-
公开(公告)号：US20220300803A1
公开(公告)日：2022-09-22
申请号：US17342354
申请日：2021-06-08
Inventor： Hyun-Woo CHO , Jeong-Si KIM , Hong-Soog KIM , Jin-Wuk SEOK , Seung-Tae HONG
Abstract: Disclosed herein are a method for performing a dilated convolution operation using an atypical kernel pattern and a dilated convolutional neural network system using the same. The method for performing a dilated convolution operation includes learning a weight matrix for a kernel of dilated convolution through deep learning, generating an atypical kernel pattern based on the learned weight matrix, and performing a dilated convolution operation on input data by applying the atypical kernel pattern to a kernel of a dilated convolutional neural network.
-
公开(公告)号：US20200351509A1
公开(公告)日：2020-11-05
申请号：US16760609
申请日：2018-10-30
Inventor： Joo-Young LEE , Seung-Hyun CHO , Youn-Hee KIM , Jin-Wuk SEOK , Woong LIM , Jong-Ho KIM , Dae-Yeol LEE , Se-Yoon JEONG , Hui-Yong KIM , Jin-Soo CHOI
IPC: H04N19/42 , G06N3/08 , G06N3/04 , H04N19/136
Abstract: A method and apparatus for image compression using a latent variable are provided. The multiple components of the latent variable may be sorted in order of importance. Through sorting, when the feature information of only some of the multiple components is used, the quality of a reconstructed image may be improved. In order to generate a latent variable, the components of which are sorted in order of importance, learning may be performed in various manners. Also, less important information may be eliminated from the latent variable, and processing, such as quantization, may be applied to the latent variable. Through elimination and processing, the amount of data for the latent variable may be reduced.
-
公开(公告)号：US20190246102A1
公开(公告)日：2019-08-08
申请号：US16270468
申请日：2019-02-07
Inventor： Seung-Hyun CHO , Youn-Hee KIM , Jin-Wuk SEOK , Joo-Young LEE , Woong LIM , Jong-Ho KIM , Dae-Yeol LEE , Se-Yoon JEONG , Hui-Yong KIM , Jin-Soo CHOI , Je-Won KANG , Na-Young KIM
IPC: H04N19/109 , G06N3/04 , H04N19/184 , H04N19/172 , H04N19/176
CPC classification number: H04N19/109 , G06N3/0454 , H04N19/172 , H04N19/176 , H04N19/184
Abstract: Disclosed herein are a video decoding method and apparatus and a video encoding method and apparatus. A virtual frame is generated by a video generation network including a generation encoder and a generation decoder. The virtual frame is used as a reference frame in inter prediction for a target. Further, a video generation network for inter prediction may be selected from among multiple video generation networks, and inter prediction that uses the selected video generation network may be performed.
-
Patent Agency Ranking
14.发明公开公开(公告)号：US20240069875A1
公开(公告)日：2024-02-29
申请号：US18209617
申请日：2023-06-14
Inventor： Jae-Bok PARK , Chang-Sik CHO , Kyung-Hee LEE , Ji-Young KWAK , Seon-Tae KIM , Hong-Soog KIM , Jin-Wuk SEOK , Hyun-Woo CHO
Abstract: Disclosed herein are a neural network model deployment method and apparatus for providing a deep learning service. The neural network model deployment method may include providing a specification wizard to a user, searching for and training a neural network based on a user requirement specification that is input through the specification wizard, generating a neural network template code based on the user requirement specification and the trained neural network, converting the trained neural network into a deployment neural network that is usable in a target device based on the user requirement specification, and deploying the deployment neural network to the target device.
-
公开(公告)号：US20210133626A1
公开(公告)日：2021-05-06
申请号：US16894306
申请日：2020-06-05
Inventor： Jin-Wuk SEOK
Abstract: Disclosed herein are an apparatus and method for optimizing a quantized machine-learning algorithm. The apparatus includes one or more processors and executable memory for storing at least one program executed by the one or more processors. The at least one program sets the learning rate of the quantized machine-learning algorithm using at least one of an Armijo rule and golden search methods, calculates a quantized orthogonal compensation search vector from the search direction vector of the quantized machine-learning algorithm, compensates for the search performance of the quantized machine-learning algorithm using the quantized orthogonal compensation search vector, and calculates an optimized quantized machine-learning algorithm using the learning rate and the quantized machine-learning algorithm, the search performance of which is compensated for.
-
16.发明申请公开(公告)号：US20200175668A1
公开(公告)日：2020-06-04
申请号：US16697585
申请日：2019-11-27
Inventor： Se-Yoon JEONG , Dae-Yeol LEE , Seung-Hyun CHO , Hyunsuk KO , Youn-Hee KIM , Jong-Ho KIM , Jin-Wuk SEOK , Joo-Young LEE , Woong LIM , Hui-Yong KIM , Jin-Soo CHOI
Abstract: Disclosed herein are a method and apparatus for measuring video quality based on a perceptually sensitive region. The quality of video may be measured based on a perceptually sensitive region and a change in the perceptually sensitive region. The perceptually sensitive region includes a spatial perceptually sensitive region, a temporal perceptually sensitive region, and a spatio-temporal perceptually sensitive region. Perceptual weights are applied to a detected perceptually sensitive region and a change in the detected perceptually sensitive region. Distortion is calculated based on the perceptually sensitive region and the change in the perceptually sensitive region, and a result of quality measurement for a video is generated based on the calculated distortion.
-
公开(公告)号：US20200162736A1
公开(公告)日：2020-05-21
申请号：US16684041
申请日：2019-11-14
Inventor： Jin-Wuk SEOK , Hyunsuk KO , Youn-Hee KIM , Jong-Ho KIM , Joo-Young LEE , Woong LIM , Se-Yoon JEONG , Seung-Hyun CHO , Hui-Yong KIM , Jin-Soo CHOI
IPC: H04N19/124 , H04N19/18 , H04N19/184
Abstract: Disclosed herein are a video decoding method and apparatus and a video encoding method and apparatus. In image encoding, encoding using multiple quantization parameters is performed on a transform coefficient. Two quantized coefficients are generated through encoding that uses two quantization parameters. Based on the two quantized coefficients, a quantized coefficient difference is generated. Information about the quantized coefficient difference is transmitted from an encoding apparatus to a decoding apparatus through binary encoding. The information about the quantized coefficient difference may be selectively transmitted. By means of the information about the quantized coefficient difference, a high-quality video may be provided.
-
18.发明申请公开(公告)号：US20190082178A1
公开(公告)日：2019-03-14
申请号：US16084995
申请日：2017-03-30
Inventor： Youn-Hee KIM , Jin-Wuk SEOK , Hui-Yong KIM , Myung-Seok KI , Sung-Chang LIM , Jin-Soo CHOI
IPC: H04N19/119 , H04N19/114 , H04N19/174 , H04N19/136
Abstract: Disclosed herein are a method and apparatus for video encoding and decoding using picture partition information. Each of the pictures in a video is partitioned into tiles or slices based on picture partition information. Each picture is partitioned using one of at least two different methods based on the picture partition information. The picture partition information may indicate two or more picture partitioning methods. The picture partitioning methods may be changed either periodically or according to a specific rule. The picture partition information may describe such a periodic change or the specified rule.
-
-
-
-
-
-
-
Search Results
18
records
(took 0.019 seconds)
