-
1.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.
-
Patent Agency Ranking
公开(公告)号：US20160275809A1
公开(公告)日：2016-09-22
申请号：US15070393
申请日：2016-03-15
Inventor： Hyun-Woo CHO , Hong-Kee KIM , Woo-Jin JEON , Ki-Hong KIM
CPC classification number: G09B9/085 , A63F13/25 , A63F13/90 , G02B27/017 , G06F3/011 , G06F3/012 , G06F3/16 , G09B9/206 , G09B9/24 , G09B9/301 , G09B9/302 , G09B9/307
Abstract: A motion platform system includes: a wide-viewing-angle display configured to provide images according to user's head movement; a paragliding harness; a control hand brake; a top frame configured to fix the paragliding harness; a lamp structure configured to support the top frame; and a computing device configured to produce contents for the images.
Abstract translation: 运动平台系统包括：广视角显示器，被配置为根据用户的头部移动来提供图像; 滑翔伞 控制手制动器; 配置成固定滑翔伞线束的顶部框架; 构造成支撑顶架的灯结构; 以及被配置为产生图像的内容的计算装置。
-
公开(公告)号：US20150193964A1
公开(公告)日：2015-07-09
申请号：US14590885
申请日：2015-01-06
Inventor： Hang-Kee KIM , Young-Hee KIM , Yong-Sun KIM , Ki-Hong KIM , Hyun-Woo CHO , Jin-Ho KIM
CPC classification number: G06T15/10 , G06K9/00624 , G06K9/32 , G06K9/34 , G06K2009/3291 , H04N9/3182 , H04N9/3185 , H04N9/3194
Abstract: Disclosed herein is a real-time dynamic non-planar projection apparatus and method, which can reduce visual errors, such as distortion of a screen image or deviation from a border area, upon projecting screen images from a projector onto the surface of a non-planar object that is moved in real time. The presented real-time dynamic non-planar projection apparatus includes a preprocessing unit for preprocessing data related to a static part of a screen image to be projected onto a non-planar surface. A real-time projection unit classifies non-planar objects in the screen image to be projected onto the non-planar surface into a rigid body and a non-rigid body using data output from the preprocessing unit, respectively renders the rigid body and the non-rigid body depending on a viewer's current viewpoint, and projects rendered results onto the non-planar surface via projection mapping.
Abstract translation: 本文公开了一种实时动态非平面投影设备和方法，其可以将屏幕图像从投影仪投影到非平面投影仪的表面上，从而可以减少诸如屏幕图像的失真或偏离边界区域的视觉错误， 实时移动的平面对象。 所呈现的实时动态非平面投影装置包括预处理单元，用于预处理与投影到非平面表面上的屏幕图像的静态部分有关的数据。 实时投影单元将屏幕图像中的非平面物体分类为使用来自预处理单元的数据输出的投影到非平面表面的刚体和非刚体，分别使刚体和非平面物体 - 根据观众的当前观点进行的刚体，并通过投影映射将渲染结果投影到非平面表面上。
-
公开(公告)号：US20230316091A1
公开(公告)日：2023-10-05
申请号：US18166948
申请日：2023-02-09
Inventor： Jin-Wuk SEOK , Ji-Young KWAK , Seon-Tae KIM , Hong-Soog KIM , Jae-Bok PARK , Kyung-Hee LEE , Chang-Sik CHO , Hyun-Woo CHO
IPC: G06N3/098
CPC classification number: G06N3/098
Abstract: Disclosed herein are a federated learning method and apparatus. The federated learning method includes receiving a feature vector extracted from a client side and label data corresponding to the feature vector, outputting a feature vector with phase information preserved therein by applying the feature vector as input of a Self-Organizing Feature Map (SOFM), and training a neural network model by applying both the feature vector with the phase information preserved therein and the label data as input of a neural network model.
-
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：US20170371423A1
公开(公告)日：2017-12-28
申请号：US15624206
申请日：2017-06-15
Inventor： Seok-Jin YOON , Do-Hyung KIM , Cheol RYU , Jae-Ho LEE , Hyung-Seok LEE , Hyun-Woo CHO , Kyung-Hee LEE
CPC classification number: G06F3/0227 , G06F3/023 , G06F3/0231 , G06F3/03543 , G06F3/038 , G06F3/0383 , G06F13/385 , G06F13/4282 , G06F2203/0383 , G06F2203/0384 , G06T11/60
Abstract: Disclosed herein is an apparatus for controlling an embedded device, through which the embedded device may be controlled in a host computer in real time. The apparatus for controlling an embedded device includes a host computer connected with a monitor, a mouse, and a keyboard; an embedded device; and a connection module for connecting the host computer with the embedded device such that a first task window for controlling the host computer and a second task window for controlling the embedded device are displayed on the monitor.
-
-
-
-
-
Search Results
6
records
(took 0.017 seconds)
