公开(公告)号：US12038977B2

公开(公告)日：2024-07-16

申请号：US17958728

申请日：2022-10-03

Applicant: Google LLC

Inventor： Abhanshu Sharma ,  David Petrou ,  Matthew Sharifi

IPC: G06F16/903 ,  G06F3/04842 ,  G06F3/04883 ,  G06F16/58 ,  G06F16/9032 ,  G06V10/764 ,  G06V10/82 ,  G06V20/20 ,  G06V20/62 ,  G06V20/70 ,  G06V30/10

CPC classification number: G06F16/90335 ,  G06F3/04842 ,  G06F3/04883 ,  G06F16/5866 ,  G06F16/90324 ,  G06V10/764 ,  G06V10/82 ,  G06V20/20 ,  G06V20/63 ,  G06V20/70 ,  G06V30/10 ,  G06V2201/10

Abstract: Methods, systems, and apparatus for receiving a query image and a user tap location, processing the received query image based on the user tap location, identifying one or more entities associated with the processed query image and in response to receiving (i) the query image, and (ii) the user tap location, providing information about the identified one or more of the entities.

公开(公告)号：US12026961B2

公开(公告)日：2024-07-02

申请号：US17414838

申请日：2019-11-27

Applicant: Volkswagen Aktiengesellschaft

Inventor： Thorben Günzel

IPC: G06V20/59 ,  B60W40/02 ,  B60W40/08 ,  B60W50/14 ,  G06Q30/0242 ,  G06Q30/0272 ,  G06V20/58 ,  G06V40/19 ,  G09F15/00

CPC classification number: G06V20/597 ,  B60W40/02 ,  B60W40/08 ,  B60W50/14 ,  G06Q30/0242 ,  G06Q30/0272 ,  G06V20/58 ,  G06V40/19 ,  B60W2420/54 ,  B60W2540/225 ,  G06V2201/10 ,  G09F15/0006

Abstract: The invention relates to a method for monitoring a passenger of a vehicle in which the geographic position of the vehicle is recorded, and a viewing direction of the passenger is recorded by means of a eye-tracking device. A data memory is accessed in which objects and geographic positions assigned to them are saved and, by using the recorded geographic position of the vehicle, it is detected whether one of the objects is located in the environment of the vehicle, and whether the object in the environment of the vehicle was perceived by the passenger depending on the recorded viewing direction of the passenger, the recorded geographic position of the vehicle, and the geographic position of the detected object in the environment of the vehicle.

公开(公告)号：US12022170B2

公开(公告)日：2024-06-25

申请号：US18141076

申请日：2023-04-28

Applicant: Rovi Guides, Inc.

Inventor： Vikram Makam Gupta ,  Vishwas Sharadanagar Panchaksharaiah ,  Reda Harb

IPC: H04N21/8549 ,  G06V20/40 ,  H04N21/431 ,  H04N21/44 ,  H04N21/45 ,  H04N21/472

CPC classification number: H04N21/8549 ,  G06V20/46 ,  H04N21/4316 ,  H04N21/44008 ,  H04N21/4532 ,  H04N21/47217 ,  G06V2201/10

Abstract: Systems and methods are provided for displaying personalized preview images during trick-play operations of a media asset based on user profile data and an importance of frames of the media asset. A request from a user to move a slider of a progress bar associated with a media asset is received while the media asset is being generated for display. A scene from the media asset that contains a play position indicated by the slider is identified and a frame that best matches user profile data of the user and importance data for the scene is identified. The identified frame is generated for display as an overlay over the displayed media asset.

公开(公告)号：US12020484B2

公开(公告)日：2024-06-25

申请号：US17434669

申请日：2021-03-03

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Shwetank Choudhary ,  Tanmay Bansal ,  Punuru Sri Lakshmi ,  Chittur Ravichander Karthik ,  Mahender Rampelli ,  Nandini Narayanaswamy ,  Praveen Bangre Prabhakar Rao ,  Dwaraka Bhamidipati Sreevatsa

IPC: G06V20/40 ,  G06V10/44 ,  G06V10/74 ,  G06V10/762 ,  G06V10/82

CPC classification number: G06V20/48 ,  G06V10/454 ,  G06V10/761 ,  G06V10/762 ,  G06V20/46 ,  G06V10/82 ,  G06V2201/10

Abstract: Methods and systems for grouping of media based on similarities between features of media data are provided. A method of managing a plurality of images may include: identifying a threshold distance for clustering the plurality of images based on a degree of similarity between the plurality of images; extracting a plurality of feature vectors corresponding to the plurality of images; and generating at least one cluster comprising at least two images among the plurality of images, based on cosine distances between feature vectors corresponding to the at least two images being less than the threshold distance.

公开(公告)号：US20240202989A1

公开(公告)日：2024-06-20

申请号：US18067878

申请日：2022-12-19

Applicant: Adobe Inc.

Inventor： Ethan Tseng ,  Zhihao Xia ,  Yifei Fan ,  Xuaner Zhang ,  Peter Merrill ,  Lars Jebe ,  Jiawen Chen

IPC: G06T11/00 ,  G06T11/60 ,  G06V10/77 ,  G06V10/774 ,  G06V10/82 ,  G06V20/40

CPC classification number: G06T11/001 ,  G06T11/60 ,  G06V10/7715 ,  G06V10/774 ,  G06V10/82 ,  G06V20/46 ,  G06V2201/10

Abstract: Digital content stylization techniques are described that leverage a neural photofinisher to generate stylized digital images. In one example, the neural photofinisher is implemented as part of a stylization system to train a neural network to perform digital image style transfer operations using reference digital content as training data. The training includes calculating a style loss term that identifies a particular visual style of the reference digital content. Once trained, the stylization system receives a digital image and generates a feature map of a scene depicted by the digital image. Based on the feature map as well as the style loss, the stylization system determines visual parameter values to apply to the digital image to incorporate a visual appearance of the particular visual style. The stylization system generates the stylized digital image by applying the visual parameter values to the digital image automatically and without user intervention.

公开(公告)号：US12014553B2

公开(公告)日：2024-06-18

申请号：US17450914

申请日：2021-10-14

Applicant: Tesla, Inc.

Inventor： Ashok Kumar Elluswamy ,  Matthew Bauch ,  Christopher Payne ,  Andrej Karpathy ,  Dhaval Shroff ,  Arvind Ramanandan ,  James Robert Howard Hakewill

IPC: G06V20/56 ,  G05D1/00 ,  G06F18/214 ,  G06N20/00 ,  G06T7/20 ,  G06V10/764 ,  G06V10/82

CPC classification number: G06V20/588 ,  G05D1/0214 ,  G05D1/0221 ,  G05D1/0223 ,  G05D1/0231 ,  G06F18/214 ,  G06N20/00 ,  G06T7/20 ,  G06V10/764 ,  G06V10/82 ,  G06T2207/20076 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30241 ,  G06T2207/30256 ,  G06V2201/10

Abstract: A processor coupled to memory is configured to receive image data based on an image captured by a camera of a vehicle. The image data is used as a basis of an input to a trained machine learning model trained to predict a three-dimensional trajectory of a machine learning feature. The three-dimensional trajectory of the machine learning feature is provided for automatically controlling the vehicle.

公开(公告)号：US12014542B2

公开(公告)日：2024-06-18

申请号：US17120525

申请日：2020-12-14

Applicant: Google LLC

Inventor： Sanketh Shetty ,  Tomas Izo ,  Min-Hsuan Tsai ,  Sudheendra Vijayanarasimhan ,  Apostol Natsev ,  Sami Abu-El-Haija ,  George Dan Toderici ,  Susana Ricco ,  Balakrishnan Varadarajan ,  Nicola Muscettola ,  WeiHsin Gu ,  Weilong Yang ,  Nitin Khandelwal ,  Phuong Le

IPC: G06K9/00 ,  G06F16/783 ,  G06V20/40

CPC classification number: G06V20/41 ,  G06F16/7834 ,  G06V20/46 ,  G06V20/47 ,  G06V20/49 ,  G06V2201/10

Abstract: A computer-implemented method for selecting representative frames for videos is provided. The method includes receiving a video and identifying a set of features for each of the frames of the video. The features including frame-based features and semantic features. The semantic features identifying likelihoods of semantic concepts being present as content in the frames of the video. A set of video segments for the video is subsequently generated. Each video segment includes a chronological subset of frames from the video and each frame is associated with at least one of the semantic features. The method generates a score for each frame of the subset of frames for each video segment based at least on the semantic features, and selecting a representative frame for each video segment based on the scores of the frames in the video segment. The representative frame represents and summarizes the video segment.

公开(公告)号：US20240196000A1

公开(公告)日：2024-06-13

申请号：US18493874

申请日：2023-10-25

Applicant: CANON KABUSHIKI KAISHA

Inventor： KIYOSHI IWABUCHI ,  KOJI OKAWA

IPC: H04N19/46 ,  G06V20/40 ,  H04N19/142 ,  H04N19/167 ,  H04N19/172 ,  H04N19/177 ,  H04N19/23

CPC classification number: H04N19/46 ,  G06V20/41 ,  H04N19/142 ,  H04N19/167 ,  H04N19/172 ,  H04N19/177 ,  H04N19/23 ,  G06V2201/10

Abstract: A video distribution apparatus includes an object detection unit configured to execute object detection processing with respect to a video indicated by video data obtained by the image capturing unit; metadata addition unit configured to add information related to an object obtained by the object detection unit, as metadata, to encoded data of a corresponding frame of the video, and a control unit configured to control the metadata addition unit based on a result of the detection processing executed by the object detection unit, wherein in a case where the result of the detection processing executed by the object detection unit indicates a disappearance of the object, the control unit controls the metadata addition unit to add metadata indicating the disappearance of the object also to a frame that follows the corresponding frame and satisfies a predetermined condition.

公开(公告)号：US12009015B2

公开(公告)日：2024-06-11

申请号：US17704060

申请日：2022-03-25

Applicant: Ready Set, Inc.

Inventor： John Gargiulo ,  Sambou Makalou

IPC: G11B27/036 ,  G06Q30/0241 ,  G06V10/74 ,  G06V20/40 ,  G11B27/00 ,  G11B27/031 ,  G11B27/34

CPC classification number: G11B27/036 ,  G06Q30/0276 ,  G06V10/761 ,  G11B27/002 ,  G11B27/34 ,  G06V2201/10

Abstract: According to one aspect, a computer-implemented method for automatically generating a video advertisement is provided. The method includes obtaining one or more attributes relating to a video advertisement. The method includes obtaining a template, wherein the template comprises one or more blocks, wherein each block of the one or more blocks comprises one or more placeholders corresponding to one or more types of media assets. The method includes identifying, in a first block of the one or more blocks in the template, a first placeholder corresponding to a first type of media asset. The method includes selecting a first media asset from a first media library based on first metadata associated with the first media asset, the one or more attributes, and the first type of media asset. The method includes generating, using a rendering engine, a video advertisement, wherein the generated video advertisement comprises the first asset. The method includes outputting the generated video advertisement.

公开(公告)号：US20240185835A1

公开(公告)日：2024-06-06

申请号：US18076144

申请日：2022-12-06

Applicant: Hillming Company Limited

Inventor： Hillming LI

IPC: G10L13/08 ,  G06Q20/36 ,  G06V10/764 ,  G06V40/70

CPC classification number: G10L13/08 ,  G06Q20/3674 ,  G06V10/764 ,  G06V40/70 ,  G06V2201/10

Abstract: A system for assisting the blind in financial management is used for mobile phones, computers, and other communication terminals to operate without relying on eyesight, and dealing with related commodity transactions, online shopping, taxi service, food delivery, takeaway order, fee payment, membership services, purchasing services, sending red envelopes, buying and selling services, leasing services, payment, collection, transfer, refund, currency exchange, account inquiry, e-wallet management, stock securities investment, foreign exchange fund trading, futures real estate and/or other related finance and other mobile banking services.