Zobrazeno 1 - 10
of 188
pro vyhledávání: '"Lu, Zhengyang"'
Classical Chinese poetry and painting represent the epitome of artistic expression, but the abstract and symbolic nature of their relationship poses a significant challenge for computational translation. Most existing methods rely on large-scale pair
Externí odkaz:
http://arxiv.org/abs/2410.19307
Autor:
Lu, Zhengyang, Chen, Ying
Monocular depth estimation from a single image is an ill-posed problem for computer vision due to insufficient reliable cues as the prior knowledge. Besides the inter-frame supervision, namely stereo and adjacent frames, extensive prior information i
Externí odkaz:
http://arxiv.org/abs/2404.07176
Restart policy is an important technique used in modern Conflict-Driven Clause Learning (CDCL) solvers, wherein some parts of the solver state are erased at certain intervals during the run of the solver. In most solvers, variable activities are pres
Externí odkaz:
http://arxiv.org/abs/2404.03753
Modern SMT solvers, such as Z3, offer user-controllable strategies, enabling users to tailor solving strategies for their unique set of instances, thus dramatically enhancing solver performance for their use case. However, this approach of strategy c
Externí odkaz:
http://arxiv.org/abs/2401.17159
This paper introduces AlphaMapleSAT, a novel Monte Carlo Tree Search (MCTS) based Cube-and-Conquer (CnC) SAT solving method aimed at efficiently solving challenging combinatorial problems. Despite the tremendous success of CnC solvers in solving a va
Externí odkaz:
http://arxiv.org/abs/2401.13770
Autor:
Lu, Zhengyang, Chen, Ying
Significant attention has been attracted to deep learning-based depth estimates. Dynamic objects become the most hard problems in inter-frame-supervised depth estimates due to the uncertainty in adjacent frames. Thus, integrating optical flow informa
Externí odkaz:
http://arxiv.org/abs/2310.00011
Autor:
Lu, Zhengyang, Chen, Ying
Deep-learning-based approaches to depth estimation are rapidly advancing, offering superior performance over existing methods. To estimate the depth in real-world scenarios, depth estimation models require the robustness of various noise environments
Externí odkaz:
http://arxiv.org/abs/2204.02386
Autor:
Lu, Tao, Zhu, Changsheng, Cui, Hao, Meng, Yanhai, Yang, Qiulan, Lu, Zhengyang, Song, Yunhu, Wang, Shuiyun
Publikováno v:
In International Journal of Cardiology 15 January 2025 419
Autor:
Lu, Zhengyang, Mei, Gui, Zhong, Fangfang, Gu, Yingzi, Xi, Jiahe, Chen, Xianghong, Xu, Jing, Huang, Xianju, Yang, Guangzhong, Chen, Yu
Publikováno v:
In Phytochemistry January 2025 229
In this paper, we propose a new approach for stochastic control problems arising from utility maximization. The main idea is to directly start from the dynamical programming equation and compute the conditional expectation using a novel representatio
Externí odkaz:
http://arxiv.org/abs/2202.12745