-
公开(公告)号:US20250069247A1
公开(公告)日:2025-02-27
申请号:US18943520
申请日:2024-11-11
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor: Haoyu REN , Mostafa EL-KHAMY , Jungwon LEE , Hai SU , Qingfeng LIU
Abstract: Methods and systems for performing video prediction, including obtaining an input frame from among a plurality of frames included in an input video; extracting a first feature map by providing the input frame to a first plurality of feature extraction layers and a first strided convolutional layer included in an encoder; providing the first feature map and at least one neighboring first feature map corresponding to at least one neighboring frame to a first fusion module included in the encoder; fusing the first feature map with the at least one neighboring first feature map to generate a fused first feature map using the first fusion module; generating a prediction corresponding to the input frame based on the fused first feature map using a decoder; and performing a video prediction task using the prediction.
-
公开(公告)号:US20220188984A1
公开(公告)日:2022-06-16
申请号:US17215529
申请日:2021-03-29
Applicant: Samsung Electronics Co., Ltd.
Inventor: Mojtaba RAHMATI , Dongwoon BAI , Jungwon LEE
Abstract: A method and system are provided. The method includes obtaining a difference map between a reference frame and a non-reference frame, estimating a noise variance of the obtained difference map, obtaining merging weights based on the estimated noise variance and the obtained different map, and merging the non-reference frame with the reference frame using the obtained merging weights.
-
公开(公告)号:US20220092383A1
公开(公告)日:2022-03-24
申请号:US17173107
申请日:2021-02-10
Applicant: Samsung Electronics Co., Ltd.
Inventor: Fatih CAKIR , Mostafa EL-KHAMY , Jungwon LEE
IPC: G06N3/04
Abstract: A method and system are provided. The method includes topologically sorting layers of a neural network, selecting a quantization process that utilizes a quantization of a previous layer, and determining, with the selected quantization process, a quantization mode of one layer in the neural network based on the quantization of a previous layer.
-
公开(公告)号:US20220004827A1
公开(公告)日:2022-01-06
申请号:US17241848
申请日:2021-04-27
Applicant: Samsung Electronics Co., Ltd.
Inventor: Qingfeng LIU , Mostafa EL-KHAMY , Jungwon LEE , Behnam Babagholami MOHAMADABADI
Abstract: A method and system for training a neural network are provided. The method includes receiving an input image, selecting at least one data augmentation method from a pool of data augmentation methods, generating an augmented image by applying the selected at least one data augmentation method to the input image, and generating a mixed image from the input image and the augmented image.
-
公开(公告)号:US20200265561A1
公开(公告)日:2020-08-20
申请号:US16794583
申请日:2020-02-19
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor: Sanguk PARK , Bongsoo JUNG , Changho KIM , Jungwon LEE , Donghyun YEOM
IPC: G06T5/00
Abstract: Disclosed is an electronic device including a memory and a processor electrically connected with the memory. The memory stores instructions that, when executed, cause the processor to control the electronic device to: obtain information about a maximum value of brightness of image content based on metadata of the image content, to perform tone mapping on at least one or more frames corresponding to a preview image of the image content based on the information about the maximum value of the brightness, and to output the preview image based on the at least one or more frames on which the tone mapping is performed, on a display device.
-
公开(公告)号:US20200052726A1
公开(公告)日:2020-02-13
申请号:US16656971
申请日:2019-10-18
Applicant: Samsung Electronics Co., Ltd.
Inventor: Liangbin LI , Pranav DAYAL , Jungwon LEE , Gennady FEYGIN
Abstract: Apparatuses (and methods of manufacturing same), systems, and methods concerning polyphase digital filters are described. In one aspect, an apparatus is provided, including at least one pair of subfilters, each having symmetric coefficients, and a lattice comprising two adders and feedlines corresponding to each of the at least one pair of subfilters, each having symmetric coefficients. In one aspect, the apparatus is a polyphase finite impulse response (FIR) digital filter, including an interpolator and a decimator, where each of the interpolator and the decimator have at least one pair of subfilters, each having symmetric coefficients, and a lattice comprising two adders and feedlines corresponding to each of the at least one pair of subfilters, each having symmetric coefficients.
-
7.
公开(公告)号:US20190173498A1
公开(公告)日:2019-06-06
申请号:US16272722
申请日:2019-02-11
Applicant: Samsung Electronics Co., Ltd.
Inventor: Mostafa EL-KHAMY , Jinhong WU , Jungwon LEE , Inyup KANG
Abstract: Method for decoding signal includes receiving signal, where signal includes at least one symbol; decoding signal in stages, where each at least one symbol of signal is decoded into at least one bit per stage, wherein Log-Likelihood Ratio (LLR) for each at least one bit at each stage is determined, and identified in vector LAPP; performing Cyclic Redundancy Check (CRC) on LAPP, and stopping if LAPP passes CRC; otherwise, determining magnitudes of LLRs in LAPP; identifying K LLRs in LAPP with smallest magnitudes and indexing K LLRs as r={r(1), r(2), . . . , r(K)}; setting Lmax to maximum magnitude of LLRs in LAPP or maximum possible LLR quantization value; setting v=1; generating {tilde over (L)}A(r(k))=LA(r(k))−Lmaxvksign[LAPP(r(k))], for k=1, 2, . . . , K; decoding with {tilde over (L)}A to identify {tilde over (L)}APP, wherein {tilde over (L)}APP is LLR vector; and performing CRC on {tilde over (L)}APP, and stopping if {tilde over (L)}APP passes CRC or v=2K-1; otherwise, incrementing v and returning to generating {tilde over (L)}A(r(k)).
-
公开(公告)号:US20190109604A1
公开(公告)日:2019-04-11
申请号:US16215928
申请日:2018-12-11
Applicant: Samsung Electronics Co., Ltd.
Inventor: Mostafa EL-KHAMY , Hsien-Ping LIN , Jungwon LEE
Abstract: An apparatus and a method. The apparatus includes a receiver including an input for receiving a codeword of length mj, where m and j are each an integer; a processor configured to determine a decoding node tree structure with mj leaf nodes for the received codeword and receive an integer i indicating a level at which parallelism of order m is applied to the decoding node tree structure; and m successive cancellation decoders (SCDs) configured to decode, in parallel, each child node in the decoding node tree structure at level i.
-
9.
公开(公告)号:US20180192310A1
公开(公告)日:2018-07-05
申请号:US15455979
申请日:2017-03-10
Applicant: Samsung Electronics Co., Ltd.
Inventor: Binnan ZHUANG , Hongbing CHENG , Jungwon LEE
IPC: H04W24/08 , H04B7/06 , H04L27/26 , H04B17/345
CPC classification number: H04B17/345 , H04B7/0626 , H04B17/309 , H04L25/067 , H04L27/2657 , H04L27/2675 , H04L27/2679
Abstract: A method and apparatus are provided. The method includes receiving, by at least one antenna of a receiver, at least one signal from a transceiver, detecting at least one data symbol within the at least one signal, determining a probability associated with the at least one detected data symbol, determining channel state information (CSI) of at least one channel between the transceiver and the at least one antenna of the receiver, and estimating a common phase error (CPE) of the at least one signal based on the probabilities associated with the at least one detected data symbol and the CSI of the at least one channel.
-
公开(公告)号:US20180115351A1
公开(公告)日:2018-04-26
申请号:US15453553
申请日:2017-03-08
Applicant: Samsung Electronics Co., Ltd.
Inventor: Federico PENNA , Hongbing CHENG , Jungwon LEE
IPC: H04B7/0456 , H04L25/03
CPC classification number: H04B7/0456 , H04B7/0469 , H04L25/03949
Abstract: An apparatus and a method. The apparatus includes a singular value decomposition (SVD) processor configured to receive a channel matrix H and output samples y of an optimal precoding matrix for H; a linear phase estimation (LPE) processor connected to the SVD processor and configured to determine a phase estimate {circumflex over (θ)}l of an angle θl of a horizontal discrete Fourier transform (DFT) index l, where l is an integer; and a decision processor connected to the LPE processor and configured to determine a hard estimate of l.
-
-
-
-
-
-
-
-
-