Zobrazeno 1 - 10
of 23
pro vyhledávání: '"Lingfeng Qiao"'
Publikováno v:
IET Computer Vision, Vol 12, Iss 6, Pp 873-881 (2018)
Zero‐shot learning (ZSL) aims to classify the objects without any training samples. Attributes are used to transfer knowledge from the training set to testing one in ZSL. Most ZSL methods based on Direct Attribute Prediction (DAP) assume that attri
Externí odkaz:
https://doaj.org/article/becccde753cf4434b1f4298c40e730f9
Publikováno v:
Applied Computational Intelligence and Soft Computing, Vol 2017 (2017)
The removal of mixed Gaussian-impulse noise plays an important role in many areas, such as remote sensing. However, traditional methods may be unaware of promoting the degree of the sparsity adaptively after decomposing into low rank component and sp
Externí odkaz:
https://doaj.org/article/15fd86e8b20e4e5d82cb75092bd4d1cf
Autor:
Wuji Liu, Zhongliang Jing, Jianzhe Huang, Xiangming Dun, Lingfeng Qiao, Henry Leung, Wujun Chen
Publikováno v:
IEEE Transactions on Industrial Electronics. :1-10
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::76eb434e570ff6258d67ed832694bb6c
https://doi.org/10.1109/tie.2023.3239912
https://doi.org/10.1109/tie.2023.3239912
Publikováno v:
Aerospace Systems. 4:261-267
Multiband image fusion has become a thriving area of research in a number of different fields, such as space robotics, and remote sensing, etc. Many multiband image fusion methods have been proposed for hyperspectral sharpening with panchromatic imag
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::89b7953e516323168a70bfd27a21dbe7
https://doi.org/10.1007/s42401-020-00075-6
https://doi.org/10.1007/s42401-020-00075-6
Publikováno v:
Neurocomputing. 423:190-199
A key issue in RGBD classification is how to fuse the RGB and depth modalities. A popular way is to extract the private features of unimodality and the common features between the two modalities. Most of them use low order algebraic metrics to find t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0514064eba3efa625dd1edb01689ecad
https://doi.org/10.1016/j.neucom.2020.07.129
https://doi.org/10.1016/j.neucom.2020.07.129
Publikováno v:
Journal of Bionic Engineering. 17:1126-1138
Performing complex tasks by soft robots in constrained environment remains an enormous challenge owing to the limitations of flexible mechanisms and control methods. In this paper, a novel biomimetic soft robot driven by Shape Memory Alloy (SMA) with
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9900d2fa138b2fe6e755ca3467e828f2
https://doi.org/10.1007/s42235-020-0102-8
https://doi.org/10.1007/s42235-020-0102-8
Scene segmentation and classification (SSC) serve as a critical step towards the field of video structuring analysis. Intuitively, jointly learning of these two tasks can promote each other by sharing common information. However, scene segmentation c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::673c7ba54ee07ce7ad7ddd58e80d2d4a
Publikováno v:
Lecture Notes in Electrical Engineering ISBN: 9789811659119
In the flexible robot domain, due to the high nonlinear characteristics of flexible robot actuators, infinite degrees of freedom in theory, and multidisciplinary integration of mechanics, electricity, chemistry, etc., the establishment of its kinemat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a65bc666008c98bc345a081caa6084bc
https://doi.org/10.1007/978-981-16-5912-6_58
https://doi.org/10.1007/978-981-16-5912-6_58
Publikováno v:
Aerospace Systems. 2:163-174
Object detection on multi-source images from satellite platforms is difficult due to the characteristics of imaging sensors. Multi-model image fusion provides a possibility to improve the performance of object detection. This paper proposes a fusion
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3148ab7d91f5fa18bbab4a81aee6ea08
https://doi.org/10.1007/s42401-019-00033-x
https://doi.org/10.1007/s42401-019-00033-x
Autor:
Junchi Yan, Henry Leung, Jian Hu, Zhongliang Jing, Lingfeng Qiao, Hongya Tuo, Chao Wang, Haowen Zhong
Publikováno v:
Computer Vision – ECCV 2020 ISBN: 9783030585822
ECCV (27)
ECCV (27)
Domain adaptation (DA) has been a fundamental building block for Transfer Learning (TL) which assumes that source and target domain share the same label space. A more general and realistic setting is that the label space of target domain is a subset
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b24dcb1c9f97107fd4854e9a5bc9afb2
https://doi.org/10.1007/978-3-030-58583-9_38
https://doi.org/10.1007/978-3-030-58583-9_38