Zobrazeno 1 - 10
of 28
pro vyhledávání: '"Sungrack Yun"'
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 36:7354-7362
It has been crucial to leverage the rich information of multiple modalities in many tasks. Existing works have tried to design multi-modal networks with descent multi-modal fusion modules. Instead, we focus on improving generalization capability of m
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7736968c996125f615abb2bda610b172
https://doi.org/10.1609/aaai.v36i7.20698
https://doi.org/10.1609/aaai.v36i7.20698
Deep learning models for verification systems often fail to generalize to new users and new environments, even though they learn highly discriminative features. To address this problem, we propose a few-shot domain generalization framework that learn
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::14ddc1bcbfa6339ea8bd215dd2077555
http://arxiv.org/abs/2206.13700
http://arxiv.org/abs/2206.13700
Publikováno v:
2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7f805de82f7e54c96917a7db7d2b21ad
https://doi.org/10.1109/wacv51458.2022.00089
https://doi.org/10.1109/wacv51458.2022.00089
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031198267
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2550d912cb021fc0079919c657f18a2e
https://doi.org/10.1007/978-3-031-19827-4_26
https://doi.org/10.1007/978-3-031-19827-4_26
Publikováno v:
2021 IEEE/CVF International Conference on Computer Vision (ICCV).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::320518e2399f8745b8bccd4a987a578c
https://doi.org/10.1109/iccv48922.2021.01346
https://doi.org/10.1109/iccv48922.2021.01346
Publikováno v:
ICASSP
Nowadays, as edge devices such as smartphones become prevalent, there are increasing demands for personalized services. However, traditional personalization methods are not suitable for edge devices because retraining or finetuning is needed with lim
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1eaa16a394f15bc99caf441eab86ee37
https://doi.org/10.1109/icassp39728.2021.9414526
https://doi.org/10.1109/icassp39728.2021.9414526
Publikováno v:
ICASSP
Convolutional Neural Networks are widely used in various machine learning domains. In image processing, the features can be obtained by applying 2D convolution to all spatial dimensions of the input. However, in the audio case, frequency domain input
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b4c6890f578f105285a980be14422de9
Autor:
Hee Seok Lee, Duck Hoon Kim, Hyoungwoo Park, Heesoo Myeong, Sungrack Yun, Janghoon Cho, Seungwoo Yoo
Publikováno v:
CVPR Workshops
In autonomous driving, detecting reliable and accurate lane marker positions is a crucial yet challenging task. The conventional approaches for the lane marker detection problem perform a pixel-level dense prediction task followed by sophisticated po
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f161febb4363c26535bbe1aefc3a2a50
http://arxiv.org/abs/2005.08630
http://arxiv.org/abs/2005.08630
In this paper, we present an acoustic scene classification framework based on a large-margin factorized convolutional neural network (CNN). We adopt the factorized CNN to learn the patterns in the time-frequency domain by factorizing the 2D kernel in
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a080ce539b36256ef9fcb80a44a5ca93
Publikováno v:
Proceedings of the Detection and Classification of Acoustic Scenes and Events 2019 Workshop (DCASE2019).
This paper considers a semi-supervised learning framework for weakly labeled polyphonic sound event detection problems for the DCASE 2019 challenge's task4 by combining both the tri-training and adversarial learning. The goal of the task4 is to detec
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a6687a78ff5197c1a351750bed36b99a
https://doi.org/10.33682/ntr9-6764
https://doi.org/10.33682/ntr9-6764