-
公开(公告)号：US20210312910A1
公开(公告)日：2021-10-07
申请号：US17353758
申请日：2021-06-21
Inventor： Li CHEN , Saisai ZOU
Abstract: Embodiments of the present disclosure disclose a method, apparatus and device for training a network, and a storage medium, relate to the field of artificial intelligence technology such as deep learning and speech analysis. A semantic prediction network comprises: an encoder network and at least one decoder network; and a particular solution is: acquiring a first speech feature of a target speech sample; the target speech sample being a synthesized speech sample or a real speech sample, the synthesized speech sample being attached with a sample syllable label and a semantic label comprising a value of the domain, and the real speech sample being attached with a sample syllable label; and jointly training an initial semantic prediction network and a syllable classification network using the first speech feature of the target speech sample, to obtain a trained semantic prediction network.
-
192.发明申请公开(公告)号：US20210312686A1
公开(公告)日：2021-10-07
申请号：US17350449
申请日：2021-06-17
Inventor： Tianwei Lin , Fu Li , Xiaoqing Ye , Henan Zhang , Xin Li
Abstract: The present disclosure discloses a method and apparatus for generating a human body three-dimensional model, a device and a storage medium. The method may include: receiving a single human body image, and extracting an SMPL human body three-dimensional model corresponding to the human body image and a PIFu human body three-dimensional model corresponding to the human body image; matching the SMPL human body three-dimensional model with the PIFu human body three-dimensional model to obtain a matching result; determining a vertex of the SMPL human body three-dimensional model closest to a vertex of the PIFu human body three-dimensional model based on the matching result to obtain a binding weight of the vertex of the PIFu human body three-dimensional model and each skeleton point of the SMPL human body three-dimensional model; and outputting a drivable human body three-dimensional model.
-
193.发明申请公开(公告)号：US20210312293A1
公开(公告)日：2021-10-07
申请号：US17354873
申请日：2021-06-22
Inventor： Teng Xi , Gang Zhang , Shengzhao Wen
Abstract: Embodiments of the present disclosure provide a method and apparatus for determining a network model pruning strategy, a device and a storage medium. The method may include: generating a BN threshold search space using configuration information of the BN threshold search space for a network model for a target hardware; generating a pruning strategy code generator using the BN threshold search space; randomly generating a BN threshold code using the pruning strategy code generator; decoding the BN threshold code to obtain a candidate BN threshold; and determining a target pruning strategy of the network model for the target hardware, based on a pruning accuracy loss of the network model corresponding to the candidate BN threshold.
-
194.发明申请公开(公告)号：US20210312230A1
公开(公告)日：2021-10-07
申请号：US17348306
申请日：2021-06-15
Inventor： Tao HUANG , Baohui WANG , Li LIU , Litao ZHENG
IPC: G06K9/62 , G06F40/30 , G06F40/279 , G06N3/08
Abstract: An information extraction method, an extraction model training method, an apparatus and an electronic device all relate to knowledge graphs. A specific implementation includes acquiring an input text and determining a semantic vector of the input text according to the input text. Such implementation also includes inputting the semantic vector of the input text to a pre-acquired extraction model to obtain a first enhanced text of the input text. The first enhanced text is a text with a text score greater than a preset threshold output by the extraction model. The extraction model performs text extraction based on the semantic vector of the input text. Since the semantic vector has rich context semantics, the enhanced text extracted by the extraction model can be more in line with the context of the input text.
-
195.发明申请公开(公告)号：US20210312171A1
公开(公告)日：2021-10-07
申请号：US17352767
申请日：2021-06-21
Inventor： Qingyue Meng
Abstract: The human body 3D key point detection method includes: acquiring a to-be-detected image, the to-be-detected image including first human body image data; inputting the to-be-detected image into a key point extraction model to acquire N first 3D heatmaps of N human body 3D key points in the first human body image data, each first 3D heatmap representing a Gaussian distribution of one human body 3D key point in first human body image data in a predetermined space, where N is a positive integer; and determining coordinate information about the N human body 3D key points in the first human body image data based on the N first 3D heatmaps.
-
Patent Agency Ranking
196.发明申请公开(公告)号：US20210311914A1
公开(公告)日：2021-10-07
申请号：US17347698
申请日：2021-06-15
Inventor： Yongqiang Yang , Pengfei Zheng , Yan Sun , Fei Zhou , Wei Lu , Meng Wang
Abstract: A transaction processing method, a transaction processing device, an electronic device and a readable storage medium are provided, which relate to the field of cloud service and cloud storage. The transaction processing method includes: receiving an operation request for a target shard in a directory tree of a file system, the directory tree of the file system being stored in a namespace of a distributed file system, the directory tree of the file system including a plurality of shards, each of the shards including data about a parent node identifier; converting the operation request into a transaction operation statement associated with the target shard; and processing the target shard in accordance with the transaction operation statement.
-
公开(公告)号：US20210310809A1
公开(公告)日：2021-10-07
申请号：US17350744
申请日：2021-06-17
Inventor： Wenlong Chen , Yang Yang , Pengbin Yang , Jianxu Zhang
Abstract: The present application discloses a dead reckoning method for a vehicle, an apparatus, an apparatus and a storage medium, and relates to the fields of vehicle control, intelligent driving and automatic driving. The specific implementation solution is as follows: obtaining a position and attitude increment of the vehicle on the basis of wheel speed information of the vehicle; and carrying out dead reckoning on the position and attitude of the vehicle at a current moment, on the basis of the position and attitude increment of the vehicle and the position and attitude at a previous moment.
-
公开(公告)号：US20210304371A1
公开(公告)日：2021-09-30
申请号：US17082761
申请日：2020-10-28
Inventor： Yuzhan CAI , Chao ZHENG , Chao YAN , Hantian ZHANG
Abstract: The disclosure provides a 3-dimensional reconstruction method, an electronic device and a storage medium. The method includes: obtaining an image sequence pre-collected by a camera; obtaining nominal intrinsic parameters of the camera, and preset initial values of distortion coefficients of the camera, the camera being a camera for collecting the image sequence; calculating fluctuation ranges of the distortion coefficients; performing the 3D reconstruction on the image sequence based on the nominal intrinsic parameters, the initial values of the distortion coefficients, and the fluctuation ranges of the distortion coefficients; and during the 3D reconstruction, optimizing an obtained visual point cloud and a camera pose.
-
公开(公告)号：US20210303938A1
公开(公告)日：2021-09-30
申请号：US17345612
申请日：2021-06-11
Inventor： Yuanfei GAO
IPC: G06K9/62 , G06N20/00 , H04N21/234 , H04N21/24
Abstract: A method and apparatus for optimizing a video playback start, a device and a storage medium are provided. An implementation of the method may include: acquiring feature data, the acquired feature data affecting the video playback start speed when a video starts to play; inputting the acquired feature data into a pre-trained gradient boosting decision tree (GBDT) regression model to output a predicted value for a video buffer frame, and recording the predicted value as a first predicted value; and ascertaining whether to start playing the video based on the first predicted value.
-
公开(公告)号：US20210303864A1
公开(公告)日：2021-09-30
申请号：US17347290
申请日：2021-06-14
Inventor： Xiangming ZHAO , Fei LI , Ting YUN , Guoqing CHEN , Saiqun LIN , Lin WANG
IPC: G06K9/00
Abstract: A method, apparatus, and electronic device for processing a video, a medium and a product are presented. An implementation of the method includes: acquiring a target video; selecting, from at least one preset model, a preset model as a target model; determining output data of the target model based on the target video and the target model; reselecting, in response to determining that the output data does not meet a condition corresponding to the target model, another preset model as the target model from the at least one preset model until the output data of the target model meets the condition corresponding to the target model; and determining, based on the output data, a dynamic cover from the target video.
-
-
-
-
-
-
-
-
-
Search Results
1985
records
(took 0.038 seconds)
