Zobrazeno 1 - 10
of 1 109
pro vyhledávání: '"Hu Wentao"'
Autor:
You Xinpeng, Yu Hui, Su Lingjie, Yin Jun, Chen Junchao, Cao Zhihui, Pan Junxi, Li Yiting, Zheng Yuying, Hu Wentao
Publikováno v:
Processing and Application of Ceramics, Vol 18, Iss 2, Pp 146-155 (2024)
Superhydrophobic materials have found extensive applications in everyday life and various industries due to their outstanding attributes such as waterproofing, exceptional anti-corrosion and self-cleaning capabilities. Nonetheless, their limited mech
Externí odkaz:
https://doaj.org/article/36184bce7fe84498a7e24c821e1d8160
Autor:
Hu Wentao, Yao Tandong
Publikováno v:
Open Geosciences, Vol 13, Iss 1, Pp 1463-1475 (2021)
Two adjacent glaciers collapsed consecutively in the Western Xizang Autonomous Region, China, on July 17 and September 21, 2016, presumably triggered by relatively intensive climate change in this region, leading to massive downstream ice and mud ava
Externí odkaz:
https://doaj.org/article/7d07623760564a418aec4f54c1520f34
Model extraction aims to create a functionally similar copy from a machine learning as a service (MLaaS) API with minimal overhead, typically for illicit profit or as a precursor to further attacks, posing a significant threat to the MLaaS ecosystem.
Externí odkaz:
http://arxiv.org/abs/2409.14122
Publikováno v:
Gong-kuang zidonghua, Vol 46, Iss 10, Pp 55-60 (2020)
In view of 'information island' problem which is common in coal mines, a smart mine information interaction method based on resource model and constrained application protocol (CoAP) was proposed from practical point of view. Two key issues to be sol
Externí odkaz:
https://doaj.org/article/c2c09ce7e6e94cf891f104c8817153d0
With the rise of Machine Learning as a Service (MLaaS) platforms,safeguarding the intellectual property of deep learning models is becoming paramount. Among various protective measures, trigger set watermarking has emerged as a flexible and effective
Externí odkaz:
http://arxiv.org/abs/2404.13518
Autor:
Peng, Ziqiao, Hu, Wentao, Shi, Yue, Zhu, Xiangyu, Zhang, Xiaomei, Zhao, Hao, He, Jun, Liu, Hongyan, Fan, Zhaoxin
Achieving high synchronization in the synthesis of realistic, speech-driven talking head videos presents a significant challenge. Traditional Generative Adversarial Networks (GAN) struggle to maintain consistent facial identity, while Neural Radiance
Externí odkaz:
http://arxiv.org/abs/2311.17590
Large Language Models (LLMs) have emerged as promising agents for web navigation tasks, interpreting objectives and interacting with web pages. However, the efficiency of spliced prompts for such tasks remains underexplored. We introduces AllTogether
Externí odkaz:
http://arxiv.org/abs/2310.18331
As a modern ensemble technique, Deep Forest (DF) employs a cascading structure to construct deep models, providing stronger representational power compared to traditional decision forests. However, its greedy multi-layer learning procedure is prone t
Externí odkaz:
http://arxiv.org/abs/2309.09030
Autor:
Hu, Wentao, Fang, Hui
With increasing frequency of high-profile privacy breaches in various online platforms, users are becoming more concerned about their privacy. And recommender system is the core component of online platforms for providing personalized service, conseq
Externí odkaz:
http://arxiv.org/abs/2309.11515
Autor:
Leeuwenkamp, Aleksy, Hu, Wentao
We propose a set of dependence measures that are non-linear, local, invariant to a wide range of transformations on the marginals, can show tail and risk asymmetries, are always well-defined, are easy to estimate and can be used on any dataset. We pr
Externí odkaz:
http://arxiv.org/abs/2309.00025