Zobrazeno 1 - 10
of 51
pro vyhledávání: '"Wan-Lei Zhao"'
Autor:
Yixin Yang, Wan‐Lei Zhao, Yubing Liu, Qin Wang, Ziheng Song, Qinghe Zhuang, Wei Chen, Yu‐Fei Song
Publikováno v:
Advanced Science, Vol 11, Iss 36, Pp n/a-n/a (2024)
Abstract Efficient 2D membranes play a critical role in water purification and desalination. However, most 2D membranes, such as graphene oxide (GO) membranes, tend to swell or disintegrate in liquid, making precise ionic sieving a tough challenge. H
Externí odkaz:
https://doaj.org/article/d0f27c58e79c43a3bbec9f3fb8c41677
Autor:
Huaiying Zhang, Wan-Lei Zhao, Hongqiang Li, Qinghe Zhuang, Zeqian Sun, Dongyuan Cui, Xuejie Chen, Ao Guo, Xiang Ji, Sai An, Wei Chen, Yu-Fei Song
Publikováno v:
Polyoxometalates, Vol 1, Iss 2, Pp 9140011-9140011 (2022)
Covalently modified polyoxometalates (POMs), which benefit from the synergistic effect between POMs and covalently grafted moieties, have received increasing attention in various fields. Recent studies on covalently modified POMs mainly focus on func
Externí odkaz:
https://doaj.org/article/33f48fc49cf848a3a9fc0af61333ccec
Publikováno v:
ACM Transactions on Multimedia Computing, Communications, and Applications. 18:1-19
The performance of instance search relies heavily on the ability to locate and describe a wide variety of object instances in a video/image collection. Due to the lack of a proper mechanism for locating instances and deriving feature representation,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1645b124056ff81c1ca9e0a1cd9239d1
https://doi.org/10.1145/3510004
https://doi.org/10.1145/3510004
Publikováno v:
IEEE Transactions on Multimedia. 24:1909-1921
Nearest neighbor search and k-nearest neighbor graph construction are two fundamental issues that arise from many disciplines such as multimedia information retrieval, data-mining, and machine learning. They become more and more imminent given the bi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::53d3886fea434e69a0ae274f1e97865e
https://doi.org/10.1109/tmm.2021.3073811
https://doi.org/10.1109/tmm.2021.3073811
Publikováno v:
Pattern Recognition Letters. 150:49-56
Deep metric learning maps visually similar images onto nearby locations and visually dissimilar images apart from each other in an embedding manifold. The learning process is mainly based on the supplied image negative and positive training pairs. In
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fb70696666041c8c1a9bb07422b8a27d
https://doi.org/10.1016/j.patrec.2021.06.027
https://doi.org/10.1016/j.patrec.2021.06.027
Publikováno v:
Neurocomputing. 424:117-124
Instance search has been conventionally addressed as an image retrieval issue. In the existing solutions, traditional hand-crafted features and global deep features have been widely adopted. Unfortunately, since the features are not directly derived
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cd09882b15a155f16ca633a2f5b4d99e
https://doi.org/10.1016/j.neucom.2019.11.029
https://doi.org/10.1016/j.neucom.2019.11.029
The detection of 3D objects through a single perspective camera is a challenging issue. The anchor-free and keypoint-based models receive increasing attention recently due to their effectiveness and simplicity. However, most of these methods are vuln
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3c93b71ced3fb6c6a0812cc3978cdecf
Deep metric learning aims to transform input data into an embedding space, where similar samples are close while dissimilar samples are far apart from each other. In practice, samples of new categories arrive incrementally, which requires the periodi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ef5179c8ee0fb755f5a473c585e8ad9a
Publikováno v:
CIKM
NN-Descent is a classic k-NN graph construction approach. It is still widely employed in machine learning, computer vision, and information retrieval tasks due to its efficiency and genericness. However, the current design only works well on CPU. In
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::87a1b5e84d58425f1604e24d6dacf76b
https://doi.org/10.1145/3459637.3482344
https://doi.org/10.1145/3459637.3482344
Publikováno v:
CIKM
In this paper, we revisit the decades-old clustering method k -means. The egg-chicken loop in traditional k -means has been replaced by a pure stochastic optimization procedure. The optimization is undertaken from the perspective of each individual s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::92f81a1bde5271b7a4969040e4b1c908
https://doi.org/10.1145/3459637.3482359
https://doi.org/10.1145/3459637.3482359