Zobrazeno 1 - 10
of 50 274
pro vyhledávání: '"Tin, A."'
Autor:
Jiang, Chengze, Wang, Junkai, Dong, Minjing, Gui, Jie, Shi, Xinli, Cao, Yuan, Tang, Yuan Yan, Kwok, James Tin-Yau
Adversarial training has achieved remarkable advancements in defending against adversarial attacks. Among them, fast adversarial training (FAT) is gaining attention for its ability to achieve competitive robustness with fewer computing resources. Exi
Externí odkaz:
http://arxiv.org/abs/2409.17589
Current speech-based LLMs are predominantly trained on extensive ASR and TTS datasets, excelling in tasks related to these domains. However, their ability to handle direct speech-to-speech conversations remains notably constrained. These models often
Externí odkaz:
http://arxiv.org/abs/2409.17353
Autor:
Zhou, Yihao, Huang, Zixun, Lee, Timothy Tin-Yan, Wu, Chonglin, Lai, Kelly Ka-Lee, Yang, De, Hung, Alec Lik-hang, Cheng, Jack Chun-Yiu, Lam, Tsz-Ping, Zheng, Yong-ping
Ultrasound curve angle (UCA) measurement provides a radiation-free and reliable evaluation for scoliosis based on ultrasound imaging. However, degraded image quality, especially in difficult-to-image patients, can prevent clinical experts from making
Externí odkaz:
http://arxiv.org/abs/2409.16661
Thanks to advancements in deep learning, speech generation systems now power a variety of real-world applications, such as text-to-speech for individuals with speech disorders, voice chatbots in call centers, cross-linguistic speech translation, etc.
Externí odkaz:
http://arxiv.org/abs/2409.15180
Publikováno v:
in IEEE Transactions on Information Forensics and Security, vol. 19, pp. 7810-7823, 2024
Finger vein recognition technology has become one of the primary solutions for high-security identification systems. However, it still has information leakage problems, which seriously jeopardizes users privacy and anonymity and cause great security
Externí odkaz:
http://arxiv.org/abs/2409.14774
Autor:
Zhai, Siyu, He, Zhibo, Cong, Xiaofeng, Hou, Junming, Gui, Jie, You, Jian Wei, Gong, Xin, Kwok, James Tin-Yau, Tang, Yuan Yan
Learning-based methods for underwater image enhancement (UWIE) have undergone extensive exploration. However, learning-based models are usually vulnerable to adversarial examples so as the UWIE models. To the best of our knowledge, there is no compre
Externí odkaz:
http://arxiv.org/abs/2409.06420
We show that if $\mathcal{A} \subset {[n] \choose n/2}$ with measure bounded away from zero and from one, then the $\Omega(\sqrt{n})$-iterated upper shadows of $\mathcal{A}$ and $\mathcal{A}^c$ intersect in a set of positive measure. This confirms (i
Externí odkaz:
http://arxiv.org/abs/2409.05487
The primary objective of this study was to design the grabbing technique used to determine the vacuum suction gripper and its design parameters for the pocket welting operation in apparel manufacturing. It presents the application of vacuum suction i
Externí odkaz:
http://arxiv.org/abs/2408.09504
A data analyst might worry about generalization if dropping a very small fraction of data points from a study could change its substantive conclusions. Finding the worst-case data subset to drop poses a combinatorial optimization problem. To overcome
Externí odkaz:
http://arxiv.org/abs/2408.09008
If the conclusion of a data analysis is sensitive to dropping very few data points, that conclusion might hinge on the particular data at hand rather than representing a more broadly applicable truth. How could we check whether this sensitivity holds
Externí odkaz:
http://arxiv.org/abs/2408.07240