Zobrazeno 1 - 10
of 199
pro vyhledávání: '"ZHANYU MA"'
Autor:
Yujun TONG, Heqing WANG, Yueheng LUO, Wenxin NING, Mandan GUAN, Wenqing YU, Keyan HUANG, Jiaxun ZHANG, Zhanyu MA
Publikováno v:
智能科学与技术学报, Vol 5, Pp 380-388 (2023)
Domain generalization is an important and challenging problem in computer vision, arising from the distribution shift of real-world data.In practical applications, it is common to encounter training and testing data from different domains, and the di
Externí odkaz:
https://doaj.org/article/746b41561e374a9a8707535a14b0eb61
Publikováno v:
Journal of High Energy Physics, Vol 2023, Iss 4, Pp 1-14 (2023)
Abstract We compute the leading correction to entanglement entropy in T T ¯ $$ T\overline{T} $$ deformed massive QFTs. We show that both for massive scalar and Dirac fermion, the leading order correction to the entanglement entropy of half space com
Externí odkaz:
https://doaj.org/article/ee6be2a89b7d4f2d8c346e40264e7c45
Publikováno v:
IEEE Access, Vol 8, Pp 169146-169159 (2020)
Traditional video captioning requests a holistic description of the video, yet the detailed descriptions of the specific objects may not be available. Besides, most methods adopt frame-level inter-tangled features among objects and ambiguous descript
Externí odkaz:
https://doaj.org/article/f27229505e5e4ead935efeb4c4ea6bfb
Publikováno v:
IEEE Access, Vol 8, Pp 199882-199898 (2020)
With the rapid development of network infrastructures and personal electronic products, big data generated from the Internet, sensing networks, and other equipment are rapidly growing and have received increasing attention in recent years. Recently,
Externí odkaz:
https://doaj.org/article/a1108a7f7db4479ebad66ede5dccf570
Publikováno v:
IEEE Access, Vol 7, Pp 59728-59736 (2019)
Identifying shoe-print impressions in the scene of crime (SoC) from database images is a challenging problem in forensic science due to the complicated impressing surface, the partial absence of on-site impressions, and the huge domain gap between th
Externí odkaz:
https://doaj.org/article/c33ea1c1adb44999a8e534566779b9cf
Publikováno v:
IEEE Access, Vol 6, Pp 31481-31485 (2018)
Computer vision is an interdisciplinary field that deals with how computers can be made to gain high-level understanding from digital images or videos. From the perspective of engineering, it seeks to automate tasks that the human visual system can d
Externí odkaz:
https://doaj.org/article/88207313cfb14971845dc4f6966cb2e5
Publikováno v:
IEEE Access, Vol 5, Pp 4779-4787 (2017)
With the development of speech synthesis techniques, automatic speaker verification systems face the serious challenge of spoofing attack. In order to improve the reliability of speaker verification systems, we develop a new filter bank-based cepstra
Externí odkaz:
https://doaj.org/article/1a137fcec578423da0236f57ca436f73
Publikováno v:
IEEE Access, Vol 4, Pp 2732-2737 (2016)
Many studies demonstrated that the DNA methylation, which occurs in the context of a CpG, has strong correlation with diseases, including cancer. There is a strong interest in analyzing the DNA methylation data to find how to distinguish different su
Externí odkaz:
https://doaj.org/article/547dbf0ee96a4b4bba44d189a9802069
Publikováno v:
IEEE Access, Vol 4, Pp 9733-9739 (2016)
In this paper, we propose a novel probabilistic method for the task of text-independent speaker identification (SI). In order to capture the dynamic information during SI, we design super-mel-frequency cepstral coefficients (MFCCs) features by cascad
Externí odkaz:
https://doaj.org/article/06db8445b242460b91cfa04981319a61
Publikováno v:
Algorithms, Vol 8, Iss 4, Pp 1143-1174 (2015)
Generative algorithms for random graphs have yielded insights into the structure and evolution of real-world networks. Most networks exhibit a well-known set of properties, such as heavy-tailed degree distributions, clustering and community formation
Externí odkaz:
https://doaj.org/article/21d7626848de4dbd94c58b40de2ca4c7