-
公开(公告)号：US20220351390A1
公开(公告)日：2022-11-03
申请号：US17866934
申请日：2022-07-18
Inventor： Yang ZHAO
Abstract: A method for generating motion capture data, an electronic device and a storage medium are provided, relating to fields of computer technologies such as augmented reality and deep learning, and in particular, to a field of computer vision. The method includes processing a plurality of video frames comprising a target object to obtain a key point coordinate of the target object in at least one of the video frames; and obtaining, as motion capture data for the target object, a posture information of the target object according to the plurality of video frames and the key point coordinate of the target object in the video frame.
-
公开(公告)号：US20220350965A1
公开(公告)日：2022-11-03
申请号：US17864636
申请日：2022-07-14
Inventor： Tongyang LIU , Shu WANG , Wanli CHANG , Wei ZHENG , Zhifan FENG , Chunguang CHAI , Yong ZHU
IPC: G06F40/211 , G06F40/30 , G06F40/109 , G06N3/08
Abstract: A method for generating a pre-trained language model, includes: obtaining sample files; obtaining typography structure information and text information of the sample files by parsing the sample files; obtaining a plurality of task models of a pre-trained language model; obtaining a trained pre-trained language model by jointly training the pre-trained language model and the plurality of task models according to the typography structure information and the text information; and generating a target pre-trained language model by fine-tuning the trained pre-trained language model according to the typography structure information and the text information.
-
793.发明授权公开(公告)号：US11488294B2
公开(公告)日：2022-11-01
申请号：US16939277
申请日：2020-07-27
Inventor： Yawei Wen , Jiabing Leng , Minghao Liu , Yulin Xu , Jiangliang Guo , Xu Li
Abstract: Provided are a method for detecting display screen quality, an apparatus, an electronic device and a storage medium. The method includes: receiving a quality detection request sent by a console deployed on a display screen production line, the quality detection request including a display screen image collected by an image collecting device on the display screen production line; inputting the display screen image into a defect detection model to obtain a defect detection result, the defect detection model being obtained by training historical defective display screen images using a structure of deep convolutional neural networks and an object detection algorithm; and determining, according to the defect detection result, a defect on a display screen corresponding to the display screen image, a defect category corresponding to the defect, and a position corresponding to the defect.
-
公开(公告)号：US20220341737A1
公开(公告)日：2022-10-27
申请号：US17862929
申请日：2022-07-12
Inventor： Xuecen SHEN
Abstract: A navigation method is provided. The method relates to the field of computer technologies, and in particular, to the field of augmented reality technologies and visual navigation technologies. An implementation is: in response to resumption of navigation after interruption, calculating an initial angle of an inertial sensor based on an angle of a gyroscope; and continuing the navigation based on the initial angle of the inertial sensor and a position of a visual odometry device before the interruption.
-
公开(公告)号：US20220335316A1
公开(公告)日：2022-10-20
申请号：US17659516
申请日：2022-04-18
Inventor： YE ZHANG , JUN WANG , HAO WANG , YU MA , LIANG WANG
Abstract: The present disclosure discloses a data annotation method and apparatus, an electronic device and a readable storage medium, and relates to artificial intelligence fields such as deep learning, computer vision and autonomous driving. The method may include: acquiring a detection model, the detection model being trained by using sensor data manually annotated as startup data; performing obstacle detection on to-be-annotated sensor data by using the detection model, the startup data and the to-be-annotated sensor data being a same type of sensor data; performing obstacle tracking and matching according to detection results to obtain obstacle trajectory information; and modifying the detection results according to the obstacle trajectory information, and taking modified detection results as required annotation results. Labor and time costs can be saved by use of the solutions of the present disclosure.
-
Patent Agency Ranking
公开(公告)号：US20220335070A1
公开(公告)日：2022-10-20
申请号：US17811262
申请日：2022-07-07
Inventor： Yehan ZHENG , Yuanjun CAI
IPC: G06F16/28 , G06F16/245
Abstract: The disclosure provides a method and apparatus for querying a writing material, an apparatus for querying a writing material, and a storage medium. The method includes: determining a first topic corresponding to a target cluster by performing clustering on topics extracted from a plurality of candidate materials; determining a second topic associated with the first topic; determining at least one first candidate event associated with the first topic, and at least one second candidate event associated with the second topic; generating an event map according to a correlation between the first candidate event and the second candidate event; and querying the event map according to a target event to be written, so as to determine an event associated with the target event as the writing material.
-
797.发明申请公开(公告)号：US20220327147A1
公开(公告)日：2022-10-13
申请号：US17844975
申请日：2022-06-21
Inventor： Yingchao SHI , Jizhou HUANG
IPC: G06F16/29
Abstract: There is provided a method for updating information of a point of interest, an electronic device and a storage medium, relating to the field of artificial intelligence, in particular to the field of information intelligent search, and being applicable to a scene for identifying a specified type of text content. The method includes identifying a user focus information to be approved for a target point of interest from at least one user-generated content; constructing an approval request information for approving the user focus information; pushing the approval request information to an operator of the target point of interest and obtaining an approval result information for the user focus information from the operator; and updating an attribute information of the target point of interest according to the approval result information.
-
公开(公告)号：US20220324109A1
公开(公告)日：2022-10-13
申请号：US17809687
申请日：2022-06-29
Inventor： Hongsheng Zeng , Bo Zhou , Fan Wang , Yongfeng Chen , Jingzhou He
IPC: B25J9/16 , B62D57/032
Abstract: Disclosed are a method and an apparatus for controlling a multi-legged robot, and a storage medium. The method includes: acquiring current state parameters of the multi-legged robot; when types and/or quantities of the current state parameters meet a first preset condition, acquiring a first motion control policy by inputting the current state parameters into a first model generated by training; and controlling the multi-legged robot based on the first motion control policy.
-
公开(公告)号：US20220319141A1
公开(公告)日：2022-10-06
申请号：US17845843
申请日：2022-06-21
Inventor： Fanglong LIU , Xin LI , Dongliang HE
IPC: G06V10/22 , G06T7/11 , H04N19/174
Abstract: A methods for processing an image, a device, and a storage medium are provided. The method may include: inputting a target image into a pre-trained image segmentation model, the target image including at least one sub-image; extracting high-level semantic features and low-level features of the target image through the image segmentation model, and determining target location information of the sub-image in the target image based on the high-level semantic features and the low-level features; and performing a preset processing operation on the sub-image, based on the target location information of the sub-image.
-
公开(公告)号：US20220310064A1
公开(公告)日：2022-09-29
申请号：US17571805
申请日：2022-01-10
Inventor： Junyao SHAO , Xiaoyin FU , Qiguang ZANG , Zhijie CHEN , Mingxin LIANG , Huanxin ZHENG , Sheng QIAN
IPC: G10L15/06 , G10L15/183 , G10L15/16 , G10L15/28
Abstract: A method for training a speech recognition model, a device and a storage medium, which relate to the field of computer technologies, and particularly to the fields of speech recognition technologies, deep learning technologies, or the like, are disclosed. The method for training a speech recognition model includes: obtaining a fusion probability of each of at least one candidate text corresponding to a speech based on an acoustic decoding model and a language model; selecting a preset number of one or more candidate texts based on the fusion probability of each of the at least one candidate text, and determining a predicted text based on the preset number of one or more candidate texts; and obtaining a loss function based on the predicted text and a standard text corresponding to the speech, and training the speech recognition model based on the loss function.
-
-
-
-
-
-
-
-
-
Search Results
1526
records
(took 0.037 seconds)
