Zobrazeno 1 - 10
of 163
pro vyhledávání: '"Lin, Yijie"'
Facilitated by the powerful feature extraction ability of neural networks, deep clustering has achieved great success in analyzing high-dimensional and complex real-world data. The performance of deep clustering methods is affected by various factors
Externí odkaz:
http://arxiv.org/abs/2406.19602
Existing video-language studies mainly focus on learning short video clips, leaving long-term temporal dependencies rarely explored due to over-high computational cost of modeling long videos. To address this issue, one feasible solution is learning
Externí odkaz:
http://arxiv.org/abs/2401.16702
In recent, some robust contrastive multi-view clustering (MvC) methods have been proposed, which construct data pairs from neighborhoods to alleviate the false negative issue, i.e., some intra-cluster samples are wrongly treated as negative pairs. Al
Externí odkaz:
http://arxiv.org/abs/2308.11164
Autor:
Lin, Yijie
We present an orbifold topological vertex formalism for PT invariants of toric Calabi-Yau 3-orbifolds with transverse $A_{n-1}$ singularities. We give a proof of the orbifold DT/PT Calabi-Yau topological vertex correspondence. As an application, we d
Externí odkaz:
http://arxiv.org/abs/2302.02342
In this paper, we study a novel and widely existing problem in graph matching (GM), namely, Bi-level Noisy Correspondence (BNC), which refers to node-level noisy correspondence (NNC) and edge-level noisy correspondence (ENC). In brief, on the one han
Externí odkaz:
http://arxiv.org/abs/2212.04085
Autor:
Lin, Yijie1 (AUTHOR) p1263670@o365.fcu.edu.tw, Liu, Jui-Chuan1 (AUTHOR) p1200318@o365.fcu.edu.tw, Chang, Ching-Chun2 (AUTHOR) ccc@fcu.edu.tw, Chang, Chin-Chen1 (AUTHOR) ccc@o365.fcu.edu.tw
Publikováno v:
Future Internet. Aug2024, Vol. 16 Issue 8, p297. 18p.
Autor:
Lin, Zili, Jin, Yuhan, Xiao, Zhenjun, Li, Yulin, Lin, Yijie, Chen, Zhihong, Zhuang, Xiaoqin, Mo, Peiying, Liu, Yang, Chen, Ping, Lv, Wenying, Liu, Guoguang
Publikováno v:
In Separation and Purification Technology 2 July 2024 339
Image hazing aims to render a hazy image from a given clean one, which could be applied to a variety of practical applications such as gaming, filming, photographic filtering, and image dehazing. To generate plausible haze, we study two less-touched
Externí odkaz:
http://arxiv.org/abs/2107.06681
Publikováno v:
In Journal of Molecular Liquids 1 April 2024 399
Autor:
Lin, Yijie
We construct relative moduli spaces of semistable pairs on a family of projective Deligne-Mumford stacks. We define moduli stacks of stable orbifold Pandharipande-Thomas pairs on stacks of expanded degenerations and pairs, and then show they are sepa
Externí odkaz:
http://arxiv.org/abs/2104.08780