-
1.
公开(公告)号:US20240054611A1
公开(公告)日:2024-02-15
申请号:US18492234
申请日:2023-10-23
Applicant: Samsung Electronics Co., Ltd.
Inventor: Biplab Ch Das , Kiran Nanjunda Iyer , Shouvik Das , Himadri Sekhar Bandyopadhyay
CPC classification number: G06T5/50 , G06T7/10 , G06V10/25 , G06V10/56 , G06T2207/10024 , G06T2207/20084 , G06T2207/20221
Abstract: In a method of encoding of temporal information for stable video instance segmentation and video object detection, a neural network analyzes an input frame of a video to output a prediction template. The prediction template includes either segmentation masks of objects in the input frame or bounding boxes surrounding objects in the input frame. The prediction template is then colour coded by a template generator. The colour coded template, along with a frame subsequent to the input frame, is supplied to a template encoder such that temporal information from the input frame is encoded into the output of the temporal encoder.
-
公开(公告)号:US10958842B2
公开(公告)日:2021-03-23
申请号:US15708550
申请日:2017-09-19
Applicant: Samsung Electronics Co., Ltd.
Inventor: Raushan Kumar , Viswanath Gopalakrishnan , Biplab Chandra Das , Kiran Nanjunda Iyer
IPC: H04N5/232 , H04N1/00 , G06K9/00 , G06K9/62 , G06F3/0488 , G06F16/65 , G06F3/0482 , G06F3/0484 , G06F16/54 , H04N1/32 , H04N101/00
Abstract: A method and an electronic device for displaying images in a multi-dimensional mode based on personalized topics are provided. The method includes generating a plurality of personalized topics based on a plurality of images stored in the electronic device across a predetermined time period, and displaying the plurality of personalized topics along a timeline.
-
公开(公告)号:US09886762B2
公开(公告)日:2018-02-06
申请号:US14808014
申请日:2015-07-24
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor: Kiran Nanjunda Iyer , Raushan Kumar , Satish Lokkoju , Viswanath Gopalakrishnan , Viswanath Veera
CPC classification number: G06T7/143 , G06F17/30268 , G06K9/6276 , G06K2209/27 , G06T7/11 , G06T7/162 , G06T2207/20104
Abstract: The present disclosure relates to image retrieval in an electronic device. An operating method of an electronic device includes determining an object included in an image and a position of extent occupied by the object in the image and retrieving at least one image including the object at the position from among a plurality of images.
-
公开(公告)号:US10521009B2
公开(公告)日:2019-12-31
申请号:US15597442
申请日:2017-05-17
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor: Kiran Nanjunda Iyer , Viswanath Gopalakrishnan , Kapil Soni , Satish Lokkoju
IPC: G06F3/01 , G06F3/0346 , G06F1/16 , G06F3/0354 , G06F3/0362 , G06F3/038
Abstract: A method, which facilitates interaction with virtual reality device, includes receiving a user input via a wearable device; extracting a parameter and a value of the parameter from the user input; transmitting the parameter and the value of the parameter to the VR device; identifying an action corresponding to the parameter and the value; and executing the action.
-
公开(公告)号:US12008037B2
公开(公告)日:2024-06-11
申请号:US17554658
申请日:2021-12-17
Applicant: Samsung Electronics Co., Ltd.
Inventor: Sathish Chalasani , Ujjawal Soni , Kiran Nanjunda Iyer , Shreyasi Das , Samarjeet Sahoo
IPC: G06F16/738 , G06F16/732 , G06F16/74 , G06F16/78 , G06N3/08 , G06V20/40
CPC classification number: G06F16/739 , G06F16/732 , G06F16/743 , G06F16/7867 , G06N3/08 , G06V20/46
Abstract: A method of video search in an electronic device is provided. The method includes extracting a plurality of visual features vectors comprising visual features from a plurality of videos stored in a video database, wherein each visual feature corresponds to a pre-defined moment, generating a temporal map of the plurality of visual feature vectors, generating at least one video tag and at least one time stamp associated with the visual feature vector, storing the at least one video tag, the visual feature vectors and the at least one time stamp for each visual feature in a vector database, receiving a search query from a user for a specific moment in a plurality of videos in the electronic device, running the search query on the vector database, and displaying visual features associated with the specific moments from the plurality of videos.
-
公开(公告)号:US20230131589A1
公开(公告)日:2023-04-27
申请号:US17983119
申请日:2022-11-08
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor: Biplab Chandra DAS , Kiran Nanjunda Iyer , Shouvik Das , Himadri Sekhar Bandyopadhyay
Abstract: A method for segmenting objects in a scene by an electronic device is provided. The method includes inputting at least one input frame of the scene into a pre-trained neural network model, the scene including a plurality of objects; determining a position and a shape of each object of the plurality of objects in the scene using the pre-trained neural network model; determining an array of coefficients for pixels associated with each object of the plurality of objects in the scene using the pre-trained neural network model; and generating a segment mask for each object of the plurality of objects based on the position, the shape, and the array of coefficients for each object of the plurality of objects in the scene.
-
公开(公告)号:US11570367B2
公开(公告)日:2023-01-31
申请号:US17302673
申请日:2021-05-10
Applicant: Samsung Electronics Co., Ltd.
Inventor: Santhosh Kumar Banadakoppa Narayanaswamy , Kiran Nanjunda Iyer , Sai Krishna Kasibhotla , Biplab Ch Das , Moneish Kumar
Abstract: A method for displaying an intelligent zoom recommendation in an electronic device includes displaying a scene comprising a plurality of objects in a preview frame of at least one imaging sensor of the electronic device. The method also includes determining a preference for each of the objects by mapping each of the objects into a preference database of the electronic device. The method further includes determining a position of each of the objects in the preview frame of the at least one imaging sensor of the electronic device. Additionally, the method includes selecting at least one object from the plurality of objects based on the preference and the position of each of the objects. The method also includes displaying at least one graphical indication to zoom the at least one selected object in the preview frame of the at least one imaging sensor of the electronic device.
-
-
-
-
-
-