Zobrazeno 1 - 10
of 54
pro vyhledávání: '"Zizhu Fan"'
Publikováno v:
Sensors, Vol 24, Iss 23, p 7655 (2024)
Hypergraph neural networks have gained widespread attention due to their effectiveness in handling graph-structured data with complex relationships and multi-dimensional interactions. However, existing hypergraph neural network models mainly rely on
Externí odkaz:
https://doaj.org/article/1a39b1738a5d4ab9a354c794b3ced30a
Publikováno v:
智能科学与技术学报, Vol 3, Pp 359-369 (2021)
The typical sparse representation for classification (SRC) is usually based on L1minimization problem.Conceptually, SRC is essentially an L0norm minimization problem solved in the original input space, which cannot capture well the nonlinear informat
Externí odkaz:
https://doaj.org/article/0770c94aefc94daebfa1eff1a6ffdb80
Publikováno v:
Mathematics, Vol 10, Iss 12, p 2110 (2022)
Feature extraction is an important part of perceptual hashing. How to compress the robust features of images into hash codes has become a hot research topic. Converting a two-dimensional image into a one-dimensional descriptor requires a higher compu
Externí odkaz:
https://doaj.org/article/3225bf7de2ea4544ba26aef93ae24796
Publikováno v:
Remote Sensing, Vol 12, Iss 17, p 2694 (2020)
The lunar crater recognition plays a key role in lunar exploration. Traditional crater recognition methods are mainly based on the human observation that is usually combined with classical machine learning methods. These methods have some drawbacks,
Externí odkaz:
https://doaj.org/article/83b2b12349bb43aa8a8e7fadfbd185d8
Publikováno v:
PLoS ONE, Vol 8, Iss 8, p e70370 (2013)
Minimum squared error based classification (MSEC) method establishes a unique classification model for all the test samples. However, this classification model may be not optimal for each test sample. This paper proposes an improved MSEC (IMSEC) meth
Externí odkaz:
https://doaj.org/article/738589fdce1b4580b6e6a55be27e7cd5
Publikováno v:
ACM Transactions on Knowledge Discovery from Data. 17:1-17
Dictionary learning is an efficient knowledge representation method that can learn the essential features of data. Traditional dictionary learning methods are difficult to obtain nonlinear information when processing large-scale and high-dimensional
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::343aed8745e3ce5d78df2b4b211bc499
https://doi.org/10.1145/3588575
https://doi.org/10.1145/3588575
Publikováno v:
IEEE Transactions on Neural Networks and Learning Systems. 34:64-78
In transfer learning model, the source domain samples and target domain samples usually share the same class labels but have different distributions. In general, the existing transfer learning algorithms ignore the interclass differences and intracla
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c409a30f06426c08e3658f8c5effb87b
https://doi.org/10.1109/tnnls.2021.3089566
https://doi.org/10.1109/tnnls.2021.3089566
Publikováno v:
IEEE Transactions on Instrumentation and Measurement. 72:1-9
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0ec8d8c0bee12e45a9affef3265910c5
https://doi.org/10.1109/tim.2023.3244839
https://doi.org/10.1109/tim.2023.3244839
Publikováno v:
IEEE Journal of Biomedical and Health Informatics. 26:1394-1405
Fast-developing single-cell technologies create unprecedented opportunities to reveal cell heterogeneity and diversity. Accurate classification of single cells is a critical prerequisite for recovering the mechanisms of heterogeneity. However, the sc
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::095b33072a37a4faf5c887c4041dd3b0
https://doi.org/10.1109/jbhi.2021.3099127
https://doi.org/10.1109/jbhi.2021.3099127
Publikováno v:
Neurocomputing. 472:224-251
Crowd counting and crowd density estimation methods are of great significance in the field of public security. Estimating crowd density and counting from single image or video frame has become an essential part of a computer vision system in various
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bd55d974421be11310998640acb9ad2e
https://doi.org/10.1016/j.neucom.2021.02.103
https://doi.org/10.1016/j.neucom.2021.02.103