公开(公告)号：US20240005453A1

公开(公告)日：2024-01-04

申请号：US18368897

申请日：2023-09-15

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Albert SAA-GARRIGA ,  Mehmet YUCEL ,  Tommaso MAESTRI ,  Konstantinos PEPPAS

IPC: G06T3/60 ,  G06V10/774 ,  G06V10/82 ,  G06V10/776 ,  G06V10/94 ,  G06N3/098 ,  G06N3/045

CPC classification number: G06T3/60 ,  G06V10/774 ,  G06V10/82 ,  G06V10/776 ,  G06V10/95 ,  G06N3/098 ,  G06N3/045 ,  G06V2201/10

Abstract: Broadly speaking, the present techniques generally relates to methods, systems and apparatuses for performing image orientation correction, i.e. correcting or adjusting images that are tilted. In particular, the present application relates to a computer-implemented method for generating a training dataset for training a machine learning, ML, model using federated learning to perform image orientation correction, and methods for training the ML model using the generated training dataset. Advantageously, the method to generate a training dataset enables a diverse training dataset to be generated while maintaining user data privacy, where the diversity refers to the range of image tilt angles represented by the dataset. The present application also provides methods for training the ML model using the generated training dataset.

公开(公告)号：US20240005042A1

公开(公告)日：2024-01-04

申请号：US18216403

申请日：2023-06-29

Applicant: Russell Earles ,  Alex Songe

Inventor： Russell Earles ,  Alex Songe

IPC: G06F21/64 ,  H04N5/76 ,  G06F21/60

CPC classification number: G06F21/64 ,  H04N5/76 ,  G06V20/40 ,  G06V2201/10 ,  G06F21/602

Abstract: A system and method for recording, backing up, and authenticating footage from a dash cam or other video device comprises continuously synchronizing checksums from segments of video as they are recorded into rolling storage with an authentication server located remotely. Only metadata is uploaded until the video device experiences an interrupt event, at which point the last few rolling segments, as well as subsequent rolling segments until the termination of the interrupt event, are written to persistent storage and uploaded to the authentication server at the earliest opportunity. The metadata and video are encrypted with an asymmetric public/private key system enabling third parties to confirm, with the public key, that the metadata on the recording device and the authentication server match, and with the private key, download the video footage from the interrupt event.

公开(公告)号：US20230410471A1

公开(公告)日：2023-12-21

申请号：US18031850

申请日：2021-11-12

Applicant: VOLPARA HEALTH TECHNOLOGIES LIMITED

Inventor： Ralph HIGHNAM

IPC: G06V10/764 ,  G06V10/82 ,  G06V10/778

CPC classification number: G06V10/764 ,  G06V10/82 ,  G06V2201/03 ,  G06V2201/10 ,  G06V10/7788

Abstract: The present invention relates to a system and method to embed meta data from an imaging and communications system whereby the meta data is combined with image data as an input to a deep learning network. An image classification learning network is disclosed which comprises: a means to input image data and meta data; and an embedding layer comprising learnable embedding weights to encode the meta data to provide a learned object, and a softmax layer to classify a combination of the image data and the learned object.

公开(公告)号：US11829399B1

公开(公告)日：2023-11-28

申请号：US17814383

申请日：2022-07-22

Applicant: Schlumberger Technology Corporation

Inventor： Prashanth Pillai ,  Purnaprajna Raghavendra Mangsuli

IPC: G06F7/00 ,  G06F16/33 ,  G06V30/412 ,  G06F40/279 ,  G01V11/00 ,  G06V30/413

CPC classification number: G06F16/3347 ,  G01V11/002 ,  G06F40/279 ,  G06V30/412 ,  G06V30/413 ,  G06V2201/10

Abstract: Systems, computer-readable media, and methods are provided. Relevant documents related to a specific entity are identified based on document metadata. Text and associated spatial coordinates are extracted based on relevant document pages. Significant document entities and associated spatial locations are identified. Page ranking is based on the extracted text and the spatial coordinates, the significant document entities, and image vector representations of the pages. A deep learning language model that utilizes the text and the spatial coordinates, layout information of the document entities, and the image vector representations of the pages is used to extract the user-defined attributes from the relevant document pages. First attribute values associated with the user-defined attributes are aggregated from the pages of one of the relevant documents into a single record. Second attribute values associated with the user-defined attributes are aggregated across the relevant documents. Aggregated records, including a first and second attribute, are written to a database.

公开(公告)号：US20230377214A1

公开(公告)日：2023-11-23

申请号：US18320857

申请日：2023-05-19

Applicant: DISNEY ENTERPRISES, INC. ,  ETH Zürich (Eidgenössische Technische Hochschule Zürich)

Inventor： Manuel Jakob KANSY ,  Anton Julien RAËL ,  Jacek Krzysztof NARUNIEC ,  Christopher Richard SCHROERS ,  Romann Matthew WEBER

IPC: G06T11/00 ,  G06T5/00 ,  G06V40/16 ,  G06V10/82

CPC classification number: G06T11/00 ,  G06T5/002 ,  G06V40/171 ,  G06V10/82 ,  G06T2210/32 ,  G06T2207/20081 ,  G06V2201/10 ,  G06T2207/30201

Abstract: One embodiment of the present invention sets forth a technique for performing identity-preserving image generation. The technique includes converting an identity image depicting a facial identity into an identity embedding. The technique further includes generating a combined embedding based on the identity embedding and a diffusion iteration identifier. The technique further includes converting, using a neural network and based on the combined embedding, a first input image that includes first noise into a first predicted image depicting one or more facial features that include one or more first facial identity features, wherein the one or more first facial identity features correspond to one or more respective second facial identity features of the identity image and are based at least on the identity embedding.

公开(公告)号：US11810020B2

公开(公告)日：2023-11-07

申请号：US16907278

申请日：2020-06-21

Applicant: Olive Seed Industries, LLC

Inventor： Christine Soule ,  Charles H. Cella ,  Richard Spitz

IPC: G06Q30/02 ,  H04W4/024 ,  H04W4/33 ,  H04W4/12 ,  H04W4/029 ,  H04W4/021 ,  G06Q30/0251 ,  G06Q30/0217 ,  H04W4/10 ,  G06N20/00 ,  G06Q30/0279 ,  G01C21/20 ,  G06Q30/0282 ,  G06F16/953 ,  G06Q10/047 ,  G06Q30/0214 ,  G06Q30/0207 ,  G06Q50/00 ,  G06T11/00 ,  H04N21/2187 ,  H04N7/15 ,  G06T5/00 ,  G06T11/60 ,  G06F16/435 ,  G06F16/438 ,  G06F3/0482 ,  G06Q30/0201 ,  H04L9/40 ,  H04L67/12 ,  G06F3/01 ,  G06Q30/0203 ,  G06F16/954 ,  G06Q20/20 ,  H04W4/80 ,  H04W12/08 ,  G06F16/587 ,  G06F16/9535 ,  H04W12/06 ,  H04W12/084 ,  G06V20/20 ,  G06V20/52 ,  G06V40/16 ,  H04L67/50 ,  G06Q50/26 ,  G06K7/14 ,  H04W12/64

CPC classification number: G06Q30/0279 ,  G01C21/206 ,  G06F3/013 ,  G06F3/0482 ,  G06F16/435 ,  G06F16/438 ,  G06F16/587 ,  G06F16/953 ,  G06F16/954 ,  G06F16/9535 ,  G06N20/00 ,  G06Q10/047 ,  G06Q20/20 ,  G06Q30/0201 ,  G06Q30/0203 ,  G06Q30/0207 ,  G06Q30/0214 ,  G06Q30/0217 ,  G06Q30/0224 ,  G06Q30/0236 ,  G06Q30/0261 ,  G06Q30/0267 ,  G06Q30/0271 ,  G06Q30/0281 ,  G06Q30/0282 ,  G06Q50/01 ,  G06T5/005 ,  G06T11/00 ,  G06T11/60 ,  G06V20/20 ,  G06V20/52 ,  G06V40/16 ,  G06V40/176 ,  H04L63/0861 ,  H04L67/12 ,  H04L67/535 ,  H04N7/15 ,  H04N21/2187 ,  H04W4/021 ,  H04W4/024 ,  H04W4/029 ,  H04W4/10 ,  H04W4/12 ,  H04W4/33 ,  H04W4/80 ,  H04W12/068 ,  H04W12/08 ,  H04W12/084 ,  G06K7/1417 ,  G06Q50/26 ,  G06V2201/10 ,  H04W12/64

Abstract: A method for developing content for a personalized non-profit venue experience using a mobile computing device, comprising: providing an interface for management of a set of multimedia assets; receiving a mapping of multimedia assets to a set of locations on a site plan for the non-profit venue; receiving metadata for the set of multimedia assets; receiving personalized interest data indicating personal philanthropic interests of a visitor to the non-profit venue; and applying a machine learning algorithm to analyze the metadata and the personalized interest data to provide, to a mobile computing device, a selection of a multimedia asset from the set of multimedia assets for consumption by the visitor.

公开(公告)号：US20230343066A1

公开(公告)日：2023-10-26

申请号：US18305047

申请日：2023-04-21

Applicant: Fluke Corporation

Inventor： Matthew F. Schmidt ,  Michael D. Stuart ,  Seyed Navid Roohani Isfahani ,  Shreyas Shivaram Shastry ,  Dileepa Prabhakar ,  Ronald Ainsworth

IPC: G06V10/74 ,  G06V10/143 ,  G06V10/40 ,  G06V20/60 ,  G06T7/73 ,  G06T7/62 ,  G06T7/50

CPC classification number: G06V10/761 ,  G06V10/143 ,  G06V10/40 ,  G06V20/60 ,  G06T7/73 ,  G06T7/62 ,  G06T7/50 ,  G06V2201/10 ,  G06T2207/10048 ,  G06T2207/20081

Abstract: Methods and apparatuses that utilize machine learning techniques to identify maintenance assets using sets of machine-health diagnostic images and link individual machine-health diagnostic images to the identified maintenance assets are described. The sets of machine-health diagnostic images may include a set of thermal images, a set of visible-light images, and/or a set of acoustic images. An identified maintenance asset may comprise an individual machine associated with a unique asset identifier. A diagnostic image linking system may acquire machine-health diagnostic images, apply object detection and other computer vision techniques to identify a particular machine within the machine-health diagnostic images, determine machine properties for the particular machine, generate a feature vector using the machine properties, select machine learning models corresponding with maintenance assets, generate predicted answers using the machine learning models, and generate an asset identifier for the particular machine based on the predicted answers.

公开(公告)号：US20230334874A1

公开(公告)日：2023-10-19

申请号：US17722127

申请日：2022-04-15

Applicant: GM Cruise Holdings LLC

Inventor： Yi Zhang ,  Xingxing Huang ,  Gia Tri Nguyen

IPC: G06V20/58 ,  G06V10/60 ,  G06V10/82 ,  G06V10/774 ,  G06V10/22

CPC classification number: G06V20/584 ,  G06V10/60 ,  G06V10/82 ,  G06V10/7747 ,  G06V10/22 ,  G06V2201/10 ,  B60R11/04

Abstract: The disclosed technology provides solutions for improving perception systems and in particular for improving perception systems of autonomous vehicles (AVs). A process of the disclosed technology can provide solutions for improving vehicle blinker detection/identification. In some approaches, blinker detection/identification can include steps for receiving a set of image frames, identifying image areas in the set of image frames, corresponding with a light source of the vehicle, and determining a blinker state associated with the vehicle. Systems and machine-readable media are also provided.

公开(公告)号：US11785300B2

公开(公告)日：2023-10-10

申请号：US17674339

申请日：2022-02-17

Applicant: Roku, Inc.

Inventor： Purushottam Narayana ,  Andre Goddard Rosa

IPC: H04N21/45 ,  H04N21/458 ,  G06V20/40 ,  H04N21/4363 ,  H04N21/44 ,  H04N21/431 ,  H04N21/81

CPC classification number: H04N21/458 ,  G06V20/44 ,  G06V20/48 ,  H04N21/4312 ,  H04N21/43635 ,  H04N21/44008 ,  H04N21/812 ,  G06V2201/10

Abstract: Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for ad insertion by a display device coupled to a media device via a high-definition media interface (HDMI) connection, where the media device provides media content and/or a control signal. When the media device pauses the media content, the display device can determine that a pause event has occurred and insert an ad shown on the display device. Further, some embodiments include determining the context and/or content of the media content that is paused, and determining an ad that is customized to the determined context and/or content to be displayed on the display device. In some embodiments, the display device can determine additional information from the control signal that may also be used to determine the ad to be displayed on the display device.

公开(公告)号：US11782979B2

公开(公告)日：2023-10-10

申请号：US17114922

申请日：2020-12-08

Applicant: Alibaba Group Holding Limited

Inventor： Yiliang Lyu ,  Mingqian Tang ,  Zhen Han ,  Yulin Pan

IPC: G06F16/73 ,  G11B27/10 ,  G06F16/71 ,  G06F40/30 ,  G06V20/40

CPC classification number: G06F16/73 ,  G06F16/71 ,  G06F40/30 ,  G06V20/41 ,  G06V20/49 ,  G11B27/10 ,  G06V2201/10

Abstract: Embodiments of the disclosure provide methods and apparatuses for video searches and methods and apparatuses for index construction. In one embodiment, the method comprises: upon receiving a search request input by a user to search for a target video, processing, based on a pre-configured algorithm, multimodal search data for the target video included in the search request; providing a processing result of the multimodal search data with regard to a corresponding pre-constructed index to search to obtain the target video.