Zobrazeno 51 - 60
of 422
pro vyhledávání: '"Yang, Guang"'
Multi-exposure image fusion aims to generate a single high-dynamic image by integrating images with different exposures. Existing deep learning-based multi-exposure image fusion methods primarily focus on spatial domain fusion, neglecting the global
Externí odkaz:
http://arxiv.org/abs/2312.10604
Autor:
Zhou, Yao, Yin, Zhen-Qiang, Shan, Yang-Guang, Wang, Ze-Hao, Wang, Shuang, Chen, Wei, Guo, Guang-Can, Han, Zheng-Fu
Quantum key distribution (QKD) stands as a pioneering method for establishing information-theoretically secure communication channels by utilizing the principles of quantum mechanics. In the security proof of QKD, the phase error rate serves as a cri
Externí odkaz:
http://arxiv.org/abs/2312.06385
Shape modeling of volumetric data is essential for medical image analysis and computer-aided intervention. In practice, automated shape reconstruction cannot always achieve satisfactory results due to limited image resolution and a lack of sufficient
Externí odkaz:
http://arxiv.org/abs/2312.06164
Large Language Models (LLMs) have demonstrated remarkable potential in code generation. The integration of Chain of Thought (CoT) reasoning can further boost their performance. However, current CoT methods often require manual writing or LLMs with ov
Externí odkaz:
http://arxiv.org/abs/2312.05562
Infrared and visible image fusion aims at generating a fused image containing the intensity and detail information of source images, and the key issue is effectively measuring and integrating the complementary information of multi-modality images fro
Externí odkaz:
http://arxiv.org/abs/2312.04328
Using the atomic cluster expansion (ACE) framework, we develop a machine learning interatomic potential for fast and accurately modelling the phonon transport properties of wurtzite aluminum nitride. The predictive power of the ACE potential against
Externí odkaz:
http://arxiv.org/abs/2311.11990
The previous smart contract code comment (SCC) generation approaches can be divided into two categories: fine-tuning paradigm-based approaches and information retrieval-based approaches. However, for the fine-tuning paradigm-based approaches, the per
Externí odkaz:
http://arxiv.org/abs/2311.10388
The fluid dynamics of liquid droplet impact on surfaces hold significant relevance to various industrial applications. However, high impact velocities introduce compressible effects, leading to material erosion. A gap in understanding and modeling th
Externí odkaz:
http://arxiv.org/abs/2311.09328
Autor:
Yeung, Michael, Watts, Todd, Tan, Sean YW, Ferreira, Pedro F., Scott, Andrew D., Nielles-Vallespin, Sonia, Yang, Guang
Stain variation is a unique challenge associated with automated analysis of digital pathology. Numerous methods have been developed to improve the robustness of machine learning methods to stain variation, but comparative studies have demonstrated li
Externí odkaz:
http://arxiv.org/abs/2311.06552
Autor:
Zhou, Shengzhe, Lee, Zejian, Zhang, Shengyuan, Hou, Lefan, Yang, Changyuan, Yang, Guang, Yang, Zhiyuan, Sun, Lingyun
Denoising Diffusion models have exhibited remarkable capabilities in image generation. However, generating high-quality samples requires a large number of iterations. Knowledge distillation for diffusion models is an effective method to address this
Externí odkaz:
http://arxiv.org/abs/2311.03830