Zobrazeno 1 - 10
of 13
pro vyhledávání: '"Detian Hu"'
Publikováno v:
Journal of Lipid Research, Vol 65, Iss 6, Pp 100559- (2024)
Adipogenesis is one of the major mechanisms for adipose tissue expansion, during which spindle-shaped mesenchymal stem cells commit to the fate of adipocyte precursors and differentiate into round-shaped fat-laden adipocytes. Here, we investigated th
Externí odkaz:
https://doaj.org/article/9d4742301bcd4fcd8047c3e3e95988b2
Publikováno v:
Applied Sciences, Vol 14, Iss 22, p 10589 (2024)
Visual object tracking is a fundamental task in computer vision, with applications ranging from video surveillance to autonomous driving. Despite recent advances in transformer-based one-stream trackers, unrestricted feature interactions between the
Externí odkaz:
https://doaj.org/article/06ff2bed0d574cc68af885630e12ed09
Publikováno v:
IEEE Access, Vol 12, Pp 174782-174795 (2024)
Convolutional neural network (CNN) has achieved impressive success in lightweight image super-resolution (SR) methods, yet the nature of its local operations constrains the SR performance. Recent Transformer has attracted increasing attention in ligh
Externí odkaz:
https://doaj.org/article/4380ee689eae43a0804e6dffcd6a168a
Autor:
Wenwen Tan, Detian Huang
Publikováno v:
IEEE Access, Vol 12, Pp 105268-105280 (2024)
The prioritized experience replay mechanisms have achieved remarkable success in accelerating the convergence of reinforcement learning algorithms. However, applying traditional prioritized experience replay mechanisms directly to asynchronous reinfo
Externí odkaz:
https://doaj.org/article/c592122041094bcba1a144b711138711
Publikováno v:
ISPA/IUCC/BDCloud/SocialCom/SustainCom
Load imbalance reduces performance of cloud object storage with restrained system utilization and cost performance. The state of the art is to model load status by probing data nodes for decentralized scheduling (e.g. C3). This paper exploits the pot
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a457e944f281af013e6b36a533693b05
https://doi.org/10.1109/bdcloud.2018.00063
https://doi.org/10.1109/bdcloud.2018.00063
Publikováno v:
Sensors, Vol 24, Iss 1, p 83 (2023)
Unsupervised learning has shown immense potential in object tracking, where accurate classification and regression are crucial for unsupervised trackers. However, the classification and regression branches of most unsupervised trackers calculate obje
Externí odkaz:
https://doaj.org/article/f96de718a0ce49f7b2d4a8452636902d
Publikováno v:
IEEE Access, Vol 10, Pp 128077-128089 (2022)
Twin delayed deep deterministic (TD3) policy gradient is an effective algorithm for continuous action spaces. However, it cannot efficiently explore the spatial space and suffers from slow convergence, which is mainly due to the serial mode strategy
Externí odkaz:
https://doaj.org/article/c72fe85e1849445db27d1870f693d626
Autor:
Detian Huang, Jian Chen
Publikováno v:
IEEE Access, Vol 10, Pp 54599-54612 (2022)
Recently, the deep-learning-based image super-resolution methods have achieved astounding advancement. Whereas most of these methods utilize features from the low-resolution image space exclusively, and ignore the dependency between contextual featur
Externí odkaz:
https://doaj.org/article/78dbe4e07a8349b9a58b55c9de199b00
Publikováno v:
Applied Sciences, Vol 13, Iss 2, p 833 (2023)
Recent deep learning has shown great potential in super-resolution (SR) tasks. However, most deep learning-based SR networks are optimized via pixel-level loss (i.e., L1, L2, and MSE), which forces the networks to output the average of all possible p
Externí odkaz:
https://doaj.org/article/980051608b3e474f8c08f5a616594b14
Publikováno v:
IEEE Access, Vol 7, Pp 117206-117218 (2019)
Visual tracking is a challenging problem since it usually faces adverse factors, such as object deformation, fast motion, occlusion, and background clutter in practical applications. Reinforcement learning based Action-Decision Network (ADNet) has sh
Externí odkaz:
https://doaj.org/article/74ae806e0df1495982184e6b4969f4e6