Zobrazeno 1 - 10
of 133
pro vyhledávání: '"Yang, Yu Qi"'
Data diversity and abundance are essential for improving the performance and generalization of models in natural language processing and 2D vision. However, 3D vision domain suffers from the lack of 3D data, and simply combining multiple 3D datasets
Externí odkaz:
http://arxiv.org/abs/2402.14215
Autor:
Yang, Yu-Qi, Guo, Yu-Xiao, Xiong, Jian-Yu, Liu, Yang, Pan, Hao, Wang, Peng-Shuai, Tong, Xin, Guo, Baining
The use of pretrained backbones with fine-tuning has been successful for 2D vision and natural language processing tasks, showing advantages over task-specific networks. In this work, we introduce a pretrained 3D backbone, called {\SST}, for 3D indoo
Externí odkaz:
http://arxiv.org/abs/2304.06906
Autor:
Sun, Chun-Yu, Yang, Yu-Qi, Guo, Hao-Xiang, Wang, Peng-Shuai, Tong, Xin, Liu, Yang, Shum, Heung-Yeung
The lack of fine-grained 3D shape segmentation data is the main obstacle to developing learning-based 3D segmentation techniques. We propose an effective semi-supervised method for learning 3D segmentations from a few labeled 3D shapes and a large am
Externí odkaz:
http://arxiv.org/abs/2204.08824
Autor:
GAO, Guo-jian, GUO, Hui-jun, LI, Xin, CHEN, Yao-kai, TAN, Xing-hua, YANG, Yu-qi, MA, Jian-ping, LIU, Shui-qing, FENG, Quan-sheng, ZOU, Wen, DONG, Ji-peng, WANG, Jian, LIU, Ying
Publikováno v:
In World Journal of Acupuncture – Moxibustion October 2024 34(4):318-324
Autor:
Ye, Mei-Zhen, Wan, Zhen-Ling, Ruan, Hong-Yu, Yang, Yu-Qi, Chen, Ying, Chen, Lin, Huang, Shuai, Zhou, Xian-Li
Publikováno v:
In Phytochemistry July 2024 223
Sparse voxel-based 3D convolutional neural networks (CNNs) are widely used for various 3D vision tasks. Sparse voxel-based 3D CNNs create sparse non-empty voxels from the 3D input and perform 3D convolution operations on them only. We propose a simpl
Externí odkaz:
http://arxiv.org/abs/2108.06925
Multilayer perceptrons (MLPs) have been successfully used to represent 3D shapes implicitly and compactly, by mapping 3D coordinates to the corresponding signed distance values or occupancy values. In this paper, we propose a novel positional encodin
Externí odkaz:
http://arxiv.org/abs/2106.01553
Autor:
Xu, Jia-Hui, Wang, Yi-Jia, Shi, Yu-Kun, Ding, Shan, Yang, Yu-Qi, Cui, Di, Yang, Guang-Sheng, Xu, Yan-Hong, Jiang, Chun-Jie
Publikováno v:
In Journal of Solid State Chemistry March 2024 331
Publikováno v:
Journal of Applied Physics; 5/28/2024, Vol. 135 Issue 20, p1-11, 11p
Although unsupervised feature learning has demonstrated its advantages to reducing the workload of data labeling and network design in many fields, existing unsupervised 3D learning methods still cannot offer a generic network for various shape analy
Externí odkaz:
http://arxiv.org/abs/2008.01068