4,291 Hits in 1.9 sec


Hang Zhang, Shao-Liang Chen
2019 JACC: Cardiovascular Interventions  
*Hang Zhang, MD Shao-Liang Chen, MD *Department of Cardiology Nanjing First Hospital Nanjing Medical University 68 Changle Road Nanjing 21006 China E-mail:  ... 
doi:10.1016/j.jcin.2019.02.023 pmid:31000019 fatcat:bj565qppizbmzjb24to3a4akvu

OmniHang: Learning to Hang Arbitrary Objects using Contact Point Correspondences and Neural Collision Estimation [article]

Yifan You, Lin Shao, Toki Migimatsu, Jeannette Bohg
2021 arXiv   pre-print
Then, the robot needs to find a collision-free path to move the object from its initial pose to stable hanging pose.  ...  In this paper, we explore whether a robot can learn to hang arbitrary objects onto a diverse set of supporting items such as racks or hooks.  ...  The following subsections describe the two modules for hanging an object: goal pose prediction (where to hang) and path planning (how to hang). B.  ... 
arXiv:2103.14283v1 fatcat:sfi2tmdfineqnh5bigcdck3tuu

The Riemannian Geometry of Deep Generative Models [article]

Hang Shao, Abhishek Kumar, P. Thomas Fletcher
2017 arXiv   pre-print
Deep generative models learn a mapping from a low dimensional latent space to a high-dimensional data space. Under certain regularity conditions, these models parameterize nonlinear manifolds in the data space. In this paper, we investigate the Riemannian geometry of these generated manifolds. First, we develop efficient algorithms for computing geodesic curves, which provide an intrinsic notion of distance between points on the manifold. Second, we develop an algorithm for parallel translation
more » ... of a tangent vector along a path on the manifold. We show how parallel translation can be used to generate analogies, i.e., to transport a change in one data point into a semantically similar change of another data point. Our experiments on real image data show that the manifolds learned by deep generative models, while nonlinear, are surprisingly close to zero curvature. The practical implication is that linear paths in the latent space closely approximate geodesics on the generated manifold. However, further investigation into this phenomenon is warranted, to identify if there are other architectures or datasets where curvature plays a more prominent role. We believe that exploring the Riemannian geometry of deep generative models, using the tools developed in this paper, will be an important step in understanding the high-dimensional, nonlinear spaces these models learn.
arXiv:1711.08014v1 fatcat:otos3xigbzg5nden6shxb47g6m

M3DSSD: Monocular 3D Single Stage Object Detector [article]

Shujie Luo, Hang Dai, Ling Shao, Yong Ding
2021 arXiv   pre-print
In this paper, we propose a Monocular 3D Single Stage object Detector (M3DSSD) with feature alignment and asymmetric non-local attention. Current anchor-based monocular 3D object detection methods suffer from feature mismatching. To overcome this, we propose a two-step feature alignment approach. In the first step, the shape alignment is performed to enable the receptive field of the feature map to focus on the pre-defined anchors with high confidence scores. In the second step, the center
more » ... ment is used to align the features at 2D/3D centers. Further, it is often difficult to learn global information and capture long-range relationships, which are important for the depth prediction of objects. Therefore, we propose a novel asymmetric non-local attention block with multi-scale sampling to extract depth-wise features. The proposed M3DSSD achieves significantly better performance than the monocular 3D object detection methods on the KITTI dataset, in both 3D object detection and bird's eye view tasks.
arXiv:2103.13164v1 fatcat:y63agjgtljepdp7rubvfzsjyzu

Review of the article J. Norovsuren, Liu Shao-Wei, Sun Cheng-Hang, B. Altansukh, Ch. Dorjsuren «Molecular and biological characteristics of streptomyces diversity in the soils of the Saxaul forest in Mongolia»

I. G. Shirokikh
2021 Agricultural science Euro-North-East  
doaj:343697e7ee164dedb6c2c8a3c4020e03 fatcat:ssye26v3azdbpmynbfa7wqvfri

Spin photogalvanic effect in two-dimensional collinear antiferromagnets [article]

Rui-Chun Xiao, Ding-Fu Shao, Yu-Hang Li, Hua Jiang
2020 arXiv   pre-print
Spin photogalvanic effect (SPGE) is an efficient method to generate a spin current by photoexcitation in a contactless and ultra-fast way. In two-dimensional (2D) collinear antiferromagnetic (AFM) materials that preserve the combined time-reversal (T) and inversion (I) symmetry (i.e., TI symmetry), we find that the photogalvanic currents in two magnetic sublattices carry different kinds of spins and propagate in opposite direction if the spin-orbit coupling is negligible, resulting in a pure
more » ... n current without net charge current. Based on the first-principles calculations, we show that two experimentally synthesized 2D collinear AFM materials, monolayer MnPS_3 and bilayer CrCl_3, host the required symmetry and support sizable SPGE. The predicted SPGE in 2D collinear AFM materials makes them promising platforms for nano spintronics devices.
arXiv:2009.02748v1 fatcat:ru2pycjkwjdw5ehdarmyy3vi6m

Exploring Semantic Segmentation on the DCT Representation [article]

Shao-Yuan Lo, Hsueh-Ming Hang
2019 arXiv   pre-print
To the best of our knowledge, we are the first Exploring Semantic Segmentation on the DCT Representation Shao-Yuan Lo Hsueh-Ming Hang National Chiao Tung University, hmhang  ... 
arXiv:1907.10015v2 fatcat:gm2v7k5o3zagrjhc5ae4h3ijyy

Localized high pressure near an aspheric encapsulated microbubble

Shao Wei-Hang, Chen Wei-Zhong
2014 Wuli xuebao  
Based on hydrodynamics, the pressure of the liquid outside an aspheric encapsulated bubble driven by ultrasound is studied, and its analytical expression is derived. Numerical simulation shows that 1) the aspheric shape of an encapsulated bubble makes little influence on the pressure of the liquid far away from the bubble; 2) the pressure is extremely high at some local places of the liquid near an aspheric encapsulated bubble, and the pressure values at these places are apparently larger than
more » ... hose for a spherical encapsulated bubble at the same conditions. This phenomenon is of significance in the applications such as high intensity ultrasound therapy, drug delivery, cell membrane perforation, etc. As the ultrasound frequency shifts to the resonance frequency of an encapsulated bubble, or bubble shape deviates from sphericity, the localized high pressure becomes even greater.
doi:10.7498/aps.63.204702 fatcat:ls5v2niif5cudej6h4guw3fdti

Efficient Road Lane Marking Detection with Deep Learning [article]

Ping-Rong Chen, Shao-Yuan Lo, Hsueh-Ming Hang, Sheng-Wei Chan, Jing-Jhih Lin
2018 arXiv   pre-print
Lane mark detection is an important element in the road scene analysis for Advanced Driver Assistant System (ADAS). Limited by the onboard computing power, it is still a challenge to reduce system complexity and maintain high accuracy at the same time. In this paper, we propose a Lane Marking Detector (LMD) using a deep convolutional neural network to extract robust lane marking features. To improve its performance with a target of lower complexity, the dilated convolution is adopted. A
more » ... r and thinner structure is designed to decrease the computational cost. Moreover, we also design post-processing algorithms to construct 3rd-order polynomial models to fit into the curved lanes. Our system shows promising results on the captured road scenes.
arXiv:1809.03994v1 fatcat:7g2szbdc5jd75maah5fs4vbbq4

Capacitive Behavior of Single Gallium Oxide Nanobelt

Haitao Cai, Hang Liu, Huichao Zhu, Pai Shao, Changmin Hou
2015 Materials  
Author Contributions Haitao Cai has fabricated Ga 2 O 3 nanobelt and the device, Hang Liu has performed the electrical investigation, Huichao Zhu and Pai Shao have analyzed the impedance model, Changmin  ... 
doi:10.3390/ma8085244 pmid:28793506 pmcid:PMC5455499 fatcat:iwkvi5juqng6pflr3zo5biohye

Zero-shot multi-label learning via label factorisation

Hang Shao, Yuchen Guo, Guiguang Ding, Jungong Han
2018 IET Computer Vision  
This study considers the zero-shot learning problem under the multi-label setting where each test sample is associated with multiple labels that are unseen in training data. The authors propose a novel learning framework based on label factorisation for this problem. Specifically, the authors' framework takes three key issues into consideration and addresses them in a unified way. The first is knowledge transfer that utilises information from seen classes to build recognition models for unseen
more » ... lasses. The second is label correlation which means that labels which have different semantics may co-occur frequently. This is an important issue in multi-label learning. The authors propose to learn a shared latent space by label factorisation and use the label semantics as the decoding function, which can address both issues. The third is the predictability which requires the learned latent space to be strongly related to the visual features. It is guaranteed by incorporating a regression model into the learning framework. The authors derive two specific formulations from the general framework and propose the corresponding learning algorithms. The authors conducted extensive experiments on three multi-label data sets. The results demonstrated the effectiveness. Nomenclature semantics V latent factors R( ⋅ ) regression model n s , n t #images d #dimension m #semantics c s , c t #classes α, β parameters IET Comput.
doi:10.1049/iet-cvi.2018.5131 fatcat:5shug5tmyvbqzncizpspcf5toi


Yi-Hang Shao
1999 Bulletin of Informatics and Cybernetics  
In this paper, we introduce trilevel dynamic optimization problems. Reformulating the trilevel dynamic problem as a single-level optimal control problem with state-control functional constraints, we derive the necessary optimality conditions. We also show that the necessary conditions are sufficient for optimality in a 'convex' case.
doi:10.5109/13485 fatcat:ayqid7o46nezlo2bjuysm7pnee

Optimal Discrete Constellation Inputs for Aggregated LiFi-WiFi Networks [article]

Shuai Ma, Fan Zhang, Songtao Lu, Hang Li, Ruixin Yang, Sihua Shao, Jiaheng Wang, Shiyin Li
2021 arXiv   pre-print
Shao is with the Department of Electrical Engineering, New Mexico Tech, Socorro, NM 87801 USA. (email: J.  ... 
arXiv:2111.02581v1 fatcat:2esgqliv2rfrld7zltbgbu74vq

Spin photogalvanic effect in two-dimensional collinear antiferromagnets

Rui-Chun Xiao, Ding-Fu Shao, Yu-Hang Li, Hua Jiang
2021 npj Quantum Materials  
AbstractRecent discovered two-dimensional (2D) antiferromagnetic (AFM) van der Waals quantum materials have attracted increasing interest due to the emergent exotic physical phenomena. The spintronic properties utilizing the intrinsic AFM state in 2D antiferromagnets, however, have been rarely found. Here we show that the spin photogalvanic effect (SPGE), which has been predicted in three-dimensional (3D) antiferromagnets, can intrinsically emerge in 2D antiferromagnets for promising spintronic
more » ... applications. Based on the symmetry analysis of possible AFM orders in the honeycomb lattice, we conclude suitable 2D AFM candidate materials for realizing the SPGE. We choose two experimentally synthesized 2D collinear AFM materials, monolayer MnPS3, and bilayer CrCl3, as representative materials to perform first-principles calculations, and find that they support sizable SPGE. The SPGE in collinear 2D AFM materials can be utilized to generate pure spin current in a contactless and ultra-fast way.
doi:10.1038/s41535-021-00334-5 fatcat:ld2hdxjdyrgivnxhv2xvpvmlkq

High-resolution Iterative Feedback Network for Camouflaged Object Detection [article]

Xiaobin Hu, Deng-Ping Fan, Xuebin Qin, Hang Dai, Wenqi Ren, Ying Tai, Chengjie Wang, Ling Shao
2022 arXiv   pre-print
Hang Dai, Xuebin Qin and Ling Shao are with Mohamed bin Zayed University of Artificial Intelligence Abu Dhabi, United Arab Emirates.  ...  Wenqi Ren is with the School of Cyber Science and Technology, Sun Yat-sen University at Shenzhen, Shenzhen 518107, China Corresponding author: Hang Dai ( β is a comprehensive metric  ... 
arXiv:2203.11624v1 fatcat:dzjfisfinbfwza3dcxcjgigiji
« Previous Showing results 1 — 15 out of 4,291 results