Zobrazeno 1 - 10
of 219
pro vyhledávání: '"Wang, Songhe"'
Federated learning (FL) represents a novel paradigm to machine learning, addressing critical issues related to data privacy and security, yet suffering from data insufficiency and imbalance. The emergence of foundation models (FMs) provides a promisi
Externí odkaz:
http://arxiv.org/abs/2311.00144
Deep neural networks (DNNs) have achieved tremendous success in various applications including video action recognition, yet remain vulnerable to backdoor attacks (Trojans). The backdoor-compromised model will mis-classify to the target class chosen
Externí odkaz:
http://arxiv.org/abs/2308.11070
Publikováno v:
In Construction and Building Materials 11 October 2024 447
Objective evaluation (OE) is essential to artificial music, but it's often very hard to determine the quality of OEs. Hitherto, subjective evaluation (SE) remains reliable and prevailing but suffers inevitable disadvantages that OEs may overcome. The
Externí odkaz:
http://arxiv.org/abs/2108.12973
Publikováno v:
In International Journal of Heat and Fluid Flow July 2024 107
Publikováno v:
In Construction and Building Materials 8 March 2024 418
Publikováno v:
In Cold Regions Science and Technology January 2024 217
COVID-19 has been affecting every aspect of societal life including human mobility since December, 2019. In this paper, we study the impact of COVID-19 on human mobility patterns at the state level within the United States. From the temporal perspect
Externí odkaz:
http://arxiv.org/abs/2010.03707
Machine Reading at Scale (MRS) is a challenging task in which a system is given an input query and is asked to produce a precise output by "reading" information from a large knowledge base. The task has gained popularity with its natural combination
Externí odkaz:
http://arxiv.org/abs/1909.08041
Publikováno v:
In Journal of Rock Mechanics and Geotechnical Engineering February 2023 15(2):412-428