Zobrazeno 1 - 10
of 18 543
pro vyhledávání: '"Kernel (image processing)"'
Publikováno v:
Jisuanji kexue yu tansuo, Vol 16, Iss 7, Pp 1570-1582 (2022)
Although the traditional programmable processors are highly flexible, their processing speed and perfor-mance are inferior to the application specific integrated circuit (ASIC). Image processing is often a diverse, intensive and repetitive operation,
Externí odkaz:
https://doaj.org/article/62bf2d46df7348489a75aefb29ecff5d
Publikováno v:
IEEE Transactions on Neural Networks and Learning Systems. 34:2693-2700
In this brief, stabilization of Boolean networks (BNs) by flipping a subset of nodes is considered, here we call such action state-flipped control. The state-flipped control implies that the logical variables of certain nodes are flipped from 1 to 0
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8b0f264c0418e12d3b08a96298757734
https://doi.org/10.1109/tnnls.2021.3106918
https://doi.org/10.1109/tnnls.2021.3106918
Publikováno v:
IEEE Transactions on Big Data. 9:75-92
With the continuously increasing amount of video data, image set classification has recently received widespread attention in the CV & PR community. However, the intra-class diversity and inter-class ambiguity of representations remain an open challe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4446ac26e350955235d92e49a96cdfef
https://doi.org/10.1109/tbdata.2021.3113084
https://doi.org/10.1109/tbdata.2021.3113084
Publikováno v:
IEEE Transactions on Cybernetics. 52:12084-12098
With the development of Earth observation technology, very-high-resolution (VHR) image has become an important data source of change detection. Nowadays, deep learning methods have achieved conspicuous performance in the change detection of VHR image
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1839434c8cd54e782569da55ac57edcd
https://doi.org/10.1109/tcyb.2021.3086884
https://doi.org/10.1109/tcyb.2021.3086884
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. 44:7235-7252
Spherical images or videos, as typical non-Euclidean data, are usually stored in the form of 2D panoramas obtained through an equirectangular projection, which is neither equal area nor conformal. The distortion caused by the projection limits the pe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0916e1a50008eb890af269711d9559b7
https://doi.org/10.1109/tpami.2021.3100259
https://doi.org/10.1109/tpami.2021.3100259
Autor:
Zilei Wang, Xiangbin Wu, Lichao Huang, Kunfeng Wang, Xuesong Li, Hui Yu, Yonglin Tian, Fei-Yue Wang
Publikováno v:
IEEE Transactions on Intelligent Transportation Systems. 23:10773-10785
Varying density of point clouds increases the difficulty of 3D detection. In this paper, we present a context-aware dynamic network (CADNet) to capture the variance of density by considering both point context and semantic context. Point-level contex
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::13c8312a9d37c6ac45bce6127f9584a5
https://doi.org/10.1109/tits.2021.3095719
https://doi.org/10.1109/tits.2021.3095719
Publikováno v:
IEEE Transactions on Cybernetics. 52:7704-7718
Cross-manifold clustering is a hard topic and many traditional clustering methods fail because of the cross-manifold structures. In this paper, we propose a Multiple Flat Projections Clustering (MFPC) to deal with cross-manifold clustering problems.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::dd536ee9d3dd0fce473dd0bba9cb06fd
https://doi.org/10.1109/tcyb.2021.3050487
https://doi.org/10.1109/tcyb.2021.3050487
Publikováno v:
IEEE Transactions on Intelligent Transportation Systems. 23:7896-7909
Loop-closure detection (LCD), which aims to recognize a previously visited location, is a crucial component of the simultaneous localization and mapping system. In this paper, a novel appearance-based LCD method is presented. In particular, we propos
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9d0f031c450556e442442472ac66b556
https://doi.org/10.1109/tits.2021.3074520
https://doi.org/10.1109/tits.2021.3074520
Publikováno v:
Chinese Journal of Physics. 77:1450-1464
Many applications and contexts including materials science, metallurgy, and solid-state physics, are concerned with the study of the behavior of viscoelastic materials. In addition, any composite or complex construction containing embedded polymers e
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::09bbb571342373a0532b1bff058fca3d
https://doi.org/10.1016/j.cjph.2021.11.001
https://doi.org/10.1016/j.cjph.2021.11.001
Publikováno v:
IEEE Transactions on Circuits and Systems for Video Technology. 32:3514-3526
Underwater captured images are usually degraded by low contrast, hazy, and blurry due to absorbing and scattering, which limits their analyses and applications. To address these problems, a red channel prior guided variational framework is proposed b
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::dcf612eaa7234f9e4e6b6badfce0a71a
https://doi.org/10.1109/tcsvt.2021.3115791
https://doi.org/10.1109/tcsvt.2021.3115791