no code implementations • 8 Feb 2024 • Ying Zang, Chenglong Fu, Runlong Cao, Didi Zhu, Min Zhang, WenJun Hu, Lanyun Zhu, Tianrun Chen
This pioneering work lays the groundwork for future research in semi-supervised learning for referring expression segmentation.
no code implementations • 8 Jan 2024 • Danqi Yan, Qing Gao, Yuepeng Qian, Xinxing Chen, Chenglong Fu, Yuquan Leng
Additionally, we leverage the architecture of current diffusion models to convert the distribution of noisy 3D poses into ground truth 3D poses.
no code implementations • 22 Sep 2023 • Tianrun Chen, Chenglong Fu, Ying Zang, Lanyun Zhu, Jia Zhang, Papa Mao, Lingyun Sun
In this work, we introduce a novel end-to-end approach, Deep3DSketch+, which performs 3D modeling using only a single free-hand sketch without inputting multiple sketches or view information.
1 code implementation • 15 Apr 2022 • Kuangen Zhang, Jiahong Chen, Jing Wang, Xinxing Chen, Yuquan Leng, Clarence W. de Silva, Chenglong Fu
EDH mitigates the divergence between labeled data of source subjects and unlabeled data of target subjects to accurately classify the locomotion modes of target subjects without labeling data.
no code implementations • 29 Aug 2020 • Kuangen Zhang, Jongwoo Lee, Zhimin Hou, Clarence W. de Silva, Chenglong Fu, Neville Hogan
This paper focuses on the latter because the structured policy is more intuitive and can inherit insights from previous model-based controllers.
no code implementations • 29 Feb 2020 • Xia Wu, Haiyuan Liu, Ziqi Liu, Mingdong Chen, Fang Wan, Chenglong Fu, Harry Asada, Zheng Wang, Chaoyang Song
Many researchers have identified robotics as a potential solution to the aging population faced by many developed and developing countries.
no code implementations • 7 Feb 2020 • Zhimin Hou, Kuangen Zhang, Yi Wan, Dongyu Li, Chenglong Fu, Haoyong Yu
A common way to solve this problem, known as Mixture-of-Experts, is to represent the policy as the weighted sum of multiple components, where different components perform well on different parts of the state space.
1 code implementation • 22 Oct 2019 • Kuangen Zhang, Zhimin Hou, Clarence W. de Silva, Haoyong Yu, Chenglong Fu
However, the local minima caused by unsuitable rewards and the overestimation of the cumulative reward impede the maximization of the cumulative reward.
1 code implementation • 22 Apr 2019 • Kuangen Zhang, Ming Hao, Jing Wang, Clarence W. de Silva, Chenglong Fu
Learning on point cloud is eagerly in demand because the point cloud is a common type of geometric data and can aid robots to understand environments robustly.
no code implementations • 16 Mar 2019 • Kuangen Zhang, Jing Wang, Chenglong Fu
Environmental information can provide reliable prior information about human motion intent, which can aid the subject with wearable robotics to walk in complex environments.