and the downstream model may be reduced.
-
公开(公告)号：US20250029303A1
公开(公告)日：2025-01-23
申请号：US18715500
申请日：2023-05-09
Inventor： Dan LU
IPC: G06T13/00 , G06F3/0488
Abstract: The present disclosure provides an animation effect generation method and apparatus, a medium, and a device, and the method includes: in response to determining that an inertial movement of a target element after an end event of a two-dimensional touch movement involves a region outside a first elastic boundary of a display interface, determining collision information for occurrence of a collision rebound according to the first elastic boundary, a motion state of the target element when the end event occurs, and an assumed end-point position; and according to a preset target easing function and the collision information, generating a first animation from the motion state to the occurrence of the collision rebound, and a second animation from the occurrence of the collision rebound to a case where a first boundary of the target element is aligned with the first elastic boundary.
-
Patent Agency Ranking
公开(公告)号：US20250024088A1
公开(公告)日：2025-01-16
申请号：US18715068
申请日：2022-11-29
Inventor： Yixin CHEN
IPC: H04N21/234 , G06T3/40 , G06T3/60 , G06T5/50 , G06T7/194
Abstract: Embodiments of the present disclosure disclose a video generation method and apparatus, a device, and a storage medium. The method includes: obtaining a video frame contained in a video to be processed, where the video to be processed contains a portrait; performing portrait segmentation on the video frame to obtain a portrait image and a background image; adjusting transparency of pixels that meet a defined condition in the portrait image to obtain the adjusted portrait image; processing the background image to obtain an entire background image; fusing the adjusted portrait image and the entire background image to obtain a portrait video frame; and stitching a plurality of portrait video frames to obtain a target video.
-
公开(公告)号：US20250024065A1
公开(公告)日：2025-01-16
申请号：US18895908
申请日：2024-09-25
Inventor： Hongbin Liu , Li Zhang , Kai Zhang , Yue Wang
IPC: H04N19/513 , H04N19/176
Abstract: A method for video processing is provided. The method includes making a determination, for a conversion between a current video block of a video and a coded representation of the current video block, of whether to use a symmetric motion vector difference (SMVD) mode based on a currently selected best mode for the conversion; and performing the conversion based on the determining.
-
公开(公告)号：US20250024011A1
公开(公告)日：2025-01-16
申请号：US18704011
申请日：2022-11-03
Inventor： Yuzhong CHEN
IPC: H04N13/279 , H04N13/00 , H04N13/128
Abstract: Embodiments of the present disclosure provide a video processing method and apparatus, an electronic device, and a storage medium. The method includes: obtaining an original video, where the original video is a single-viewpoint video; determining target depth information of each original video frame among a plurality of original video frames in the original video; and generating, based on the target depth information and pixel values of original pixels in each original video frame, a three-dimensional viewpoint model corresponding to each original video frame, so that a client generates a new-viewpoint video corresponding to the original video based on the three-dimensional viewpoint model, where an absolute value of a difference between each of a plurality of viewpoints within a viewpoint range of the three-dimensional viewpoint model and a viewpoint of the corresponding original video frame is less than or equal to a preset angle threshold.
-
公开(公告)号：US20250022201A1
公开(公告)日：2025-01-16
申请号：US18715079
申请日：2022-11-29
Inventor： Panpan XU
IPC: G06T13/40 , G06T17/00 , H04N21/234
Abstract: Embodiments of the present disclosure disclose a special effect video generation method and apparatus, a device, and a storage medium. One person portrait image or a plurality of person portrait images are acquired, and a special effect information sequence is obtained. The one person portrait image and the special effect information sequence are input into a first special effect generation model, or the plurality of person portrait images and the special effect information sequence are input into the first special effect generation model, to obtain a plurality of special effect images. The plurality of special effect images are stitched in the set order, to obtain a target special effect video.
-
40.发明申请公开(公告)号：US20250016421A1
公开(公告)日：2025-01-09
申请号：US18575120
申请日：2022-05-23
IPC: H04N21/4788 , H04N21/431 , H04N21/858
Abstract: The present disclosure relates to a method and an apparatus for replying to information, electronic device, computer storage medium, and product. The method includes: playing first multimedia content and displaying a first sticker comprising target information in a playing interface of the first multimedia content, wherein the target information is associated with target multimedia content; receiving a first instruction for the first sticker which instructs to make a reply to the target information in multimedia form; and in response to receiving the first instruction, acquiring second multimedia content for replying to the target information.
-
-
-
-
-
-
-
-
-
Search Results
2981
records
(took 0.041 seconds)
