Zobrazeno 1 - 10
of 26
pro vyhledávání: '"Zhihang, Ji"'
Publikováno v:
Applied Sciences, Vol 14, Iss 8, p 3441 (2024)
The multi-armed bandit (MAB) problem is a typical problem of exploration and exploitation. As a classical MAB problem, the stochastic multi-armed bandit (SMAB) is the basis of reinforcement learning recommendation. However, most existing SMAB and MAB
Externí odkaz:
https://doaj.org/article/0aa9ebb0ca864413bb5d1b2a7c971dd8
Publikováno v:
Cognitive Computation and Systems, Vol 4, Iss 4, Pp 378-390 (2022)
Abstract With the international development of the medical service informatisation, medical information sharing has become the key standard to measure the degree of medical informatisation. In this process, it is important to ensure the security of p
Externí odkaz:
https://doaj.org/article/c6c6893173d64971915fa423ee8be5a9
Publikováno v:
IEEE Access, Vol 8, Pp 86595-86607 (2020)
In this paper, we propose a multi-scale visual tracking algorithm based on attention mechanism to solve the problem that the appearance characteristic model of region proposals network has weak ability to distinguish foreground and semantic backgroun
Externí odkaz:
https://doaj.org/article/1dbfad04edac45d4bf91099a4d23bd26
Publikováno v:
IET Computer Vision, Vol 13, Iss 8, Pp 691-699 (2019)
In natural images, it remains challenging to estimate dissimilarities between image elements for scene representation due to gradual variations of illuminations, textures or clutters. To tackle this problem, we utilise a path‐based bottleneck analy
Externí odkaz:
https://doaj.org/article/32641bb457344c189ae3866628ef606f
Publikováno v:
Applied Sciences, Vol 10, Iss 7, p 2302 (2020)
Infrared and visible image match is an important research topic in the field of multi-modality image processing. Due to the difference of image contents like pixel intensities and gradients caused by disparate spectrums, it is a great challenge for i
Externí odkaz:
https://doaj.org/article/b48e79a839ae4776ab678f8aefbc63d0
Publikováno v:
Applied Sciences, Vol 10, Iss 1, p 140 (2019)
In the standard bag-of-visual-words (BoVW) model, the burstiness problem of features and the ignorance of high-order information often weakens the discriminative power of image representation. To tackle them, we present a novel framework, named the S
Externí odkaz:
https://doaj.org/article/59f9d1bdfb144bae81561d14435a6892
Publikováno v:
Applied Intelligence; May2023, Vol. 53 Issue 9, p10365-10379, 15p
Publikováno v:
IET Image Processing. 14:2166-2174
In the standard bag-of-visual-words model, the relationship between visual words and geometric structure information embedding in Voronoi cells is important for expressing the topology of the feature space. However, this information is usually ignore
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::307760eb0dff8c6886165ede53929cb3
https://doi.org/10.1049/iet-ipr.2019.0719
https://doi.org/10.1049/iet-ipr.2019.0719
Publikováno v:
IEEE Access, Vol 8, Pp 86595-86607 (2020)
In this paper, we propose a multi-scale visual tracking algorithm based on attention mechanism to solve the problem that the appearance characteristic model of region proposals network has weak ability to distinguish foreground and semantic backgroun
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0da653a70af9d461a706dadd723a75cf
https://ieeexplore.ieee.org/document/9081960/
https://ieeexplore.ieee.org/document/9081960/
Publikováno v:
Wireless Communications and Mobile Computing.
In mobile multimedia applications, deep learning has received significant interest. Due to the limited computation and storage resources of mobile devices, however, general training methods are hardly suited for mobile multimedia computing. For this
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::cf581815a6b1973724791b2bbe7abd6c