Zobrazeno 1 - 10
of 19
pro vyhledávání: '"Zhuangzi Li"'
Publikováno v:
Foods, Vol 12, Iss 15, p 2885 (2023)
Real-time and accurate awareness of the grain situation proves beneficial for making targeted and dynamic adjustments to cleaning parameters and strategies, leading to efficient and effective removal of impurities with minimal losses. In this study,
Externí odkaz:
https://doaj.org/article/8cb3b70516444300ade95bf3a39604c8
Publikováno v:
IEEE Access, Vol 8, Pp 33768-33777 (2020)
It is well-known that high-frequency information (e.g. textures, edges) is significant for single image super-resolution (SISR). However, Existing of deep Convolutional Neural Network (CNN) based methods directly model mapping function from low resol
Externí odkaz:
https://doaj.org/article/e9d6c3c290ba4355a8b76ea898731939
Publikováno v:
IEEE Access, Vol 8, Pp 54698-54698 (2020)
In the above-named article, the funding information was incorrect. In addition, there was an error in the author affiliation that is corrected here.
Externí odkaz:
https://doaj.org/article/689e50c89fe94bc49a0bd7e46d8f3fd8
Publikováno v:
Pattern Recognition Letters. 138:556-562
In recent years, Convolutional Neural Networks (CNNs) have shown promising performance on image hashing retrieval. However, due to the information-discarded nature of CNN, some meaningful information can not be further extracted into a deep level and
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2de3e96daa953b5c6e1d2472f5def903
https://doi.org/10.1016/j.patrec.2020.09.002
https://doi.org/10.1016/j.patrec.2020.09.002
Publikováno v:
Information Sciences. 515:233-247
Classifying low-resolution (LR) images is notoriously challenging because of their noisy representation and limited information. Existing approaches mainly solve this challenge by training carefully designed architectures on LR datasets or by employi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c639429bd2a1a353f1e0f9d59cd66764
https://doi.org/10.1016/j.ins.2019.12.013
https://doi.org/10.1016/j.ins.2019.12.013
Publikováno v:
IEEE Access, Vol 8, Pp 33768-33777 (2020)
It is well-known that high-frequency information (e.g. textures, edges) is significant for single image super-resolution (SISR). However, Existing of deep Convolutional Neural Network (CNN) based methods directly model mapping function from low resol
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::68cc3eca280039f0e740ddf15f8ca649
https://ieeexplore.ieee.org/document/8990140/
https://ieeexplore.ieee.org/document/8990140/
Publikováno v:
ACM Multimedia
It is generally known that a high-resolution (HR) image contains more productive information compared with its low-resolution (LR) versions, so image super-resolution (SR) satisfies an information-growth process. Considering the property, we attempt
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b767dc89b7d03af493d71b7917d44d26
https://doi.org/10.1145/3474085.3475207
https://doi.org/10.1145/3474085.3475207
Publikováno v:
AAAI
Video super-resolution is a challenging task, which has attracted great attention in research and industry communities. In this paper, we propose a novel end-to-end architecture, called Residual Invertible Spatio-Temporal Network (RISTN) for video su
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d0199fc1b4805508cf43c57ebb71716d
https://doi.org/10.1609/aaai.v33i01.33015981
https://doi.org/10.1609/aaai.v33i01.33015981
Publikováno v:
IEEE Transactions on Multimedia. :1-1
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4a03da098130eebc37afd313ea8b73de
https://doi.org/10.1109/tmm.2022.3160604
https://doi.org/10.1109/tmm.2022.3160604
Publikováno v:
Computer Graphics Forum. 37:289-300
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::593efc8df434ea3e291912e009c35080
https://doi.org/10.1111/cgf.13568
https://doi.org/10.1111/cgf.13568