Zobrazeno 1 - 10
of 113
pro vyhledávání: '"Cewu Lu"'
Autor:
Chunpeng Jiang, Wenqiang Xu, Yutong Li, Zhenjun Yu, Longchun Wang, Xiaotong Hu, Zhengyi Xie, Qingkun Liu, Bin Yang, Xiaolin Wang, Wenxin Du, Tutian Tang, Dongzhe Zheng, Siqiong Yao, Cewu Lu, Jingquan Liu
Publikováno v:
Nature Communications, Vol 15, Iss 1, Pp 1-14 (2024)
Abstract Capturing forceful interaction with deformable objects during manipulation benefits applications like virtual reality, telemedicine, and robotics. Replicating full hand-object states with complete geometry is challenging because of the occlu
Externí odkaz:
https://doaj.org/article/ca01462e48e14d5fb49086af94abe34d
Publikováno v:
IET Computer Vision, Vol 18, Iss 7, Pp 1057-1067 (2024)
Abstract The authors study the problem of reconstructing detailed 3D human surfaces in various poses and clothing from images. The parametric human body allows accurate 3D clothed human reconstruction. However, the offset of large and loose clothing
Externí odkaz:
https://doaj.org/article/5bc38c9988a84aa1a0cfd0ae92bae57c
Autor:
Jimin Xu, Nuanxin Hong, Zhening Xu, Zhou Zhao, Chao Wu, Kun Kuang, Jiaping Wang, Mingjie Zhu, Jingren Zhou, Kui Ren, Xiaohu Yang, Cewu Lu, Jian Pei, Harry Shum
Publikováno v:
Engineering, Vol 25, Iss , Pp 66-76 (2023)
In recent years, data has become one of the most important resources in the digital economy. Unlike traditional resources, the digital nature of data makes it difficult to value and contract. Therefore, establishing an efficient and standard data-tra
Externí odkaz:
https://doaj.org/article/14c919f7f5344f47935e3d27fa02a3d5
Autor:
Zexin Chen, Ruihan Zhang, Hao-Shu Fang, Yu E. Zhang, Aneesh Bal, Haowen Zhou, Rachel R. Rock, Nancy Padilla-Coreano, Laurel R. Keyes, Haoyi Zhu, Yong-Lu Li, Takaki Komiyama, Kay M. Tye, Cewu Lu
Publikováno v:
Frontiers in Behavioral Neuroscience, Vol 17 (2023)
Computer vision has emerged as a powerful tool to elevate behavioral research. This protocol describes a computer vision machine learning pipeline called AlphaTracker, which has minimal hardware requirements and produces reliable tracking of multiple
Externí odkaz:
https://doaj.org/article/46ba63e31e9349eb9219b04121a340ea
Autor:
Cewu Lu, Shiquan Wang
Publikováno v:
Engineering, Vol 6, Iss 3, Pp 221-226 (2020)
Externí odkaz:
https://doaj.org/article/3d3f1eddb9784acd87ca0cd1ce11faba
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 36:2298-2306
Data augmentation is an efficient way to elevate 3D object detection performance. In this paper, we propose a simple but effective online crop-and-paste data augmentation pipeline for structured 3D point cloud scenes, named CorrelaBoost. Observing th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::afd33fa392908756199bd418c881dd5e
https://doi.org/10.1609/aaai.v36i2.20128
https://doi.org/10.1609/aaai.v36i2.20128
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 36:2044-2052
We study the unsupervised representation learning for the semantic segmentation task. Different from previous works that aim at providing unsupervised pre-trained backbones for segmentation models which need further supervised fine-tune, here, we foc
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0d3f245e754021be4655adc51f6b3a22
https://doi.org/10.1609/aaai.v36i2.20100
https://doi.org/10.1609/aaai.v36i2.20100
Publikováno v:
IEEE Robotics and Automation Letters. 7:842-849
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::98bba486542bd5c1b199848d65e3f7d0
https://doi.org/10.1109/lra.2021.3133862
https://doi.org/10.1109/lra.2021.3133862
Publikováno v:
IEEE Transactions on Image Processing. 31:1072-1083
Human life is populated with articulated objects. Current Category-level Articulation Pose Estimation (CAPE) methods are studied under the single-instance setting with a fixed kinematic structure for each category. Considering these limitations, we a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::247a79795ec38aed7f07acb5b8f8c80d
https://doi.org/10.1109/tip.2021.3138644
https://doi.org/10.1109/tip.2021.3138644
Publikováno v:
IEEE Robotics and Automation Letters. 6:8718-8725
Suction is an important solution for the long-standing robotic grasping problem. Compared with other kinds of grasping, suction grasping is easier to represent and often more reliable in practice. Though preferred in many scenarios, it is not fully i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5bd37c8b4a17ca6ec56aa75c89e3664e
https://doi.org/10.1109/lra.2021.3115406
https://doi.org/10.1109/lra.2021.3115406