-
Patent Agency Ranking
1.发明申请公开(公告)号：US20200372694A1
公开(公告)日：2020-11-26
申请号：US16877869
申请日：2020-05-19
Inventor： Won Jun HWANG , Dong Yi Kim , Joon Pyo Hong , Hyung Ho Kim
Abstract: A generative adversarial network (GAN)-based system for generating a color image from an edge image includes: a first GAN training a model for converting the edge image into an intermediate image; and a second GAN training a model for converting the intermediate image into the color image, wherein an entropy of the intermediate image corresponds to a value between an entropy of the edge image and an entropy of the color image.
-
公开(公告)号：US20210192343A1
公开(公告)日：2021-06-24
申请号：US17082148
申请日：2020-10-28
Applicant: AJOU UNIVERSITY INDUSTRY-ACADEMIC COOPERATION FOUNDATION , INCHEON NATIONAL UNIVERSITY RESEARCH & BUSINESS FOUNDATION
Inventor： Won Jun HWANG , Hyung Ho KIM , Hyeon CHO , Ouk CHOI
Abstract: Provided is a method of training a generative adversarial network (GAN) for converting between heterogeneous domains, the method including training a first GAN and a second GAN with at least one unpaired training data set comprised of a training image of a first domain and a training image of a second domain; using the trained first GAN to convert a first image of the first domain to an image of the second domain; using the trained second GAN to reconvert the converted image of the second domain to a second image of the first domain; and performing segmentation on at least one of the first image of the first domain, the converted image of the second domain, or the reconverted second image of the first domain.
-
公开(公告)号：US20220398865A1
公开(公告)日：2022-12-15
申请号：US17839443
申请日：2022-06-13
Inventor： Won Jun HWANG , Kun Liang LIU
Abstract: Provided are a device and method for human parsing. The method includes receiving at least one piece of image data and ground truth values for human parsing, generating a height distribution map and a width distribution map for the image data, acquiring attention maps and scaled feature maps for each of a height and a width of the image data using the distribution maps, calculating a distribution loss rate by concatenating the scaled feature maps, acquiring an improved feature map on the basis of the calculated distribution loss rate, and performing human parsing on an object included in the image data using the improved feature map.
-
公开(公告)号：US20200380297A1
公开(公告)日：2020-12-03
申请号：US16716881
申请日：2019-12-17
Applicant: AJOU UNIVERSITY INDUSTRY-ACADEMIC COOPERATION FOUNDATION , Dongguk University Industry-Academic Cooperation Foundation
Inventor： Won Jun HWANG , Ho Chul SIN , Dong Yi KIM , Soo Chul LIM , Dae Kwan KO
Abstract: A method of measuring an interaction force includes: generating feature maps corresponding to a plurality of sequential images; generating pooling maps respectively corresponding to feature map groups including a predetermined number of feature maps among the feature maps; generating attention maps corresponding to the pooling maps; and sequentially receiving feature maps modified based on the attention maps and outputting interaction force information.
-
公开(公告)号：US20220383047A1
公开(公告)日：2022-12-01
申请号：US17563663
申请日：2021-12-28
Inventor： Won Jun HWANG , Jae Min NA
IPC: G06K9/62
Abstract: The present invention relates to a method and apparatus for unsupervised domain adaptation, including the steps of generating a first augmented domain associated with a source domain, generating a second augmented domain associated with a target domain, and performing unsupervised domain adaptation by using the first augmented domain and the second augmented domain as a bridge for connecting the source domain and the target domain, and it is possible to apply to other exemplary embodiments.
-
-
-
-
Search Results
5
records
(took 0.013 seconds)
