Výsledky vyhledávání - "Zhou, Zhuoran"

Report

Detection-Triggered Recursive Impact Mitigation against Secondary False Data Injection Attacks in Microgrids

Autor: Liu, Mengxiang, Zhang, Xin, Zhang, Rui, Zhou, Zhuoran, Zhang, Zhenyong, Deng, Ruilong

The cybersecurity of microgrid has received widespread attentions due to the frequently reported attack accidents against distributed energy resource (DER) manufactures. Numerous impact mitigation schemes have been proposed to reduce or eliminate the

Externí odkaz: http://arxiv.org/abs/2407.06948

Zobrazit plný text záznamu

Report

Efficient Domain Adaptation via Generative Prior for 3D Infant Pose Estimation

Autor: Zhou, Zhuoran, Jiang, Zhongyu, Chai, Wenhao, Yang, Cheng-Yen, Li, Lei, Hwang, Jenq-Neng

Although 3D human pose estimation has gained impressive development in recent years, only a few works focus on infants, that have different bone lengths and also have limited data. Directly applying adult pose estimation models typically achieves low

Externí odkaz: http://arxiv.org/abs/2311.12043

Zobrazit plný text záznamu

Report

CValues: Measuring the Values of Chinese Large Language Models from Safety to Responsibility

Autor: Xu, Guohai, Liu, Jiayi, Yan, Ming, Xu, Haotian, Si, Jinghui, Zhou, Zhuoran, Yi, Peng, Gao, Xing, Sang, Jitao, Zhang, Rong, Zhang, Ji, Peng, Chao, Huang, Fei, Zhou, Jingren

With the rapid evolution of large language models (LLMs), there is a growing concern that they may pose risks or have negative social impacts. Therefore, evaluation of human values alignment is becoming increasingly important. Previous work mainly fo

Externí odkaz: http://arxiv.org/abs/2307.09705

Zobrazit plný text záznamu

Report

Back to Optimization: Diffusion-based Zero-Shot 3D Human Pose Estimation

Autor: Jiang, Zhongyu, Zhou, Zhuoran, Li, Lei, Chai, Wenhao, Yang, Cheng-Yen, Hwang, Jenq-Neng

Learning-based methods have dominated the 3D human pose estimation (HPE) tasks with significantly better performance in most benchmarks than traditional optimization-based methods. Nonetheless, 3D HPE in the wild is still the biggest challenge for le

Externí odkaz: http://arxiv.org/abs/2307.03833

Zobrazit plný text záznamu