公开(公告)号：US12112494B2

公开(公告)日：2024-10-08

申请号：US17053335

申请日：2020-02-28

申请人： Google LLC

发明人： Honglak Lee ,  Xinchen Yan ,  Soeren Pirk ,  Yunfei Bai ,  Seyed Mohammad Khansari Zadeh ,  Yuanzheng Gong ,  Jasmine Hsu

IPC分类号： G06T7/55 ,  B25J9/16 ,  B25J13/08 ,  G06F18/21 ,  G06T7/50 ,  G06V20/10 ,  G06V20/64

CPC分类号： G06T7/55 ,  B25J9/1605 ,  B25J9/163 ,  B25J9/1669 ,  B25J9/1697 ,  B25J13/08 ,  G06F18/2163 ,  G06T7/50 ,  G06V20/10 ,  G06V20/64 ,  G06T2207/10024 ,  G06T2207/10028 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/20132

摘要： Implementations relate to training a point cloud prediction model that can be utilized to process a single-view two-and-a-half-dimensional (2.5D) observation of an object, to generate a domain-invariant three-dimensional (3D) representation of the object. Implementations additionally or alternatively relate to utilizing the domain-invariant 3D representation to train a robotic manipulation policy model using, as at least part of the input to the robotic manipulation policy model during training, the domain-invariant 3D representations of simulated objects to be manipulated. Implementations additionally or alternatively relate to utilizing the trained robotic manipulation policy model in control of a robot based on output generated by processing generated domain-invariant 3D representations utilizing the robotic manipulation policy model.

公开(公告)号：US12112478B2

公开(公告)日：2024-10-08

申请号：US18544662

申请日：2023-12-19

申请人： Blaize, Inc.

发明人： Deepak Chandra Bijalwan ,  Dinakar C. Munagala

IPC分类号： G06K9/00 ,  G06F18/21 ,  G06F18/214 ,  G06N3/08 ,  G06T5/70 ,  G06T7/00 ,  G06V10/774 ,  G06V10/776 ,  G06V10/82 ,  G16H30/40 ,  G16H50/20

CPC分类号： G06T7/0012 ,  G06F18/214 ,  G06F18/2163 ,  G06F18/217 ,  G06N3/08 ,  G06T5/70 ,  G06V10/774 ,  G06V10/776 ,  G06V10/82 ,  G16H30/40 ,  G16H50/20 ,  G06T2207/10116 ,  G06T2207/20081 ,  G06T2207/20084

摘要： Systems and methods are disclosed for predicting one or more medical conditions utilizing digital images and employing artificial intelligent algorithms. The system offers accurate predictions utilizing quantized pre-trained deep learning model. The pre-trained deep learning model is trained on data samples and later refined as the system processes more digital images or new medical conditions are incorporated. One pre-trained deep learning model is used to predict the probability of one or more medical conditions and identify locations in the digital image effected by the one or more medical conditions. Further, one pre-trained deep learning model utilizing additional data and plurality of digital images, forecasts rate of infection and spread of the medical condition over time.

公开(公告)号：US12086712B2

公开(公告)日：2024-09-10

申请号：US17512463

申请日：2021-10-27

申请人： Korea Electronics Technology Institute

发明人： Choong Sang Cho ,  Young Han Lee

IPC分类号： G06T7/11 ,  G06F18/21 ,  G06N3/045 ,  G06N3/08 ,  G06V10/75

CPC分类号： G06N3/08 ,  G06F18/2163 ,  G06F18/217 ,  G06N3/045 ,  G06T7/11 ,  G06V10/751 ,  G06T2207/20081 ,  G06T2207/20084

摘要： There are provided a method and a system for image segmentation utilizing a GAN architecture. A method for training an image segmentation network according to an embodiment includes: inputting an image to a first network which is trained to output a region segmentation result regarding an input image, and generating a region segmentation result; and inputting the region segmentation result generated at the generation step and a ground truth (GT) to a second network, and acquiring a discrimination result, the second network being trained to discriminate inputted region segmentation results as a result generated by the first network and a GT, respectively; and training the first network and the second network by using the discrimination result. Accordingly, region segmentation performance of a semantic segmentation network regarding various images can be enhanced, and a very small image region can be exactly segmented.

公开(公告)号：US12033375B2

公开(公告)日：2024-07-09

申请号：US17241600

申请日：2021-04-27

申请人： Airbus Defence and Space GmbH

发明人： Manfred Hiebl

IPC分类号： G06V10/82 ,  G06F18/21 ,  G06V10/70 ,  G06V10/764 ,  G06V40/16

CPC分类号： G06V10/82 ,  G06F18/2163 ,  G06V10/70 ,  G06V10/764 ,  G06V40/165 ,  G06V40/172

摘要： An object identification unit contains an artificial neural network and is designed to identify human faces. For this purpose, a face is divided into a number of triangles. The relative component of the area of each triangle in the total of the areas of all triangles is ascertained to ascertain a rotational angle of the face. The relative component of the area of each triangle in the total of the area of all triangles is then scaled to a rotation-invariant dimension of the face. The scaled area of the triangles is supplied to the artificial neural network in order to identify a person.

公开(公告)号：US20240184852A1

公开(公告)日：2024-06-06

申请号：US18435405

申请日：2024-02-07

申请人： Microsoft Technology Licensing, LLC

发明人： Hamidreza Vaezi JOZE ,  Vivek PRADEEP ,  Karthik VIJAYAN

IPC分类号： G06F18/214 ,  G06F18/21 ,  G06F18/211 ,  G06N3/04 ,  G06N3/08 ,  G06V40/10 ,  G06V40/16

CPC分类号： G06F18/2148 ,  G06F18/211 ,  G06F18/2155 ,  G06F18/2163 ,  G06N3/04 ,  G06N3/08 ,  G06V40/10 ,  G06V40/161 ,  G06V2201/07

摘要： A method of training a neural network for detecting target features in images is described. The neural network is trained using a first data set that includes labeled images, where at least some of the labeled images having subjects with labeled features, including: dividing each of the labeled images of the first data set into a respective plurality of tiles, and generating, for each of the plurality of tiles, a plurality of feature anchors that indicate target features within the corresponding tile. Target features that correspond to the plurality of feature anchors are detected in a second data set of unlabeled images. Images of the second data set having target features that were not detected are labeled. A third data set that includes the first data set and the labeled images of the second data set is generated. The neural network is trained using the third data set.

公开(公告)号：US11948090B2

公开(公告)日：2024-04-02

申请号：US17096126

申请日：2020-11-12

申请人： Tencent America LLC

发明人： Wei Jiang ,  Wei Wang ,  Shan Liu

IPC分类号： G06N3/084 ,  G06F17/18 ,  G06F18/21 ,  G06F18/213 ,  G06T9/00

CPC分类号： G06N3/084 ,  G06F17/18 ,  G06F18/213 ,  G06F18/2163 ,  G06T9/002

摘要： In the present disclosure, a method for compressing a feature map is provided, where the feature map is generated by passing a first input through a deep neural network (DNN). A respective optimal index order and a respective optimal unifying method are determined for each of super-blocks that are partitioned from the feature map. A selective structured unification (SSU) layer is subsequently determined based on the respective optimal index order and the respective optimal unifying method for each of the super-blocks. The SSU layer is added to the DNN to form an updated DNN, and is configured to perform unification operations on the feature map. Further, a first estimated output is determined, where the first estimated output is generated by passing the first input through the updated DNN.

公开(公告)号：US20240086638A1

公开(公告)日：2024-03-14

申请号：US18515947

申请日：2023-11-21

申请人： Wells Fargo Bank, N.A.

发明人： Aafrin Dabhoiwala ,  Roberto Amparan ,  Qianhui Rong ,  Yang Angelina Yang ,  Menglin Cao

IPC分类号： G06F40/295 ,  G06F18/21 ,  G06F18/2113 ,  G06F18/241 ,  G06F18/2431 ,  G06V30/12 ,  G06V30/413

CPC分类号： G06F40/295 ,  G06F18/2113 ,  G06F18/2163 ,  G06F18/241 ,  G06F18/2431 ,  G06V30/12 ,  G06V30/413

摘要： Systems, apparatuses, methods, and computer program products are disclosed for automatically determining accuracy of entity recognition of text. An example method includes segmenting a service entity recognition analysis of the text and a gold entity recognition analysis of the text into common superstrings that define entity spans. The example method further includes classifying each of the entity spans based on an accuracy of entity recognition in the service analysis of the text corresponding to the entity spans using a classification system that differentiates accurately identified but improperly bounded entities into at least three subcategories to obtain an entity accuracy classification. The example method also includes obtaining a score report based on the entity accuracy classification. The example method additionally includes performing an action set based on the entity accuracy classification.

公开(公告)号：US11922628B2

公开(公告)日：2024-03-05

申请号：US17224886

申请日：2021-04-07

申请人： Arizona Board of Regents on Behalf of Arizona State University

发明人： Zongwei Zhou ,  Vatsal Sodha ,  Jiaxuan Pang ,  Jianming Liang

IPC分类号： G06V10/00 ,  G06F18/21 ,  G06F18/214 ,  G06N3/045 ,  G06N3/088 ,  G06T3/00 ,  G06T7/11 ,  G06V10/26 ,  G06V10/77 ,  G16H30/40

CPC分类号： G06T7/11 ,  G06F18/2155 ,  G06F18/2163 ,  G06N3/045 ,  G06N3/088 ,  G06T3/00 ,  G06V10/26 ,  G06V10/7715 ,  G16H30/40 ,  G06V2201/03

摘要： Described herein are means for generation of self-taught generic models, named Models Genesis, without requiring any manual labeling, in which the Models Genesis are then utilized for the processing of medical imaging. For instance, an exemplary system is specially configured for learning general-purpose image representations by recovering original sub-volumes of 3D input images from transformed 3D images. Such a system operates by cropping a sub-volume from each 3D input image; performing image transformations upon each of the sub-volumes cropped from the 3D input images to generate transformed sub-volumes; and training an encoder-decoder architecture with skip connections to learn a common image representation by restoring the original sub-volumes cropped from the 3D input images from the transformed sub-volumes generated via the image transformations. A pre-trained 3D generic model is thus provided, based on the trained encoder-decoder architecture having learned the common image representation which is capable of identifying anatomical patterns in never before seen 3D medical images having no labeling and no annotation. More importantly, the pre-trained generic models lead to improved performance in multiple target tasks, effective across diseases, organs, datasets, and modalities.

公开(公告)号：US11880766B2

公开(公告)日：2024-01-23

申请号：US17384357

申请日：2021-07-23

申请人： Adobe Inc.

发明人： Cameron Smith ,  Ratheesh Kalarot ,  Wei-An Lin ,  Richard Zhang ,  Niloy Mitra ,  Elya Shechtman ,  Shabnam Ghadar ,  Zhixin Shu ,  Yannick Hold-Geoffrey ,  Nathan Carr ,  Jingwan Lu ,  Oliver Wang ,  Jun-Yan Zhu

IPC分类号： G06N3/08 ,  G06F3/04845 ,  G06F3/04847 ,  G06T11/60 ,  G06T3/40 ,  G06N20/20 ,  G06T5/00 ,  G06T5/20 ,  G06T3/00 ,  G06T11/00 ,  G06F18/40 ,  G06F18/211 ,  G06F18/214 ,  G06F18/21 ,  G06N3/045

CPC分类号： G06N3/08 ,  G06F3/04845 ,  G06F3/04847 ,  G06F18/211 ,  G06F18/214 ,  G06F18/2163 ,  G06F18/40 ,  G06N3/045 ,  G06N20/20 ,  G06T3/0006 ,  G06T3/0093 ,  G06T3/40 ,  G06T3/4038 ,  G06T3/4046 ,  G06T5/005 ,  G06T5/20 ,  G06T11/001 ,  G06T11/60 ,  G06T2207/10024 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/20221 ,  G06T2210/22

摘要： An improved system architecture uses a pipeline including a Generative Adversarial Network (GAN) including a generator neural network and a discriminator neural network to generate an image. An input image in a first domain and information about a target domain are obtained. The domains correspond to image styles. An initial latent space representation of the input image is produced by encoding the input image. An initial output image is generated by processing the initial latent space representation with the generator neural network. Using the discriminator neural network, a score is computed indicating whether the initial output image is in the target domain. A loss is computed based on the computed score. The loss is minimized to compute an updated latent space representation. The updated latent space representation is processed with the generator neural network to generate an output image in the target domain.

公开(公告)号：US20240015032A1

公开(公告)日：2024-01-11

申请号：US18219167

申请日：2023-07-07

申请人： Indeed, Inc.

发明人： Greg Altman ,  Justin Daily ,  Sergey Karamov

IPC分类号： H04L9/32 ,  H04L9/40 ,  G06F16/957 ,  G06F3/04812 ,  G06F3/0482 ,  G06F3/0485 ,  G06F11/32 ,  G06F11/34 ,  G06V30/416 ,  G06V30/414 ,  G06F18/21 ,  G06F18/40 ,  G06F18/214 ,  G06F16/9035 ,  G06Q10/1053 ,  G06Q10/109 ,  H04L65/403

CPC分类号： H04L9/3268 ,  H04L9/3247 ,  H04L63/166 ,  G06F16/957 ,  G06F3/04812 ,  G06F3/0482 ,  G06F3/0485 ,  G06F11/32 ,  G06F11/3409 ,  G06F11/3438 ,  G06V30/416 ,  G06V30/414 ,  G06F18/2163 ,  G06F18/40 ,  G06F18/2155 ,  G06F16/9035 ,  G06Q10/1053 ,  G06Q10/109 ,  H04L65/403 ,  H04L63/0428 ,  G06F11/3452 ,  G06F2203/04803 ,  G06Q30/0243

摘要： A platform security system and method improve security by binding an identity of a self-contained certificate signing request (SC CSR) requestor to the SC CSR to prevent malicious tampering, such as man-in-the-middle attacks. In at least one embodiment, the requestor, such as a client computer system or other source of a request, requests certificates from a certificate authority (CA). Binding the identity of the SC CSR to the requestor can prevent unauthorized system and/or data access and potentially resultant unauthorized access, malicious tampering, such as man-in-the-middle attacks, and other unauthorized actions or observations. Validation can be performed at the CA on the SC CSR to determine the integrity of the requestor and authorization to receive certificates before the CA sends the certificate to the requestor.