公开(公告)号：US12100427B2

公开(公告)日：2024-09-24

申请号：US18496539

申请日：2023-10-27

申请人： Cole Asher Ratias

发明人： Cole Asher Ratias

IPC分类号： G11B27/031 ,  G06F18/214 ,  G06T11/60 ,  G06V10/82 ,  G06V20/40 ,  G11B27/036

CPC分类号： G11B27/031 ,  G06F18/214 ,  G06F18/2148 ,  G06T11/60 ,  G06V10/82 ,  G06V20/41 ,  G11B27/036

摘要： A video editing program is taught by machine learning to conform a video sequence to a known style. For example, some famous filmmakers (e.g., Steven Spielberg, Michael Bay) have signature cinematic “takes” that appear in their acclaimed works. Such takes may involve use of subject tracking, placements and movements of people or objects in the scene, and lighting intensities or shadows in the scene. The editing program may be trained to recognize video sequences that can be modified to conform to one or more of such signature styles and to offer the modification to the user at the user's option.

公开(公告)号：US12100244B2

公开(公告)日：2024-09-24

申请号：US17303365

申请日：2021-05-27

申请人： STATS LLC

发明人： Xinyu Wei ,  Jennifer Hobbs ,  Long Sha ,  Patrick Joseph Lucey ,  Sujoy Ganguly

IPC分类号： G06K9/00 ,  G06F18/21 ,  G06F18/214 ,  G06K9/62 ,  G06N3/04 ,  G06N3/045 ,  G06N3/08 ,  G06V10/82 ,  G06V20/40 ,  G06V20/52 ,  G06V40/20

CPC分类号： G06V40/20 ,  G06F18/214 ,  G06F18/217 ,  G06N3/045 ,  G06N3/08 ,  G06V10/82 ,  G06V20/42 ,  G06V20/46 ,  G06V20/52

摘要： A method and system of generating agent and actions prediction based on multi-agent tracking data are disclosed herein. A computing system retrieves tracking data from a data store. The computing system generates a trained neural network by generating a plurality of training data sets based on the tracking data by converting each frame of data into a matrix representation of the data contained in the frame and learning, by the neural network, a start frame and end frame of each action contained in the frame and its associated actor. The computing system receives target tracking data associated with an event. The target tracking data includes a plurality of actors and a plurality of actions. The computing system generates, via the trained neural network, a target start frame and a target end frame of each action identified in the tracking data and a corresponding actor.

公开(公告)号：US12100082B2

公开(公告)日：2024-09-24

申请号：US17983952

申请日：2022-11-09

申请人： Mohamed bin Zayed University of Artificial Intelligence

发明人： Amandeep Kumar ,  Ankan Kumar Bhunia ,  Hisham Cholakkal ,  Sanath Narayan ,  Rao Muhammad Anwer ,  Fahad Khan

IPC分类号： G06T11/60 ,  G06T9/00 ,  G06V10/44 ,  G06V10/74 ,  G06V10/80 ,  G06V10/82

CPC分类号： G06T11/60 ,  G06T9/00 ,  G06V10/44 ,  G06V10/761 ,  G06V10/806 ,  G06V10/82 ,  G06T2200/24

摘要： An apparatus, computer readable storage medium and method of generating a diverse set of images from few-shot images, includes a parameter input receiving values for control parameters to control an extent to which each reference image impacts a newly generated image. The apparatus involves an image generation deep learning network for generating an image for each of the values for the control parameters. The deep learning network has an encoder, a transformer-based fusion block, and a decoder. The transformer-based fusion block includes a mapping network that computes meta-weights from features extracted from the reference images and the control parameters, and a cross-attention block to generate modulation weights based on the meta-weights. An output displays high-quality and diverse images generated based on the values for the control parameter.

公开(公告)号：US12099905B2

公开(公告)日：2024-09-24

申请号：US17870153

申请日：2022-07-21

申请人： THE BOEING COMPANY

发明人： Ryan Scott Powell

IPC分类号： G06V10/82 ,  G06F18/214 ,  G06F18/2431 ,  G06N20/00 ,  G06V10/40 ,  G06V10/764 ,  G06V10/98

CPC分类号： G06N20/00 ,  G06F18/214 ,  G06F18/2431 ,  G06V10/40 ,  G06V10/764 ,  G06V10/82 ,  G06V10/98

摘要： A system for categorizing images is provided. The system is programmed to store a first training set of images. Each image of the first training set of images is associated with an image category of a plurality of image categories. The system is further programmed to analyze each image of the first training set of images to determine one or more features associated with each of the plurality of image categories and receive a second training set of images. The second training set of images includes one or more errors. The system is also programmed to analyze each image of the second training set of images to determine one or more features associated with an error category and generate a model to identify each of the image categories based on the analysis such that the model includes the error category in the plurality of image categories.

公开(公告)号：US12099622B2

公开(公告)日：2024-09-24

申请号：US17553536

申请日：2021-12-16

申请人： Cryptography Research, Inc.

发明人： Mark Evan Marson ,  Michael Alexander Hamburg ,  Helena Handschuh

IPC分类号： G06F21/62 ,  G06F21/14 ,  G06N3/02 ,  G06N3/048 ,  G06V10/82

CPC分类号： G06F21/6218 ,  G06F21/14 ,  G06F21/6227 ,  G06N3/02 ,  G06N3/048 ,  G06V10/82

摘要： Aspects of the present disclosure involve implementations that may be used to protect neural network models against adversarial attacks by obfuscating neural network operations and architecture. Obfuscation techniques include obfuscating weights and biases of neural network nodes, obfuscating activation functions used by neural networks, as well as obfuscating neural network architecture by introducing dummy operations, dummy nodes, and dummy layers into the neural networks.

公开(公告)号：US20240313990A1

公开(公告)日：2024-09-19

申请号：US18183053

申请日：2023-03-13

申请人： Hewlett-Packard Development Company, L.P.

发明人： Pei Hsuan Li ,  Rose Hedderman ,  Sarah Shiraz ,  Yu Chun Huang

IPC分类号： H04L12/18 ,  G06V10/82 ,  G06V40/16

CPC分类号： H04L12/1818 ,  G06V10/82 ,  G06V40/176

摘要： An example non-transitory machine-readable storage medium comprising instructions executable by a processing resource of a computing device to cause the computing device to: receive a video feed of a participant in a video conference; identify the participants within the video feed; determine a probability that a characteristic is being experienced by the participant; determine a relevancy score of the participant based on the probability that the characteristic is being experienced by the participant; and display the participant relative to other participants in the video conference based on the relevancy score.

公开(公告)号：US20240312176A1

公开(公告)日：2024-09-19

申请号：US18671412

申请日：2024-05-22

申请人： Samsung Electronics Co., Ltd.

发明人： Pawan Prasad BINDIGAN HARIPRASANNA ,  Green Rosh K S ,  Vishakha S R ,  Sungsoo CHOI ,  Hyuntaek WOO ,  Chaeeun LEE ,  Beomsu KIM

IPC分类号： G06V10/26 ,  G06V10/82 ,  G06V40/10

CPC分类号： G06V10/273 ,  G06V10/82 ,  G06V40/11

摘要： A method performed by an electronic device for estimating a landmark point of a body part of subject by electronic device is provided. The method includes generating, by the electronic device, an initial coarse estimation of the landmark point of the body part using a light-weight deep neural network, determining, by the electronic device, an occluded region of the body part based on the generated initial coarse estimation of the landmark point using a segmentation mask, estimating, by the electronic device, the occlusion probability for the landmark point in the at least one occluded region and the generated initial coarse estimation, determining, by the electronic device, a correction factor for applying on the generated initial coarse estimation as a measure of the estimated occlusion probability, and selecting, by the electronic device, a pre-defined number of neural networks by applying the determined correction factor for processing the at least one occluded region and the generated initial coarse estimation to generate final estimation of the landmark point.

公开(公告)号：US20240312122A1

公开(公告)日：2024-09-19

申请号：US18184459

申请日：2023-03-15

申请人： Nvidia Corporation

发明人： Nicolas Moenne-Loccoz ,  Zan Gojcic ,  Gavriel State ,  Zian Wang ,  Ignacio Llamas

IPC分类号： G06T15/50 ,  G06T5/50 ,  G06V10/60 ,  G06V10/74 ,  G06V10/82

CPC分类号： G06T15/506 ,  G06T5/50 ,  G06V10/60 ,  G06V10/761 ,  G06V10/82 ,  G06T2207/20221

摘要： Approaches presented herein provide for the generation of visual content, including different types of content representations from different sources, rendered to include consistent scene illumination for the various representations. A first render pass can produce a first image including only proxies of implicit representations (e.g., NeRF objects) under scene illumination. A second render pass can produce a second image that includes a representation of the explicit scene objects, as well as the proxies of the implicit representations, under the scene illumination, which produces secondary lighting effects. The first and second images are compared to determine irradiance ratio data for the various pixel locations. A third render pass can produce a third image that includes the implicit representations, which can have relighting performed according to the irradiance ratio data to include the secondary lighting effects. The implicit and explicit objects can then be composited to produce an image with consistent scene illumination.

公开(公告)号：US20240311976A1

公开(公告)日：2024-09-19

申请号：US18671582

申请日：2024-05-22

申请人： TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED

发明人： Yuanyuan ZHAO ,  Jian ZHANG ,  Yingying FU ,  Hao LIU ,  Chen LI

IPC分类号： G06T5/60 ,  G06T5/50 ,  G06V10/26 ,  G06V10/764 ,  G06V10/774 ,  G06V10/776 ,  G06V10/82

CPC分类号： G06T5/60 ,  G06T5/50 ,  G06V10/26 ,  G06V10/764 ,  G06V10/774 ,  G06V10/776 ,  G06V10/82 ,  G06T2207/10016 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/20221

摘要： This application relates to an image correction model training method including obtaining a training image, and performing random data distortion on the training image to obtain a distorted image and distortion parameter information; inputting the distorted image into an initial image correction model to predict a correction parameter, to obtain initial correction parameter information, and performing image correction on the distorted image to obtain an initial corrected image; calculating a loss between the initial correction parameter information and correction parameter information corresponding to the distortion parameter information, to obtain parameter loss information, and calculating a loss between the training image and the initial corrected image to obtain image loss information; updating the initial image correction model to obtain an updated image correction model; and performing training and obtaining the updated image correction model iteratively, until a target image correction model is obtained when a training completion condition is reached.

公开(公告)号：US20240307015A1

公开(公告)日：2024-09-19

申请号：US18641232

申请日：2024-04-19

申请人： Cleerly, Inc.

发明人： James K. Min ,  James P. Earls ,  Hugo Miguel Rodrigues Marques

IPC分类号： A61B6/50 ,  A61B5/00 ,  A61B5/055 ,  A61B6/00 ,  A61B6/03 ,  A61B6/46 ,  A61B8/12 ,  A61B8/14 ,  A61K49/04 ,  G06F18/10 ,  G06T7/00 ,  G06V10/20 ,  G06V10/24 ,  G06V10/74 ,  G06V10/764 ,  G06V10/82

CPC分类号： A61B6/504 ,  A61B5/0066 ,  A61B5/0075 ,  A61B5/055 ,  A61B5/7267 ,  A61B5/742 ,  A61B5/7475 ,  A61B6/032 ,  A61B6/037 ,  A61B6/463 ,  A61B6/467 ,  A61B6/481 ,  A61B6/5205 ,  A61B8/12 ,  A61B8/14 ,  A61K49/04 ,  G06F18/10 ,  G06T7/0012 ,  G06V10/20 ,  G06V10/245 ,  G06V10/761 ,  G06V10/764 ,  G06V10/82 ,  G06T2207/10081 ,  G06T2207/10088 ,  G06T2207/10101 ,  G06T2207/10132 ,  G06T2207/20081 ,  G06T2207/30048 ,  G06T2207/30101 ,  G06V10/247

摘要： The disclosure herein relates to systems, methods, and devices for medical image analysis, diagnosis, risk stratification, decision making and/or disease tracking. In some embodiments, the systems, devices, and methods described herein are configured to analyze non-invasive medical images of a subject to automatically and/or dynamically identify one or more features, such as plaque and vessels, and/or derive one or more quantified plaque parameters, such as radiodensity, radiodensity composition, volume, radiodensity heterogeneity, geometry, location, and/or the like. In some embodiments, the systems, devices, and methods described herein are further configured to generate one or more assessments of plaque-based diseases from raw medical images using one or more of the identified features and/or quantified parameters.