Zobrazeno 1 - 10
of 23
pro vyhledávání: '"Taesung Lee"'
Autor:
Hye Yeon Park, Yunki Lee, Jonghoon Park, Hyunseok Song, Taesung Lee, Hyung Keun Gweon, Yunji Jung, Jeongmin Bae, Boseong Kim, Junwon Han, Seungwon Kim, Cheolsang Yoon, Jeongki Kim, Changkeun Lee, Sehoon Yoo, EuiYeol Kim, Hyunmin Baek, Howoo Park, Bumsuk Kim, JungChak Ahn, JoonSeo Yim
Publikováno v:
2022 IEEE Symposium on VLSI Technology and Circuits (VLSI Technology and Circuits).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::05de7957c725474fbb05a4415453f4f2
https://doi.org/10.1109/vlsitechnologyandcir46769.2022.9830428
https://doi.org/10.1109/vlsitechnologyandcir46769.2022.9830428
Backdoor attacks mislead machine-learning models to output an attacker-specified class when presented a specific trigger at test time. These attacks require poisoning the training data to compromise the learning algorithm, e.g., by injecting poisonin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d59f0b796703f11ae7a37051207a95af
http://arxiv.org/abs/2006.06721
http://arxiv.org/abs/2006.06721
Autor:
Taesung Lee, Youngja Park
Publikováno v:
Machine Learning and Knowledge Discovery in Databases ISBN: 9783030461461
ECML/PKDD (2)
ECML/PKDD (2)
We present a new unsupervised method for learning general-purpose sentence embeddings. Unlike existing methods which rely on local contexts, such as words inside the sentence or immediately neighboring sentences, our method selects, for each target s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8675148a3dd32e7d27c4501a36369c80
https://doi.org/10.1007/978-3-030-46147-8_38
https://doi.org/10.1007/978-3-030-46147-8_38
Publikováno v:
Energy and Buildings. 257:111769
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::17abd3ad4c92f4bcd3966d72bdaf8175
https://doi.org/10.1016/j.enbuild.2021.111769
https://doi.org/10.1016/j.enbuild.2021.111769
Publikováno v:
Proceedings of the VLDB Endowment. 12:1-13
This paper studies the optimization of list intersection, especially in the context of the matching phase of search engines. Given a user query, we intersect the postings lists corresponding to the query keywords to generate the list of documents mat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b3554f31b2f6f17d1c9395f0fa9771c5
https://doi.org/10.14778/3275536.3275537
https://doi.org/10.14778/3275536.3275537
Autor:
Chaowei Xiao, Dawn Song, Bo Li, Mingyan Liu, Taesung Lee, Jinfeng Yi, Benjamin Edwards, Ian M. Molloy, Ruizhi Deng
Publikováno v:
ICCV
Deep neural networks (DNNs) have been widely applied in various applications, including autonomous driving and surveillance systems. However, DNNs are found to be vulnerable to adversarial examples, which are carefully crafted inputs aiming to mislea
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::920c99cc4d15d194d8cada56787a51f4
https://doi.org/10.1109/iccv.2019.00407
https://doi.org/10.1109/iccv.2019.00407
Publikováno v:
IEEE Symposium on Security and Privacy Workshops
Machine learning architectures are readily available, but obtaining the high quality labeled data for training is costly. Pre-trained models available as cloud services can be used to generate this costly labeled data, and would allow an attacker to
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3782affb1972ef9006c5362102e5e28f
https://doi.org/10.1109/spw.2019.00020
https://doi.org/10.1109/spw.2019.00020
Publikováno v:
EMNLP/IJCNLP (1)
We propose a novel supervised open information extraction (Open IE) framework that leverages an ensemble of unsupervised Open IE systems and a small amount of labeled data to improve system performance. It uses the outputs of multiple unsupervised Op
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::09a5b6965f34dd9c0dd933402af655a1
https://doi.org/10.18653/v1/d19-1067
https://doi.org/10.18653/v1/d19-1067
Publikováno v:
Proceedings of the VLDB Endowment. 9:132-143
Important cloud services rely on spatial-keyword queries, containing a spatial predicate and arbitrary boolean keyword queries. In particular, we study the processing of such queries in main memory to support short response times. In contrast, curren
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f1b2ed6648e7a974b5772ab711899c4b
https://doi.org/10.14778/2850583.2850588
https://doi.org/10.14778/2850583.2850588
Publikováno v:
IEEE Transactions on Knowledge and Data Engineering. 26:3051-3063
This paper studies the problem of mining named entity translations by aligning comparable corpora. Current state-of-the-art approaches mine a translation pair by aligning an entity graph in one language to another based on node similarity or propagat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::dea307400f273d0c04e24a8b780e97b2
https://doi.org/10.1109/tkde.2014.2316799
https://doi.org/10.1109/tkde.2014.2316799