Zobrazeno 1 - 10
of 251
pro vyhledávání: '"Jingjing Li"'
Publikováno v:
IEEE Transactions on Knowledge and Data Engineering. 34:5770-5783
It is widely acknowledged that the success of deep learning is built on large-scale training data and tremendous computing power. However, the data and computing power are not always available for many real-world applications. In this paper, we addre
Publikováno v:
IEEE Transactions on Cybernetics. 52:8167-8178
Zero-shot learning (ZSL) is a pretty intriguing topic in the computer vision community since it handles novel instances and unseen categories. In a typical ZSL setting, there is a main visual space and an auxiliary semantic space. Most existing ZSL m
Publikováno v:
IEEE Transactions on Transportation Electrification. 8:356-367
Remaining useful lifetime (RUL) and state of charge (SoC) of rechargeable lithium-ion batteries (LIBs) are two integral parts to ensure LIBs working reliably and safely for transportation electrification systems. The two together reflect the state of
Autor:
Qiang Wang, Jingjing Li
Publikováno v:
Information Fusion. 79:229-247
Multi-modal fusion combines multiple modal information to overcome the limitation of incomplete information expressed by a single modality, so as to realize the complementarity of modal information and enhance feature representation. Multi-modal medi
Publikováno v:
IEEE Transactions on Industrial Informatics. 18:922-931
Cross conditions prediction is a prevalent problem in manufacturing area, where tool wear prediction is a typical one. Existing data-driven methods for tool wear prediction mainly focus on cutting conditions with small variations, which encounters mu
Publikováno v:
IEEE Transactions on Multimedia. 24:1325-1337
In zero-shot learning (ZSL) tasks, especially in generalized zero-shot learning (GZSL), the model tends to classify unseen test samples into seen categories, which is well known as the domain shift problem, because the model is trained from seen samp
Publikováno v:
Science China Technological Sciences. 64:2640-2650
Despite the great success achieved by convolutional neural networks in addressing the raindrop removal problem, the still relatively blurry results call for better problem formulations and network architectures. In this paper, we revisited the rainy-
Publikováno v:
International Journal of Production Research. 60:5217-5234
As the core link of intelligent manufacturing, the process planning of aviation parts still faces the challenges such as relying on manual experiences for process decision-making and lack of linkag...
Publikováno v:
IEEE Transactions on Cybernetics. 51:3390-3403
Domain adaptation is suitable for transferring knowledge learned from one domain to a different but related domain. Considering the substantially large domain discrepancies, learning a more generalized feature representation is crucial for domain ada
Publikováno v:
IEEE Internet of Things Journal. 8:5453-5467
Massive connectivity and limited energy are main challenges for the beyond 5G (B5G)-enabled massive Internet of Things (IoT) to maintain diversified Qualify of Service (QoS) of the huge number of IoT device users. Motivated by these challenges, this