Zobrazeno 1 - 10
of 38
pro vyhledávání: '"Xiaofeng Mao"'
Publikováno v:
IET Image Processing, Vol 17, Iss 8, Pp 2385-2398 (2023)
Abstract Small object detection remains a bottleneck because there is little visual information about them, especially in the deep layers. To improve the detection performance of small objects, here, Swin Transformer is introduced as the model backbo
Externí odkaz:
https://doaj.org/article/513154c93e3941e6bdec664af4813a83
Autor:
Chuan Qin, Yuefeng Chen, Kejiang Chen, Xiaoyi Dong, Weiming Zhang, Xiaofeng Mao, Yuan He, Nenghai Yu
Publikováno v:
IEEE Transactions on Artificial Intelligence. :1-12
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1140c5b4a07419f4309abdd0593dd26e
https://doi.org/10.1109/tai.2022.3190816
https://doi.org/10.1109/tai.2022.3190816
Publikováno v:
Chemical Science. 13:3009-3013
A tetra(o-tolyl)(μ-hydrido)diborane(4) anion is facilely prepared via the reaction of tetra(o-tolyl)diborane(4) with NaH. It exhibits a σ-B–B bond nucleophilicity towards NHC-metal halides to give the corresponding η2-B–B bonded metal complexe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c36bb8ec5da490b40219f312f7d7ac06
https://doi.org/10.1039/d2sc00318j
https://doi.org/10.1039/d2sc00318j
Publikováno v:
Proceedings of the Romanian Academy, Series A: Mathematics, Physics, Technical Sciences, Information Science; Jul-Sep2023, Vol. 24 Issue 3, p253-262, 10p
Publikováno v:
Neurocomputing. 440:207-219
Cross-modal retrieval is an important but challenging research task in the multimedia community. Most existing works of this task are supervised, which typically train models on a large number of aligned image-text/video-text pairs, making an assumpt
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a6eb390249a9c74d88687ff705b77d36
https://doi.org/10.1016/j.neucom.2021.01.114
https://doi.org/10.1016/j.neucom.2021.01.114
Publikováno v:
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
Recent advances on Vision Transformer (ViT) and its improved variants have shown that self-attention-based networks surpass traditional Convolutional Neural Networks (CNNs) in most vision tasks. However, existing ViTs focus on the standard accuracy a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::794298e7dccd59d24ed885fa77bc2559
https://doi.org/10.1109/cvpr52688.2022.01173
https://doi.org/10.1109/cvpr52688.2022.01173
Autor:
Yuefeng Chen, Xiaofeng Mao, Yuan He, Hui Xue, Chao Li, Yinpeng Dong, Qi-An Fu, Xiao Yang, Wenzhao Xiang, Tianyu Pang, Hang Su, Jun Zhu, Fangcheng Liu, Chao Zhang, Hongyang Zhang, Yichi Zhang, Shilong Liu, Chang Liu, Yajie Wang, Huipeng Zhou, Haoran Lyu, Yidan Xu, Zixuan Xu, Taoyu Zhu, Wenjun Li, Xianfeng Gao, Guoqiu Wang, Huanqian Yan, Ying Guo, Chaoning Zhang, Zheng Fang, Yang Wang, Bingyang Fu, Yunfei Zheng, Yekui Wang, Haorong Luo, Zhen Yang
Publikováno v:
Ying Guo
Many works have investigated the adversarial attacks or defenses under the settings where a bounded and imperceptible perturbation can be added to the input. However in the real-world, the attacker does not need to comply with this restriction. In fa
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ffa82f18c225a03857c21ce979519c50
http://arxiv.org/abs/2110.09903
http://arxiv.org/abs/2110.09903
Publikováno v:
IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. 30
This paper strives to predict fine-grained fashion similarity. In this similarity paradigm, one should pay more attention to the similarity in terms of a specific design/attribute between fashion items. For example, whether the collar designs of the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6104950b48fdf70e36f4419e6cc2afb6
https://pubmed.ncbi.nlm.nih.gov/34596539
https://pubmed.ncbi.nlm.nih.gov/34596539
Publikováno v:
CVPR
Though it is well known that the performance of deep neural networks (DNNs) degrades under certain light conditions, there exists no study on the threats of light beams emitted from some physical source as adversarial attacker on DNNs in a real-world
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::dc835790c539659634e1b2241b68919a