-
公开(公告)号：US20220121947A1
公开(公告)日：2022-04-21
申请号：US17465439
申请日：2021-09-02
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor： Qian LOU , Yilin SHEN , Hongxia JIN
Abstract: A method of a server device is provided. The method of a server device includes retrieving a prediction input and a prediction setting, replacing at least one non-linear activation channel in a neural network with at least one replacement channel based on the received prediction setting, generating a prediction based on the received prediction input based on the neural network with the at least one replacement channel, and outputting the generated prediction.
-
公开(公告)号：US20250166339A1
公开(公告)日：2025-05-22
申请号：US18955003
申请日：2024-11-21
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor： Wenbo LI , Yilin SHEN , Hongxia JIN
Abstract: A method includes generating a pair of features of a current frame by inputting the current frame into a first cross-collaborative consistency learning (C3L) model, the current frame comprising a red-green-blue (RGB) image and a thermal image; generating a pair of denoised features by inputting the of pair of features of the current frame and one or more pairs of features of past frames into a denoised memory read (DMR) model; generating an updated pair of denoised features by inputting the pair of denoised features into a second C3L model, the updated pair of denoised features comprising an updated RGB image feature and an updated thermal feature; and generating a segmentation mask by inputting the updated pair of features into a segmentation head.
-
公开(公告)号：US20240119077A1
公开(公告)日：2024-04-11
申请号：US18368353
申请日：2023-09-14
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor： Shangqian GAO , Burak UZKENT , Yilin SHEN , Hongxia JIN
IPC: G06F16/33 , G06F16/583 , G06N3/0985
CPC classification number: G06F16/334 , G06F16/5846 , G06N3/0985
Abstract: A method of performing a multimodal tasks by using a multimodal model that includes a text encoder and a vision encoder, may include obtaining a text feature from the query via the text encoder; obtaining an image feature from the one or more input images via the vision encoder; and outputting a response to the query based on similarity between the text feature and the image feature, wherein weights vectors of the text encoder and the vision encoder are pruned and shared according to a sharing vector and a pruning vector that are generated by a hypernetwork, and wherein the hypernetwork and the multimodal model are jointly trained to minimize at least one of a difference between the weight vectors in the text encoder and the vision encoder, a difference between the weight vectors in different layers of the text encoder, and a number of parameters in the multimodal model.
-
公开(公告)号：US20180077168A1
公开(公告)日：2018-03-15
申请号：US15264116
申请日：2016-09-13
Applicant: Samsung Electronics Co., Ltd.
Inventor： Yilin SHEN , Pengfei HU , Hongxia JIN
CPC classification number: H04L63/107 , G06F1/3206 , G06F1/3212 , G06F1/3215 , G06F1/325 , G06F1/3296 , H04L43/106 , H04L43/16 , H04L63/0428 , H04L63/0492 , H04L63/06 , H04L63/083 , H04L63/0876 , H04W4/021 , H04W4/80 , H04W12/00503 , H04W12/02 , H04W12/04 , H04W12/06 , Y02D10/174
Abstract: An accurate distance between two devices can be determined in continuous and secure manner using modulated audible signals containing time-based information. This calculated distance can be used to lock and unlock one of the two devices such that if one of the devices, such as a smart phone or smart watch, is beyond a pre-configured distance from the other device, such as a laptop or tablet, the other device locks and may display a message to the user. The modulated messages contain time difference data of audible signal emission and receiving times which are used by each device to calculate an accurate estimate of the distance between the two devices.
-
-
-
Search Results
14
records
(took 0.016 seconds)
