Zobrazeno 1 - 10
of 152
pro vyhledávání: '"Fang, Xiangzhong"'
The curvature of ODE trajectories in diffusion models hinders their ability to generate high-quality images in a few number of function evaluations (NFE). In this paper, we propose a novel and effective approach to reduce trajectory curvature by util
Externí odkaz:
http://arxiv.org/abs/2409.17487
Probabilistic Results on the Architecture of Mathematical Reasoning Aligned by Cognitive Alternation
We envision a machine capable of solving mathematical problems. Dividing the quantitative reasoning system into two parts: thought processes and cognitive processes, we provide probabilistic descriptions of the architecture.
Externí odkaz:
http://arxiv.org/abs/2308.08714
Autor:
Tong, Zhengyan, Wang, Xiaohang, Yuan, Shengchao, Chen, Xuanhong, Wang, Junjie, Fang, Xiangzhong
This paper proposes a novel stroke-based rendering (SBR) method that translates images into vivid oil paintings. Previous SBR techniques usually formulate the oil painting problem as pixel-wise approximation. Different from this technique route, we t
Externí odkaz:
http://arxiv.org/abs/2209.13219
Autor:
Zhao, Linglan, Guo, Dashan, Xu, Yunlu, Qiao, Liang, Cheng, Zhanzhan, Pu, Shiliang, Niu, Yi, Fang, Xiangzhong
Few-shot learning (FSL) aims to learn models that generalize to novel classes with limited training samples. Recent works advance FSL towards a scenario where unlabeled examples are also available and propose semi-supervised FSL methods. Another line
Externí odkaz:
http://arxiv.org/abs/2110.11128
Autor:
Sun, Yang1 (AUTHOR) sunyang199610@163.com, Fang, Xiangzhong1 (AUTHOR)
Publikováno v:
Statistical Papers. Jun2024, Vol. 65 Issue 4, p1901-1926. 26p.
Publikováno v:
In Knowledge-Based Systems 25 November 2023 280
We address the problem of spatio-temporal action detection in videos. Existing methods commonly either ignore temporal context in action recognition and localization, or lack the modelling of flexible shapes of action tubes. In this paper, we propose
Externí odkaz:
http://arxiv.org/abs/1907.01847
Autor:
Zhang, Yu, Fang, Xiangzhong
Given $n=mk$ $iid$ samples from $N(\theta,\sigma^2)$ with $\theta$ and $\sigma^2$ unknown, we have two ways to construct $t$-based confidence intervals for $\theta$. The traditional method is to treat these $n$ samples as $n$ groups and calculate the
Externí odkaz:
http://arxiv.org/abs/1812.03214
Autor:
Sun, Yang1 (AUTHOR) sunyang199610@163.com, Fang, Xiangzhong1 (AUTHOR)
Publikováno v:
Communications in Statistics: Simulation & Computation. 2024, Vol. 53 Issue 10, p4738-4752. 15p.