Zobrazeno 1 - 10
of 28
pro vyhledávání: '"Aishan Liu"'
Publikováno v:
IEEE Transactions on Multimedia. :1-12
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::596e8254830116c2dfb1e798bf46d740
https://doi.org/10.1109/tmm.2023.3234368
https://doi.org/10.1109/tmm.2023.3234368
Publikováno v:
Neurocomputing. 496:227-237
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b5a082e377dba46dd5c0637f5fee2a84
https://doi.org/10.1016/j.neucom.2021.08.151
https://doi.org/10.1016/j.neucom.2021.08.151
Publikováno v:
IEEE Transactions on Image Processing. 31:598-611
Adversarial examples are inputs with imperceptible perturbations that easily mislead deep neural networks (DNNs). Recently, adversarial patch, with noise confined to a small and localized patch, has emerged for its easy feasibility in real-world scen
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7ef5fabc942c04afa916290fb8a93d53
https://doi.org/10.1109/tip.2021.3127849
https://doi.org/10.1109/tip.2021.3127849
Publikováno v:
Proceedings of the 30th ACM International Conference on Multimedia.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::918605054c78be357a384ed080bfda29
https://doi.org/10.1145/3503161.3547989
https://doi.org/10.1145/3503161.3547989
Publikováno v:
Proceedings of the 30th ACM International Conference on Multimedia.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d504cc653ce4efded58f12f1864ff35c
https://doi.org/10.1145/3503161.3548075
https://doi.org/10.1145/3503161.3548075
Publikováno v:
Proceedings of the 30th ACM International Conference on Multimedia.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::18d959797ba6f6a648858588443e8040
https://doi.org/10.1145/3503161.3548416
https://doi.org/10.1145/3503161.3548416
Publikováno v:
IEEE transactions on cybernetics.
Recently, deep neural networks have achieved promising performance for in-filling large missing regions in image inpainting tasks. They have usually adopted the standard convolutional architecture over the corrupted image, leading to meaningless cont
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::04ad988bd0331f33407298e88c3e429a
https://pubmed.ncbi.nlm.nih.gov/35976829
https://pubmed.ncbi.nlm.nih.gov/35976829
Autor:
Renshuai Tao, Hainan Li, Tianbo Wang, Yanlu Wei, Yifu Ding, Bowei Jin, Hongping Zhi, Xianglong Liu, Aishan Liu
Publikováno v:
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b5197817ba4173f856507adce20ddcb7
https://doi.org/10.1109/cvpr52688.2022.02051
https://doi.org/10.1109/cvpr52688.2022.02051
Publikováno v:
Information Sciences. 547:568-578
Deep neural networks (DNNs) are vulnerable to adversarial examples which are generated by inputs with imperceptible perturbations. Understanding adversarial robustness of DNNs has become an important issue, which would for certain result in better pr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::34de4882c37634bffeb048312636d773
https://doi.org/10.1016/j.ins.2020.08.043
https://doi.org/10.1016/j.ins.2020.08.043
Autor:
Dawn Song, Alan L. Yuille, Dacheng Tao, Xinyun Chen, Animashree Anandkumar, Xianglong Liu, Xun Yang, Aishan Liu, Chaowei Xiao, Yingwei Li
Publikováno v:
ACM Multimedia
Deep learning has achieved significant success in multimedia fields involving computer vision, natural language processing, and acoustics. However research in adversarial learning also shows that they are highly vulnerable to adversarial examples. Ex
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ef36f2cbf45c7e9bfd11c1741793afea
https://doi.org/10.1145/3474085.3478572
https://doi.org/10.1145/3474085.3478572