Zobrazeno 1 - 10
of 53
pro vyhledávání: '"Jae-Pil Heo"'
Publikováno v:
IEEE Access, Vol 11, Pp 96761-96772 (2023)
Training semantic segmentation models requires pixel-level annotations, leading to a significant labeling cost in dataset creation. To alleviate this issue, recent research has focused on semi-supervised learning, which utilizes only a small amount o
Externí odkaz:
https://doaj.org/article/c2dfc75ebb484a2db7e1d4723f4a3cdf
Publikováno v:
IEEE Access, Vol 11, Pp 69989-70000 (2023)
Optical flow estimation is a fundamental task that aims to find the 2-dimensional motion field by identifying correspondences between two input images. For quite a long time, the correlation volume followed by convolutional neural networks (CNN) to d
Externí odkaz:
https://doaj.org/article/6d54c49e8a774645937829f0896e5a8d
Publikováno v:
IEEE Access, Vol 10, Pp 126858-126870 (2022)
Neural networks have suffered from a distribution gap between training and test data, known as domain shift. Domain generalization (DG) methods aim to learn domain invariant representations only with limited source domain data to cope with unseen tar
Externí odkaz:
https://doaj.org/article/3e332f8d19474ad6957581c261836c9d
Publikováno v:
IEEE Access, Vol 9, Pp 152803-152818 (2021)
Throughout the past several years, deep learning-based models have achieved success in super-resolution (SR). The majority of these works assume that low-resolution (LR) images are ‘uniformly’ degraded from their corresponding high-resolution (HR
Externí odkaz:
https://doaj.org/article/c8c65f021cb94f388335cb8262fbb319
Autor:
Sang-Heon Shim, Jae-Pil Heo
Publikováno v:
IEEE Access, Vol 8, Pp 86972-86983 (2020)
Inverse mapping of the Generative Adversarial Networks (GANs) which projects data to latent space have been recently introduced, and it is shown that the inverse mapping models trained by the bidirectional adversarial learning can enable novel and pr
Externí odkaz:
https://doaj.org/article/77bb9132751c4f0b97cea7bc0efca8cf
Autor:
Hae-Chan Noh, Jae-Pil Heo
Publikováno v:
IEEE Access, Vol 8, Pp 56491-56500 (2020)
In this paper, we introduce and address a crucial but less accentuated problem in cross-domain retrieval task. We first highlight the challenge caused by diversity of inter-class similarities across different domains. For example, bear and teddy bear
Externí odkaz:
https://doaj.org/article/4e82cd95ae6541b2ad61086dcf040fea
Autor:
Ji-Hwan Kim, Jae-Pil Heo
Publikováno v:
IEEE Access, Vol 7, Pp 149797-149809 (2019)
Temporal action localization from untrimmed videos is a fundamental task for real-world computer vision applications such as video surveillance systems. Even though a great deal of research attention has been paid to the problem, precise localization
Externí odkaz:
https://doaj.org/article/f2d395a85217414a81c766fb3e3b23b2
Publikováno v:
Sensors, Vol 19, Iss 1, p 48 (2018)
Object tracking is a fundamental problem in computer vision since it is required in many practical applications including video-based surveillance and autonomous vehicles. One of the most challenging scenarios in the problem is when the target object
Externí odkaz:
https://doaj.org/article/27de327b2306443789c4a030f68f7bf5
Publikováno v:
Journal of Korea Planning Association. 57:41-54
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c788999dc443e680924c2851979cf3e8
https://doi.org/10.17208/jkpa.2022.12.57.7.41
https://doi.org/10.17208/jkpa.2022.12.57.7.41
Publikováno v:
Korean Journal of Chemical Engineering.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d34e70dc048b5dc9224f99936a786ec2
https://doi.org/10.1007/s11814-022-1356-0
https://doi.org/10.1007/s11814-022-1356-0