Zobrazeno 1 - 10
of 542
pro vyhledávání: '"Peng, Huei"'
Meta reinforcement learning (Meta RL) has been amply explored to quickly learn an unseen task by transferring previously learned knowledge from similar tasks. However, most state-of-the-art algorithms require the meta-training tasks to have a dense c
Externí odkaz:
http://arxiv.org/abs/2311.06673
We propose a novel approach for monocular 3D object detection by leveraging local perspective effects of each object. While the global perspective effect shown as size and position variations has been exploited for monocular 3D detection extensively,
Externí odkaz:
http://arxiv.org/abs/2301.01802
Autor:
Liu, Peng-Huei1 (AUTHOR) penghuei.liu@gmail.com, Pan, Ming-Wei2 (AUTHOR) b8801136@tmu.edu.tw, Huang, Yan-Bo1 (AUTHOR) yanhusuo79619@gmail.com, Ng, Chip-Jin1 (AUTHOR) ngowl@ms3.hinet.net, Chen, Shou-Yen1,3 (AUTHOR) allendream0621@yahoo.com.tw
Publikováno v:
Life (2075-1729). Oct2024, Vol. 14 Issue 10, p1252. 10p.
This paper proposes a convolution structure for learning SE(3)-equivariant features from 3D point clouds. It can be viewed as an equivariant version of kernel point convolutions (KPConv), a widely used convolution form to process point cloud data. Co
Externí odkaz:
http://arxiv.org/abs/2206.05398
Autor:
Oh, Geunseob, Peng, Huei
The task of predicting stochastic behaviors of road agents in diverse environments is a challenging problem for autonomous driving. To best understand scene contexts and produce diverse possible future states of the road agents adaptively in differen
Externí odkaz:
http://arxiv.org/abs/2201.09874
Publikováno v:
Life, Vol 14, Iss 10, p 1252 (2024)
Background: The COVID-19 pandemic poses severe risks for immunocompromised patients, especially those with neutropenia due to chemotherapy. This study evaluates the safety and effectiveness of remdesivir use in COVID-19 patients with neutropenia. Met
Externí odkaz:
https://doaj.org/article/ac20b3a14bee4ac883e61f2eba0493ab
Meta Reinforcement Learning (Meta-RL) has seen substantial advancements recently. In particular, off-policy methods were developed to improve the data efficiency of Meta-RL techniques. \textit{Probabilistic embeddings for actor-critic RL} (PEARL) is
Externí odkaz:
http://arxiv.org/abs/2108.08448
This paper proposes a correspondence-free method for point cloud rotational registration. We learn an embedding for each point cloud in a feature space that preserves the SO(3)-equivariance property, enabled by recent developments in equivariant neur
Externí odkaz:
http://arxiv.org/abs/2107.10296
A unified neural network structure is presented for joint 3D object detection and point cloud segmentation in this paper. We leverage rich supervision from both detection and segmentation labels rather than using just one of them. In addition, an ext
Externí odkaz:
http://arxiv.org/abs/2107.02980
Autor:
Zhong, Yuanxin, Peng, Huei
A real-time semantic 3D occupancy mapping framework is proposed in this paper. The mapping framework is based on the Bayesian kernel inference strategy from the literature. Two novel free space representations are proposed to efficiently construct tr
Externí odkaz:
http://arxiv.org/abs/2107.02981