Zobrazeno 1 - 3
of 3
pro vyhledávání: '"Dohwan Ko"'
Publikováno v:
IEEE Access, Vol 9, Pp 146938-146947 (2021)
Modern neural networks are known to be vulnerable to adversarial attacks in various domains. Although most attack methods usually densely change the input values, recent works have shown that deep neural networks (DNNs) are also vulnerable to sparse
Externí odkaz:
https://doaj.org/article/7b93adf29cfb4975b70c64124a8cca42
Publikováno v:
IEEE Access, Vol 9, Pp 146938-146947 (2021)
Modern neural networks are known to be vulnerable to adversarial attacks in various domains. Although most attack methods usually densely change the input values, recent works have shown that deep neural networks (DNNs) are also vulnerable to sparse
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f07d5320b7ce6262df993c2818e7b1a3
https://doi.org/10.1109/access.2021.3124050
https://doi.org/10.1109/access.2021.3124050
Autor:
Dohwan Ko, Joonmyung Choi, Juyeon Ko, Shinyeong Noh, Kyoung-Woon On, Eun-Sol Kim, Hyunwoo J. Kim
Learning generic joint representations for video and text by a supervised method requires a prohibitively substantial amount of manually annotated video datasets. As a practical alternative, a large-scale but uncurated and narrated video dataset, How
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6c5c30cb12c91cdb589c19a861d4c29d
http://arxiv.org/abs/2203.16784
http://arxiv.org/abs/2203.16784
