Zobrazeno 1 - 10
of 778
pro vyhledávání: '"Hua, Guang"'
Virtual faces are crucial content in the metaverse. Recently, attempts have been made to generate virtual faces for privacy protection. Nevertheless, these virtual faces either permanently remove the identifiable information or map the original ident
Externí odkaz:
http://arxiv.org/abs/2409.03434
Box-free model watermarking is an emerging technique to safeguard the intellectual property of deep learning models, particularly those for low-level image processing tasks. Existing works have verified and improved its effectiveness in several aspec
Externí odkaz:
http://arxiv.org/abs/2405.09863
Object detection is critical in autonomous driving, and it is more practical yet challenging to localize objects of unknown categories: an endeavour known as Class-Agnostic Object Detection (CAOD). Existing studies on CAOD predominantly rely on ordin
Externí odkaz:
http://arxiv.org/abs/2404.05285
Most of the artificial lights fluctuate in response to the grid's alternating current and exhibit subtle variations in terms of both intensity and spectrum, providing the potential to estimate the Electric Network Frequency (ENF) from conventional fr
Externí odkaz:
http://arxiv.org/abs/2305.02597
Autor:
Hua, Guang, Teoh, Andrew Beng Jin
Publikováno v:
Pattern Recognition, Vol. 144, Dec. 2023
Backdoor watermarking is a promising paradigm to protect the copyright of deep neural network (DNN) models. In the existing works on this subject, researchers have intensively focused on watermarking robustness, while the concept of fidelity, which i
Externí odkaz:
http://arxiv.org/abs/2208.00563
Publikováno v:
In Digital Communications and Networks August 2024 10(4):1121-1130
Autor:
Hua‐guang Pan, Han‐lin Fang, Chan Zhu, Si Li, Huan Yi, Xing Zhang, Xiang‐yu Yin, Yun‐jie Song, Dongsheng Chen, Chun‐tong Yin
Publikováno v:
Cancer Medicine, Vol 13, Iss 9, Pp n/a-n/a (2024)
Abstract Background The molecular and immunological characteristics of primary tumors and positive lymph nodes in esophageal squamous cell carcinoma (ESCC) are unknown and the relationship with recurrence is unclear, which this study attempted to exp
Externí odkaz:
https://doaj.org/article/9e8b159d025b42df96247f1533ebae53
The constant Q transform (CQT) has been shown to be one of the most effective speech signal pre-transforms to facilitate synthetic speech detection, followed by either hand-crafted (subband) constant Q cepstral coefficient (CQCC) feature extraction a
Externí odkaz:
http://arxiv.org/abs/2106.06341
Autor:
Pan, Hua‐guang1 (AUTHOR), Fang, Han‐lin1 (AUTHOR), Zhu, Chan2 (AUTHOR), Li, Si2 (AUTHOR), Yi, Huan2 (AUTHOR), Zhang, Xing2 (AUTHOR), Yin, Xiang‐yu2,3 (AUTHOR), Song, Yun‐jie2 (AUTHOR), Chen, Dongsheng2 (AUTHOR), Yin, Chun‐tong1 (AUTHOR) chuntongyin@outlook.com
Publikováno v:
Cancer Medicine. May2024, Vol. 13 Issue 9, p1-14. 14p.
Publikováno v:
IEEE Transactions on Information Forensics and Security, 2021
We present a framework for robust electric network frequency (ENF) extraction from real-world audio recordings, featuring multi-tone ENF harmonic enhancement and graph-based optimal harmonic selection. Specifically, We first extend the recently devel
Externí odkaz:
http://arxiv.org/abs/2011.03414