公开(公告)号：US20190163702A1

公开(公告)日：2019-05-30

申请号：US16203100

申请日：2018-11-28

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jatin GARG ,  Ja-yoon KOO ,  Vivek AGARWAL ,  Ernesto Evgeniy SANCHES SHAYDA

IPC: G06F16/783 ,  G06N3/08 ,  G06K9/00

Abstract: An image display apparatus for automatically determining an image in a video having a best picture of an object selected by a user.

公开(公告)号：US20210104017A1

公开(公告)日：2021-04-08

申请号：US17026926

申请日：2020-09-21

Applicant: Samsung Electronics Co., Ltd.

Inventor： Anant BAIJAL ,  Vivek AGARWAL

IPC: G06T3/40

Abstract: A mosaic generation apparatus includes: a display outputting an image, a memory storing one or more instructions, and a processor configured to execute the one or more instructions stored in the memory to: extract a first feature value from one of a plurality of sub-base areas included in a base image, extract a second feature value from one source image selected from among a plurality of source images, and generate a sub-mosaic corresponding to the one sub-base area using the first feature value and the second feature value.

公开(公告)号：US20200302242A1

公开(公告)日：2020-09-24

申请号：US16765655

申请日：2018-11-12

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Ernesto SANCHES ,  Ja Yoon KOO ,  Vivek AGARWAL ,  Jatin GARG

IPC: G06K9/62 ,  G06F16/732 ,  G06N20/00

Abstract: A server and a control method thereof are provided. The server includes a communicator configured to communicate with an external apparatus; and a processor configured to: receive an image from the external apparatus via the communicator, process the received image by applying a plurality of image analysis models of which an analysis type for the image is different from each other, to the received image, and generate analysis result information about the image respectively corresponding to a plurality of analysis types according to the processing of the received image. With this, more various types of image analysis information may be provided with respect to one image. At least a portion of the analysis of the image, the processing and the generation may be carried out using at least one of a machine learning, a nerve network or a deep learning algorithm as a rule based or artificial intelligence algorithm.

公开(公告)号：US20200160056A1

公开(公告)日：2020-05-21

申请号：US16688265

申请日：2019-11-19

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Vivek AGARWAL ,  Anant BAIJAL ,  Dae Eun HYUN ,  Mi Jeong KWON ,  Yun Joo CHOI

IPC: G06K9/00 ,  G06K9/52 ,  G06T7/11 ,  G06T7/168

Abstract: Disclosed herein is an image processing apparatus and a control method thereof. The image processing apparatus includes communication circuitry, a storage, and a controller configured to control the image processing apparatus to: perform object recognition for recognizing a plurality of objects in first image data stored in the storage, obtain a score inferred through operation processing through a neural network for the recognized plurality of objects, generate second image data based on the obtained score and proximity of the plurality of objects, and perform image processing based on the second image data.

公开(公告)号：US20190200076A1

公开(公告)日：2019-06-27

申请号：US16328055

申请日：2017-07-04

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Ernesto Evgeniy SANCHESSHAYDA ,  Vivek AGARWAL ,  Jatin GARG ,  Min-suk SONG ,  Jae-ook KWON

IPC: H04N21/442 ,  H04N21/466

Abstract: Disclosed is a server apparatus. The server apparatus comprises: a communication unit for receiving, from an external server, multiple first viewing log data for each of a plurality of first users using a first broadcast receiving apparatus and multiple user information of each of the plurality of first users; and a processor for updating a predictive model for predicting, from the viewing log data, the number of users using the broadcast receiving apparatus and user information of each of the users, on the basis of the received multiple first viewing log data and the received multiple user information, wherein, when second viewing log data is received from a second broadcast receiving apparatus through the communication unit, the processor predicts, using the updated predictive model, the number of users using the second broadcast receiving apparatus and user information of each of the users.

公开(公告)号：US20220147870A1

公开(公告)日：2022-05-12

申请号：US17421292

申请日：2020-01-06

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Vivek AGARWAL ,  Jatin GARG ,  Jayoon KOO ,  Dongjin SEO ,  Kwanki AHN ,  Keuntek LEE

IPC: G06N20/00 ,  G06F16/435 ,  H04N21/466

Abstract: An electronic device according to an embodiment of the disclosure includes: a communicator; a memory storing one or more instructions; at least one processor configured to execute the one or more instructions stored in the memory to collect content metadata and user metadata from a plurality of different servers that provide content, obtain a content latent factor including information about similarities between pieces of the content based on characteristics of the content metadata, by using a first learning network model, obtain a user latent factor related to user preferred content information based on characteristics of the user metadata, by using a second learning network model, obtain a user preference score for the content based on the content latent factor and the user latent factor, by using a third learning network model, and provide a recommended content list based on the user preference score.

公开(公告)号：US20200334468A1

公开(公告)日：2020-10-22

申请号：US16960666

申请日：2018-12-20

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Vivek AGARWAL ,  Ja Yoon KOO ,  Ernesto SANCHES ,  Jatin GARG

IPC: G06K9/00 ,  G06K9/62 ,  G06K9/46 ,  G06F40/166 ,  G11B27/031

Abstract: The disclosure relates to an electronic apparatus, a method of controlling the same, and a computer program product, the electronic apparatus including: a memory configured to store an instruction; and a processor configured to execute the instruction to: extract video features of frames from a plurality of frames of video content, extract text features from transcript information of the video content, identify importance scores of the frames based on the video features and the text features, and select a key frame of the video content among the plurality of frames based on the identified importance scores. Thus, it is possible to provide faithful information about content to a user through the video summary considering not only the video features but also the text features.

公开(公告)号：US20210118093A1

公开(公告)日：2021-04-22

申请号：US17030905

申请日：2020-09-24

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Anant BAIJAL ,  Vivek AGARWAL ,  Jayoon KOO

IPC: G06T3/40 ,  G06T7/11 ,  G06T7/174 ,  G06K9/46 ,  G06N3/08

Abstract: Provided are a computing apparatus for constructing a mosaic image and an operation method of the same. The computing apparatus includes: a memory storing one or more instructions; and a processor configured to execute the one or more instructions stored in the memory to: segment an input image into a plurality of sub areas to obtain a plurality of sub area images, extract a feature from each of the plurality of sub area images, generate a plurality of source images respectively corresponding to the plurality of sub areas using an image generation neural network, the image generation neural network using, as a condition, the feature extracted from each of the plurality of sub area images, and combine the plurality of source images respectively corresponding to the plurality of sub areas to generate a mosaic image.