Zobrazeno 1 - 10
of 26
pro vyhledávání: '"Weiqun Wu"'
Publikováno v:
IEEE Access, Vol 8, Pp 47013-47020 (2020)
Convolutional neural network-based methods are attracting increasing attention in steganalysis. However, steganalysis for content-adaptive image steganography in the spatial domain is still a difficult problem. In this paper, a new convolutional neur
Externí odkaz:
https://doaj.org/article/c4efd17e6d204c46a787da34b5e25fa9
Publikováno v:
IEEE Access, Vol 7, Pp 24411-24419 (2019)
Crowd counting is a challenging task due to the influence of various factors, such as scene transformation, complex crowd distribution, uneven illumination, and occlusion. To overcome such problems, scale-adaptive convolutional neural network (SaCNN)
Externí odkaz:
https://doaj.org/article/88ccbc57398d4b0693947363c16d346e
Publikováno v:
Multimedia Tools and Applications. 81:43503-43512
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1cbe61e9b5637e02249da9274c4a6d0f
https://doi.org/10.1007/s11042-022-13220-4
https://doi.org/10.1007/s11042-022-13220-4
Publikováno v:
Pattern Recognition Letters. 150:221-227
In this paper, we propose a density-aware and background-aware network via multi-task learning (MTL-DB) for crowd counting. It aims to enable the model to capture the high-level semantic information of density and background via multi-task joint trai
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3776fd93c6462978079e4b2fef8d36ef
https://doi.org/10.1016/j.patrec.2021.07.013
https://doi.org/10.1016/j.patrec.2021.07.013
Publikováno v:
Applied Sciences, Vol 8, Iss 12, p 2367 (2018)
In recent years, the trampling events due to overcrowding have occurred frequently, which leads to the demand for crowd counting under a high-density environment. At present, there are few studies on monitoring crowds in a large-scale crowded environ
Externí odkaz:
https://doaj.org/article/94f50a2238bc4fbcbcad341ee7a932c1
Publikováno v:
IEEE Access, Vol 8, Pp 47013-47020 (2020)
Convolutional neural network-based methods are attracting increasing attention in steganalysis. However, steganalysis for content-adaptive image steganography in the spatial domain is still a difficult problem. In this paper, a new convolutional neur
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a0ea45eeaee77c27aa7f2aed105445f5
https://ieeexplore.ieee.org/document/9026970/
https://ieeexplore.ieee.org/document/9026970/
Publikováno v:
Journal of Intelligent & Fuzzy Systems. 37:5973-5981
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cd0578d1a0cd6e3e8d301962911639a2
https://doi.org/10.3233/jifs-179179
https://doi.org/10.3233/jifs-179179
Publikováno v:
Computer Vision – ECCV 2020 Workshops ISBN: 9783030682378
ECCV Workshops (5)
ECCV Workshops (5)
In this paper, we propose a simple and effective network pruning framework, which introduces novel weight-dependent gates to prune filter adaptively. We argue that the pruning decision should depend on the convolutional weights, in other words, it sh
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d823caf198f065b4581953f0ba13fb9d
https://doi.org/10.1007/978-3-030-68238-5_3
https://doi.org/10.1007/978-3-030-68238-5_3
Publikováno v:
IEEE Access, Vol 7, Pp 24411-24419 (2019)
Crowd counting is a challenging task due to the influence of various factors, such as scene transformation, complex crowd distribution, uneven illumination, and occlusion. To overcome such problems, scale-adaptive convolutional neural network (SaCNN)
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5ec75a568ad50e34e4bf8389c779f17e
https://ieeexplore.ieee.org/document/8643345/
https://ieeexplore.ieee.org/document/8643345/
Publikováno v:
Proceedings of SPIE; 2/27/2019, Vol. 10995, p1-8, 8p