Zobrazeno 1 - 10
of 53
pro vyhledávání: '"Xie, Linhai"'
Autor:
Ding, Ning, Qu, Shang, Xie, Linhai, Li, Yifei, Liu, Zaoqu, Zhang, Kaiyan, Xiong, Yibai, Zuo, Yuxin, Chen, Zhangren, Hua, Ermo, Lv, Xingtai, Sun, Youbang, Li, Yang, Li, Dong, He, Fuchu, Zhou, Bowen
With the development of artificial intelligence, its contribution to science is evolving from simulating a complex problem to automating entire research processes and producing novel discoveries. Achieving this advancement requires both specialized g
Externí odkaz:
http://arxiv.org/abs/2411.03743
Spiking Neural Networks (SNNs) have gained enormous popularity in the field of artificial intelligence due to their low power consumption. However, the majority of SNN methods directly inherit the structure of Artificial Neural Networks (ANN), usuall
Externí odkaz:
http://arxiv.org/abs/2411.00902
Autor:
Hu, Qingyong, Yang, Bo, Xie, Linhai, Rosa, Stefano, Guo, Yulan, Wang, Zhihua, Trigoni, Niki, Markham, Andrew
We study the problem of efficient semantic segmentation of large-scale 3D point clouds. By relying on expensive sampling techniques or computationally heavy pre/post-processing steps, most existing approaches are only able to be trained and operate o
Externí odkaz:
http://arxiv.org/abs/2107.02389
In this paper, we teach machines to understand visuals and natural language by learning the mapping between sentences and noisy video snippets without explicit annotations. Firstly, we define a self-supervised learning framework that captures the cro
Externí odkaz:
http://arxiv.org/abs/2011.09634
Autor:
Hu, Qingyong, Yang, Bo, Xie, Linhai, Rosa, Stefano, Guo, Yulan, Wang, Zhihua, Trigoni, Niki, Markham, Andrew
We study the problem of efficient semantic segmentation for large-scale 3D point clouds. By relying on expensive sampling techniques or computationally heavy pre/post-processing steps, most existing approaches are only able to be trained and operate
Externí odkaz:
http://arxiv.org/abs/1911.11236
Deep Reinforcement Learning (DRL) has been applied successfully to many robotic applications. However, the large number of trials needed for training is a key issue. Most of existing techniques developed to improve training efficiency (e.g. imitation
Externí odkaz:
http://arxiv.org/abs/1812.05027
Autor:
Xie, Linhai, Miao, Yishu, Wang, Sen, Blunsom, Phil, Wang, Zhihua, Chen, Changhao, Markham, Andrew, Trigoni, Niki
Due to the sparse rewards and high degree of environment variation, reinforcement learning approaches such as Deep Deterministic Policy Gradient (DDPG) are plagued by issues of high variance when applied in complex real world environments. We present
Externí odkaz:
http://arxiv.org/abs/1811.10756
Autor:
Wang, Zhihua, Rosa, Stefano, Miao, Yishu, Lai, Zihang, Xie, Linhai, Markham, Andrew, Trigoni, Niki
Humans are able to make rich predictions about the future dynamics of physical objects from a glance. On the other hand, most existing computer vision approaches require strong assumptions about the underlying system, ad-hoc modeling, or annotated da
Externí odkaz:
http://arxiv.org/abs/1809.03330
Autor:
Wang, Zhihua, Rosa, Stefano, Xie, Linhai, Yang, Bo, Wang, Sen, Trigoni, Niki, Markham, Andrew
Modelling the physical properties of everyday objects is a fundamental prerequisite for autonomous robots. We present a novel generative adversarial network (Defo-Net), able to predict body deformations under external forces from a single RGB-D image
Externí odkaz:
http://arxiv.org/abs/1804.05928
Obstacle avoidance is a fundamental requirement for autonomous robots which operate in, and interact with, the real world. When perception is limited to monocular vision avoiding collision becomes significantly more challenging due to the lack of 3D
Externí odkaz:
http://arxiv.org/abs/1706.09829