公开(公告)号：WO2021150033A1

公开(公告)日：2021-07-29

申请号：PCT/KR2021/000831

申请日：2021-01-21

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： SEO, Chanwon ,  LEE, Youngeun ,  KIM, Eunseo ,  EOM, Myungjin

IPC: G06T5/00 ,  G06N3/04 ,  G06N3/08 ,  G06F3/04845 ,  G06K9/00624 ,  G06K9/6201 ,  G06K9/6256 ,  G06T2200/24 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T5/001

Abstract: An electronic device and a controlling method thereof are provided. An electronic device includes a memory configured to store at least one instruction and a processor configured to execute the at least one instruction and operate as instructed by the at least one instruction. The processor is configured to: obtain a first image; based on receiving a first user command to correct the first image, obtain a second image by correcting the first image; based on the first image and the second image, train a neural network model; and based on receiving a second user command to correct a third image, obtain a fourth image by correcting the third image using the trained neural network model.

公开(公告)号：WO2020210081A1

公开(公告)日：2020-10-15

申请号：PCT/US2020/025903

申请日：2020-03-31

Applicant: FACEBOOK, INC.

Inventor： NAVEH, Barak, R. ,  REYES, James

IPC: G06Q30/02 ,  G06F16/5866 ,  G06K9/00624 ,  G06K9/623 ,  G06K9/6253 ,  G06K9/6262 ,  G06N20/00 ,  G06Q30/0269 ,  G06Q30/0277 ,  G06T7/70

Abstract: An online system may identify content with which a user has an interest. For example, the online system may determine that a user has an interest in the content based on interaction information indicating that the user interacted with the content. In a particular example, the online system may identify image concepts included in the content based on computer vision techniques that recognize the image concepts. The online system may model probabilities that image concepts will appeal to users. Based on the modeled probabilities, the online system may automatically recommend image concepts for inclusion in candidate images, automatically generate candidate images, or assess candidate images to determine a probability of user interaction with the assessed candidate images.

公开(公告)号：WO2021144679A1

公开(公告)日：2021-07-22

申请号：PCT/IB2021/050167

申请日：2021-01-11

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION ,  IBM UNITED KINGDOM LIMITED ,  IBM (CHINA) INVESTMENT COMPANY LIMITED

Inventor： ZHANG, Yang ,  GAN, Chuang ,  WANG, Dakuo

IPC: G10L25/57 ,  G10L25/30 ,  G06K9/00624 ,  G06K9/4628 ,  G06K9/6293 ,  G06N3/08 ,  G11B27/02 ,  H04N5/04

Abstract: Embodiments herein describe an audio forwarding regularizer and an information bottleneck that are used when training a machine learning (ML) system. The audio forwarding regularizer receives audio training data and identifies visually irrelevant and relevant sounds in the training data. By controlling the information bottleneck, the audio forwarding regularizer forwards data to a generator that is primarily related to the visually irrelevant sounds, while filtering out the visually relevant sounds. The generator also receives data regarding visual objects from a visual encoder derived from visual training data. Thus, when being trained, the generator receives data regarding the visual objects and data regarding the visually irrelevant sounds (but little to no data regarding the visually relevant sounds). Thus, during an execution stage, the generator can generate sounds that are relevant to the visual objects while not adding visually irrelevant sounds to the videos.

公开(公告)号：WO2021142387A1

公开(公告)日：2021-07-15

申请号：PCT/US2021/012858

申请日：2021-01-09

Applicant: ADROIT WORLDWIDE MEDIA, INC.

Inventor： SCHUMACHER, Greg ,  HOWARD, Kevin ,  MASLIN, Matt

IPC: G06K9/46 ,  G06F3/14 ,  G06K9/00624 ,  G06Q10/087 ,  G06Q30/0281 ,  H04N5/2252 ,  H04N5/2253 ,  H04N7/183

Abstract: An automated inventory intelligence system and method are provided for tracking the positions of the retail products as they are moved around on a retail shelf. The automated inventory intelligence system includes a dynamic planogram, or dynamogram, that reflects the existing state of inventory on the shelf, thereby enabling the automated inventory intelligence system to automatically and intelligently determine the amount of inventory stocked on the shelf as well as tracking correct pricing information for misplaced inventory items. As such, the dynamogram is configured to enable the automated inventory intelligence system to provide a frictionless shopping environment when products are moved elsewhere by customers.

公开(公告)号：WO2021142113A1

公开(公告)日：2021-07-15

申请号：PCT/US2021/012489

申请日：2021-01-07

Applicant: HOUSE OF SKYE LTD

Inventor： DRYNAN, Skye

IPC: G06Q30/06 ,  H04N21/254 ,  H04N21/8358 ,  G06K19/06037 ,  G06K19/06112 ,  G06K7/1095 ,  G06K7/1417 ,  G06K9/00624 ,  G06N20/00 ,  G06Q10/087 ,  G06Q20/123 ,  G06Q20/3276 ,  G06Q20/384 ,  G06Q30/0222 ,  G06Q30/0226 ,  G06Q30/0623 ,  G06Q30/0633 ,  G06Q30/0643 ,  G06Q50/01 ,  H04N21/23418 ,  H04N21/4532 ,  H04N21/4725 ,  H04N21/47815 ,  H04N21/6582 ,  H04N21/812 ,  H04N21/8586

Abstract: An automated system/method for identifying and enabling viewer selection/purchase of products or services associated with digital content presented on a display device. Products within the digital content are identified and existing product placement data is ascertained. For products that do not include such data, other methodologies, with the assistance of third-party servers, are employed to assess identity and purchase availability. Viewer input designate products to assess or products can be automatically assessed. Viewers initiate purchase of identified products via the display device or other electronic devices controlled by viewers, such as via viewers' smart phones. Various processes for identifying products include use of AI processing, access to data on third-party servers, crowd sourcing and other methodologies. Various techniques for selecting products for purchases are employed including employing 3D codes (e.g., QR codes) alongside presented products to enable other portable electronic devices to facilitate purchase. Digital representations of the selected products (i.e., of real- world products) may be purchased or licensed for use within the digital realm. Other features are described.

公开(公告)号：WO2021194755A1

公开(公告)日：2021-09-30

申请号：PCT/US2021/021892

申请日：2021-03-11

Applicant: SNAP INC.

Inventor： MOURKOGIANNIS, Celia Nicole

IPC: H04L12/58 ,  G06F3/0488 ,  G06F2203/04808 ,  G06F3/04817 ,  G06F3/0482 ,  G06F3/04845 ,  G06F3/04883 ,  G06K9/00624 ,  H04L51/046 ,  H04L51/10 ,  H04N5/232935 ,  H04N5/272

Abstract: Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing a program and method for displaying augmented reality content. The program and method provide for displaying, within a messaging application running on a device, a first user interface for viewing a media content item; receiving user input via the first user interface, the user input corresponding to a predefined touch gesture; and in response to receiving the user input, switching, within the messaging application, from the first user interface to a second user interface in which a camera of the device is activated to capture an image, and displaying, via the second user interface, a resized version of the media content item with the image.

公开(公告)号：WO2021145961A1

公开(公告)日：2021-07-22

申请号：PCT/US2020/062101

申请日：2020-11-24

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC

Inventor： SOMMERLADE, Eric Chris Wolfgang ,  LIU, Yang ,  NEOFYTOU, Alexandros ,  SENGUPTA, Sunando

IPC: G10L25/51 ,  G10L25/30 ,  G06N3/04 ,  G06N3/08 ,  G10L25/57 ,  G06K9/00 ,  G06T11/00 ,  G10L21/10 ,  G06K9/00624 ,  G06K9/4628 ,  G06K9/6256 ,  G06K9/6268 ,  G06K9/6271 ,  G06N3/0454 ,  G06N3/0472 ,  H04N5/272 ,  H04N7/141

Abstract: A computing system includes an encoder that receives an input image and encodes the input image into real image features, a decoder that decodes the real image features into a reconstructed image, a generator that receives first audio data corresponding to the input image and generates first synthetic image features from the first audio data, and receives second audio data and generates second synthetic image features from the second audio data, a discriminator that receives both the real and synthetic image features and determines whether a target feature is real or synthetic, and a classifier that classifies a scene of the second audio data based on the second synthetic image features.

公开(公告)号：WO2021123945A1

公开(公告)日：2021-06-24

申请号：PCT/IB2020/060059

申请日：2020-10-27

Applicant: EVERSEEN LIMITED

Inventor： ALLEN, Joe

IPC: G06Q30/02 ,  G03B17/54 ,  G06K9/00624 ,  G06Q30/0252 ,  H04N9/3179 ,  H04N9/3194

Abstract: A system for automatically displaying output information on a display surface based on activities in a target environment includes an image capturing device for capturing data of the target environment in real-time, a processing unit for processing the data to determine a location for displaying the output information, and determine a content of the output information, and a video output unit for displaying the output information on the display surface. The video output unit is configured to rotate in a 360° manner, and wherein an angle of rotation of the video output unit is controlled by the processing unit. The image capturing device further captures the output information displayed on the display surface in real time, and provides feedback data to the processing unit in real-time, so as to enable the processing unit to control a focus, a direction, and the output information displayed on the video output unit.

公开(公告)号：WO2021231839A1

公开(公告)日：2021-11-18

申请号：PCT/US2021/032415

申请日：2021-05-14

Applicant: CCC INFORMATION SERVICES INC.

Inventor： HANTEHZADEH, Neda

IPC: G06K9/20 ,  G06K9/36 ,  G06Q40/08 ,  G06T7/00 ,  G06K9/00624 ,  G06K9/46 ,  G06K9/6217 ,  G06N3/0445 ,  G06N3/0454 ,  G07C5/008

Abstract: A method and system is described which attempts to address the technical problems involved in analyzing images using advanced computer systems and making decisions about the future of a damaged automobile based on the images. The process involves determining, based on a combination of the respective RNN outputs of the respective instances of a RNN, one of: (i) the damaged vehicle is the total loss, or (ii) the damaged vehicle is to be repaired, the determination being a TLR decision; and providing an indication of the TLR decision to at least one of a user interface or an application.

公开(公告)号：WO2021196836A1

公开(公告)日：2021-10-07

申请号：PCT/CN2021/073321

申请日：2021-01-22

Applicant: 北京沃东天骏信息技术有限公司 ,  北京京东世纪贸易有限公司

Inventor： 周鹏 ,  王云涛 ,  周默

IPC: G06Q10/08 ,  G06F16/583 ,  G06K9/00624 ,  G06Q10/083 ,  G06T2207/10004 ,  G06T2207/20081 ,  G06T7/75

Abstract: 本申请实施例公开了用于定位快递包裹的方法和装置。该方法的一具体实施方式包括：接收快递定位请求，其中，快递定位请求用于从呈现有快递包裹的快递图像中定位目标快递包裹对应的快递单，快递定位请求包括快递信息；查找预先存储的、与快递信息对应的快递单的位置信息；利用位置信息，生成快递定位结果图像，其中，快递定位结果图像包括定位标识，定位标识用于从快递图像中指示出目标快递包裹对应的快递单；输出快递定位结果图像。该实施方式提高了快递包裹定位效率，从而提高了快递配送效率。