Zobrazeno 1 - 10
of 210
pro vyhledávání: '"Shen Siqi"'
Autor:
Shen Siqi
Publikováno v:
Applied Mathematics and Nonlinear Sciences, Vol 7, Iss 1, Pp 719-728 (2021)
Random multi-attribute decision-making is a finite option selection problem related to multiple attributes, and the attribute values are random variables. Its application and supply chain risk management can transform interval decision numbers and fu
Externí odkaz:
https://doaj.org/article/a12c7096c5b84eafbd4d884e1fd2a4ca
Autor:
Xiong, Kezheng, Xiang, Haoen, Xu, Qingshan, Wen, Chenglu, Shen, Siqi, Li, Jonathan, Wang, Cheng
Point cloud registration, a fundamental task in 3D vision, has achieved remarkable success with learning-based methods in outdoor environments. Unsupervised outdoor point cloud registration methods have recently emerged to circumvent the need for cos
Externí odkaz:
http://arxiv.org/abs/2411.01870
Autor:
Dai, Yudi, Wang, Zhiyong, Lin, Xiping, Wen, Chenglu, Xu, Lan, Shen, Siqi, Ma, Yuexin, Wang, Cheng
We introduce HiSC4D, a novel Human-centered interaction and 4D Scene Capture method, aimed at accurately and efficiently creating a dynamic digital world, containing large-scale indoor-outdoor scenes, diverse human motions, rich human-human interacti
Externí odkaz:
http://arxiv.org/abs/2409.04398
Autor:
Shen, Siqi, Logeswaran, Lajanugen, Lee, Moontae, Lee, Honglak, Poria, Soujanya, Mihalcea, Rada
Large language models (LLMs) have demonstrated substantial commonsense understanding through numerous benchmark evaluations. However, their understanding of cultural commonsense remains largely unexamined. In this paper, we conduct a comprehensive ex
Externí odkaz:
http://arxiv.org/abs/2405.04655
Publikováno v:
The 2024 Conference on Empirical Methods in Natural Language Processing
We explore the alignment of values in Large Language Models (LLMs) with specific age groups, leveraging data from the World Value Survey across thirteen categories. Through a diverse set of prompts tailored to ensure response robustness, we find a ge
Externí odkaz:
http://arxiv.org/abs/2404.08760
Autor:
Yan, Ming, Zhang, Yan, Cai, Shuqiang, Fan, Shuqi, Lin, Xincheng, Dai, Yudi, Shen, Siqi, Wen, Chenglu, Xu, Lan, Ma, Yuexin, Wang, Cheng
Comprehensive capturing of human motions requires both accurate captures of complex poses and precise localization of the human within scenes. Most of the HPE datasets and methods primarily rely on RGB, LiDAR, or IMU data. However, solely using these
Externí odkaz:
http://arxiv.org/abs/2403.19501
Point cloud registration, a fundamental task in 3D computer vision, has remained largely unexplored in cross-source point clouds and unstructured scenes. The primary challenges arise from noise, outliers, and variations in scale and density. However,
Externí odkaz:
http://arxiv.org/abs/2312.08664
Autor:
Lin, Xiuhong, Qiu, Changjie, Cai, Zhipeng, Shen, Siqi, Zang, Yu, Liu, Weiquan, Bian, Xuesheng, Müller, Matthias, Wang, Cheng
Event cameras have emerged as a promising vision sensor in recent years due to their unparalleled temporal resolution and dynamic range. While registration of 2D RGB images to 3D point clouds is a long-standing problem in computer vision, no prior wo
Externí odkaz:
http://arxiv.org/abs/2311.18433
Autor:
Shen, Siqi, Ma, Chennan, Li, Chao, Liu, Weiquan, Fu, Yongquan, Mei, Songzhu, Liu, Xinwang, Wang, Cheng
Multi-agent systems are characterized by environmental uncertainty, varying policies of agents, and partial observability, which result in significant risks. In the context of Multi-Agent Reinforcement Learning (MARL), learning coordinated and decent
Externí odkaz:
http://arxiv.org/abs/2311.01753
Autor:
Ignat, Oana, Jin, Zhijing, Abzaliev, Artem, Biester, Laura, Castro, Santiago, Deng, Naihao, Gao, Xinyi, Gunal, Aylin, He, Jacky, Kazemi, Ashkan, Khalifa, Muhammad, Koh, Namho, Lee, Andrew, Liu, Siyang, Min, Do June, Mori, Shinka, Nwatu, Joan, Perez-Rosas, Veronica, Shen, Siqi, Wang, Zekun, Wu, Winston, Mihalcea, Rada
Recent progress in large language models (LLMs) has enabled the deployment of many generative NLP applications. At the same time, it has also led to a misleading public discourse that ``it's all been solved.'' Not surprisingly, this has, in turn, mad
Externí odkaz:
http://arxiv.org/abs/2305.12544