Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Sanyou Zhang"'
Publikováno v:
IEEE Access, Vol 8, Pp 185198-185208 (2020)
Currently, deep-learning-based methods have been the most popular super-resolution techniques owing to the improvement of super-resolution performance. However, they are still lack perceptual fine details and thus result in unsatisfying visual qualit
Externí odkaz:
https://doaj.org/article/58acfd3ff7054cfa8c78aad0433d8692
Publikováno v:
IEEE Access, Vol 8, Pp 185198-185208 (2020)
Currently, deep-learning-based methods have been the most popular super-resolution techniques owing to the improvement of super-resolution performance. However, they are still lack perceptual fine details and thus result in unsatisfying visual qualit
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ff2a35430e60bf3432a22959fe1922ab
https://ieeexplore.ieee.org/document/9220103/
https://ieeexplore.ieee.org/document/9220103/
Publikováno v:
Wireless Networks.
Aiming for the ResNet network structure used for feature extraction, there are still problems of overfitting, slow calculation speed and room for improvement of accuracy. A mixed depthwise separation residual network is proposed for image feature ext
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::02ce3833eee8e5e3f18dfea65e4c0a46
https://doi.org/10.1007/s11276-021-02665-4
https://doi.org/10.1007/s11276-021-02665-4
Publikováno v:
Simulation Tools and Techniques ISBN: 9783030727918
SimuTools (1)
SimuTools (1)
In this paper, an improved model based on the combination of residual and inverted residual blocks is proposed for image expression recognition, named as bi-directional residual network. The main objective of the proposed method is to alleviate the p
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::80d0d14a8131e82d533684ad4e069780
https://doi.org/10.1007/978-3-030-72792-5_16
https://doi.org/10.1007/978-3-030-72792-5_16
