-
公开(公告)号:US11386665B2
公开(公告)日:2022-07-12
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: G06V20/40 , G06F40/166 , G06K9/62 , G11B27/031 , G06V10/46 , G06V10/50
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:US11676016B2
公开(公告)日:2023-06-13
申请号:US16899841
申请日:2020-06-12
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor: Anant Baijal , Vivek Agarwal , Jayoon Koo
IPC: G06N3/08 , G06N20/20 , G06F18/20 , G06F18/2415 , G06F18/2431
CPC classification number: G06N3/08 , G06F18/2415 , G06F18/2431 , G06F18/285 , G06N20/20
Abstract: A method of selecting an artificial intelligence (AI) model based on input data to select an AI model capable of correctly obtaining a result corresponding to data to be classified, e.g., a classification result indicating one of at least one class, from among a plurality of AI models, and a display device for performing the method.
-
公开(公告)号:US10750239B2
公开(公告)日:2020-08-18
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: H04N7/10 , H04N21/442 , H04N21/258 , H04N21/45 , H04N21/466 , H04N21/25
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:US11250542B2
公开(公告)日:2022-02-15
申请号:US17026926
申请日:2020-09-21
Applicant: Samsung Electronics Co., Ltd.
Inventor: Anant Baijal , Vivek Agarwal
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:US11640650B2
公开(公告)日:2023-05-02
申请号:US17030905
申请日:2020-09-24
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor: Anant Baijal , Vivek Agarwal , Jayoon Koo
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.
-
公开(公告)号:US11625560B2
公开(公告)日:2023-04-11
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: G06F16/732 , G06K9/62 , 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:US11482000B2
公开(公告)日:2022-10-25
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
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.
-
-
-
-
-
-