Zobrazeno 1 - 10
of 117
pro vyhledávání: '"Yan, Siming"'
By combining natural language understanding, generation capabilities, and breadth of knowledge of large language models with image perception, recent large vision language models (LVLMs) have shown unprecedented visual reasoning capabilities. However
Externí odkaz:
http://arxiv.org/abs/2402.06118
A promising direction for pre-training 3D point clouds is to leverage the massive amount of data in 2D, whereas the domain gap between 2D and 3D creates a fundamental challenge. This paper proposes a novel approach to point-cloud pre-training that le
Externí odkaz:
http://arxiv.org/abs/2306.02558
Autor:
Yan, Siming, Yang, Yuqi, Guo, Yuxiao, Pan, Hao, Wang, Peng-shuai, Tong, Xin, Liu, Yang, Huang, Qixing
Masked autoencoders (MAE) have recently been introduced to 3D self-supervised pretraining for point clouds due to their great success in NLP and computer vision. Unlike MAEs used in the image domain, where the pretext task is to restore features at t
Externí odkaz:
http://arxiv.org/abs/2304.06911
Publikováno v:
In Chemical Engineering Science 5 October 2024 298
Autor:
Cheng, Xingtao, He, Yi, Yan, Siming, Song, Ruxia, Li, Zhiyuan, Yan, Liping, Li, Hongjie, Wei, Kaijun, Yuan, Qing, Xu, Shijun
Publikováno v:
In Vacuum October 2024 228
Autor:
Yan, Siming, Yang, Zhenpei, Li, Haoxiang, Song, Chen, Guan, Li, Kang, Hao, Hua, Gang, Huang, Qixing
This paper advocates the use of implicit surface representation in autoencoder-based self-supervised 3D representation learning. The most popular and accessible 3D representation, i.e., point clouds, involves discrete samples of the underlying contin
Externí odkaz:
http://arxiv.org/abs/2201.00785
Autor:
Cheng, Xingtao, He, Yi, Yan, Siming, Yan, Liping, Li, Zhiyuan, Xu, Shijun, Wei, Kaijun, Fan, Yi, Chen, Quangang, Peng, Wanwan
Publikováno v:
In Tribology International December 2024 200
Autor:
Yang, Haitao, Zhang, Zaiwei, Yan, Siming, Huang, Haibin, Ma, Chongyang, Zheng, Yi, Bajaj, Chandrajit, Huang, Qixing
Developing deep neural networks to generate 3D scenes is a fundamental problem in neural synthesis with immediate applications in architectural CAD, computer graphics, as well as in generating virtual robot training environments. This task is challen
Externí odkaz:
http://arxiv.org/abs/2108.13499
Autor:
Xu, Shijun, He, Yi, Yan, Siming, He, Teng, Li, Hongjie, Gao, Yuan, Chen, Wen, Yan, Jin, Wu, Guiyang, Yuan, Xi
Publikováno v:
In Electrochimica Acta 20 June 2024 490
This paper introduces HPNet, a novel deep-learning approach for segmenting a 3D shape represented as a point cloud into primitive patches. The key to deep primitive segmentation is learning a feature representation that can separate points of differe
Externí odkaz:
http://arxiv.org/abs/2105.10620