Zobrazeno 1 - 10
of 27
pro vyhledávání: '"Youngjoon Yoo"'
Publikováno v:
IEEE Access, Vol 11, Pp 16631-16643 (2023)
Image-mixing augmentations (e.g., Mixup and CutMix), which typically involve mix ing two images, have become the de-facto training techniques for image classification. Despite their huge success in image classification, the number of images to be mix
Externí odkaz:
https://doaj.org/article/457d2219225f450086a9aa6fadad4c69
Publikováno v:
IEEE Sensors Journal. 21:5052-5059
Data loss for electronic noses may occur because of the sensor’s installation environment or from electrical disturbances. As a result, electronic noses may experience difficulties when identifying gases. This paper proposes two deep neural network
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::257d397bf7856261856df38c5c714935
https://doi.org/10.1109/jsen.2020.3034145
https://doi.org/10.1109/jsen.2020.3034145
Publikováno v:
Journal of the Korean Society of Propulsion Engineers. 23:112-118
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::92a5883e93a5fb7f2808ae21bc205cee
https://doi.org/10.6108/kspe.2019.23.3.112
https://doi.org/10.6108/kspe.2019.23.3.112
Publikováno v:
CVPR
Designing an efficient model within the limited computational cost is challenging. We argue the accuracy of a lightweight model has been further limited by the design convention: a stage-wise configuration of the channel dimensions, which looks like
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a0c43269b315b8f73aff17679d84a74f
https://doi.org/10.1109/cvpr46437.2021.00079
https://doi.org/10.1109/cvpr46437.2021.00079
Publikováno v:
CVPR
Continual learning is a realistic learning scenario for AI models. Prevalent scenario of continual learning, however, assumes disjoint sets of classes as tasks and is less realistic rather artificial. Instead, we focus on 'blurry' task boundary; wher
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::946f3b0f58951b36cff1021bf2071878
http://arxiv.org/abs/2103.17230
http://arxiv.org/abs/2103.17230
Weakly-supervised instance segmentation (WSIS) has been considered as a more challenging task than weakly-supervised semantic segmentation (WSSS). Compared to WSSS, WSIS requires instance-wise localization, which is difficult to extract from image-le
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a3e9b63af96d86f8f6815dcf3aa3a195
Publikováno v:
WACV
Designing a lightweight and robust portrait segmentation algorithm is an important task for a wide range of face applications. However, the problem has been considered as a subset of the object segmentation problem and less handled in the semantic se
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::16eba4b965ec27f207365e4fb12b15d7
https://doi.org/10.1109/wacv45572.2020.9093588
https://doi.org/10.1109/wacv45572.2020.9093588
Publikováno v:
Pattern Recognition Letters. 112:91-97
This paper proposes a novel deep conditional generative model for human pose transforms. To generate the desired pose-transformed images from a single image, a variational inference model is formulated to disentangle human posture semantics from imag
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e11b6239defe553c4a0c504dccd47ce4
https://doi.org/10.1016/j.patrec.2018.06.020
https://doi.org/10.1016/j.patrec.2018.06.020
Publikováno v:
IEEE Transactions on Neural Networks and Learning Systems. 29:2239-2252
In this paper, we propose an efficient visual tracker, which directly captures a bounding box containing the target object in a video by means of sequential actions learned using deep neural networks. The proposed deep neural network to control track
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::82d7741d33008c0d193c3302989907b9
https://doi.org/10.1109/tnnls.2018.2801826
https://doi.org/10.1109/tnnls.2018.2801826
Publikováno v:
SIGGRAPH Asia Technical Briefs
Converting hand-drawn sketches into clean line drawings is a crucial step for diverse artistic works such as comics and product designs. Recent data-driven methods using deep learning have shown their great abilities to automatically simplify sketche
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::04a985bc9f9c4ea9d3469970479e8479
https://doi.org/10.1145/3355088.3365163
https://doi.org/10.1145/3355088.3365163