arXiv subjects

Jie Li

Publications and source records attributed to Jie Li.

At least 559 records · Page 31Linked to original sources

arXiv2021

Real-time tracking of COVID-19 and coronavirus research updates through text mining

The novel coronavirus (SARS-CoV-2) which causes COVID-19 is an ongoing pandemic. There are ongoing studies with up to hundreds of publications uploaded to databases daily. We are exploring the use-case of artificial intelligence and natural language processing in order to efficiently sort through these publications. We demonstrate that clinical trial information, preclinical studies, and a general topic model can be used as text mining data intelligence tools for scientists all over the world to use as a resource for their own research. To evaluate our method, several metrics are used to measure the information extraction and clustering results. In addition, we demonstrate that our workflow not only have a use-case for COVID-19, but for other disease areas as well. Overall, our system aims to allow scientists to more efficiently research coronavirus. Our automatically updating modules are available on our information portal at https://ghddi-ailab.github.io/Targeting2019-nCoV/ for public viewing.

cs.IR↗

arXiv2021

Enhance Information Propagation for Graph Neural Network by Heterogeneous Aggregations

Graph neural networks are emerging as continuation of deep learning success w.r.t. graph data. Tens of different graph neural network variants have been proposed, most following a neighborhood aggregation scheme, where the node features are updated via aggregating features of its neighboring nodes from layer to layer. Though related research surges, the power of GNNs are still not on-par-with their counterpart CNNs in computer vision and RNNs in natural language processing. We rethink this problem from the perspective of information propagation, and propose to enhance information propagation among GNN layers by combining heterogeneous aggregations. We argue that as richer information are propagated from shallow to deep layers, the discriminative capability of features formulated by GNN can benefit from it. As our first attempt in this direction, a new generic GNN layer formulation and upon this a new GNN variant referred as HAG-Net is proposed. We empirically validate the effectiveness of HAG-Net on a number of graph classification benchmarks, and elaborate all the design options and criterions along with.

cs.LG↗

arXiv2021

DPointNet: A Density-Oriented PointNet for 3D Object Detection in Point Clouds

For current object detectors, the scale of the receptive field of feature extraction operators usually increases layer by layer. Those operators are called scale-oriented operators in this paper, such as the convolution layer in CNN, and the set abstraction layer in PointNet++. The scale-oriented operators are appropriate for 2D images with multi-scale objects, but not natural for 3D point clouds with multi-density but scale-invariant objects. In this paper, we put forward a novel density-oriented PointNet (DPointNet) for 3D object detection in point clouds, in which the density of points increases layer by layer. In experiments for object detection, the DPointNet is applied to PointRCNN, and the results show that the model with the new operator can achieve better performance and higher speed than the baseline PointRCNN, which verify the effectiveness of the proposed DPointNet.

cs.CV↗

arXiv2021

Long time-series NDVI reconstruction in cloud-prone regions via spatio-temporal tensor completion

The applications of Normalized Difference Vegetation Index (NDVI) time-series data are inevitably hampered by cloud-induced gaps and noise. Although numerous reconstruction methods have been developed, they have not effectively addressed the issues associated with large gaps in the time series over cloudy and rainy regions, due to the insufficient utilization of the spatial and temporal correlations. In this paper, an adaptive Spatio-Temporal Tensor Completion method (termed ST-Tensor) method is proposed to reconstruct long-term NDVI time series in cloud-prone regions, by making full use of the multi-dimensional spatio-temporal information simultaneously. For this purpose, a highly-correlated tensor is built by considering the correlations among the spatial neighbors, inter-annual variations, and periodic characteristics, in order to reconstruct the missing information via an adaptive-weighted low-rank tensor completion model. An iterative l1 trend filtering method is then implemented to eliminate the residual temporal noise. This new method was tested using MODIS 16-day composite NDVI products from 2001 to 2018 obtained in the region of Mainland Southeast Asia, where the rainy climate commonly induces large gaps and noise in the data. The qualitative and quantitative results indicate that the ST-Tensor method is more effective than the five previous methods in addressing the different missing data problems, especially the temporally continuous gaps and spatio-temporally continuous gaps. It is also shown that the ST-Tensor method performs better than the other methods in tracking NDVI seasonal trajectories, and is therefore a superior option for generating high-quality long-term NDVI time series for cloud-prone regions.

eess.SP↗

arXiv2021

Proxemics and Social Interactions in an Instrumented Virtual Reality Workshop

Virtual environments (VEs) can create collaborative and social spaces, which are increasingly important in the face of remote work and travel reduction. Recent advances, such as more open and widely available platforms, create new possibilities to observe and analyse interaction in VEs. Using a custom instrumented build of Mozilla Hubs to measure position and orientation, we conducted an academic workshop to facilitate a range of typical workshop activities. We analysed social interactions during a keynote, small group breakouts, and informal networking/hallway conversations. Our mixed-methods approach combined environment logging, observations, and semi-structured interviews. The results demonstrate how small and large spaces influenced group formation, shared attention, and personal space, where smaller rooms facilitated more cohesive groups while larger rooms made small group formation challenging but personal space more flexible. Beyond our findings, we show how the combination of data and insights can fuel collaborative spaces' design and deliver more effective virtual workshops.

cs.HC↗

arXiv2021

A Density-Aware PointRCNN for 3D Object Detection in Point Clouds

We present an improved version of PointRCNN for 3D object detection, in which a multi-branch backbone network is adopted to handle the non-uniform density of point clouds. An uncertainty-based sampling policy is proposed to deal with the distribution differences of different point clouds. The new model can achieve about 0.8 AP higher performance than the baseline PointRCNN on KITTI val set. In addition, a simplified model using a single scale grouping for each set-abstraction layer can achieve competitive performance with less computational cost.

cs.CV↗

arXiv2020

Skeleton-based Approaches based on Machine Vision: A Survey

Recently, skeleton-based approaches have achieved rapid progress on the basis of great success in skeleton representation. Plenty of researches focus on solving specific problems according to skeleton features. Some skeleton-based approaches have been mentioned in several overviews on object detection as a non-essential part. Nevertheless, there has not been any thorough analysis of skeleton-based approaches attentively. Instead of describing these techniques in terms of theoretical constructs, we devote to summarizing skeleton-based approaches with regard to application fields and given tasks as comprehensively as possible. This paper is conducive to further understanding of skeleton-based application and dealing with particular issues.

cs.CV↗

arXiv2020

Anatomy of Multipath BGP Deployment in a Large ISP Network

Multipath routing is useful for networks to achieve load sharing among multiple routing paths. Multipath BGP (MBGP) is a technique to realize inter-domain multipath routing by enabling a BGP router to install multiple equally-good routes to a destination prefix. Most of previous works did not distinguish between intra-domain and inter-domain multipath routing. In this paper, we present a measurement study on the deployment of M-BGP in a large Internet service provider (ISP) network. Our method combines control-plane BGP measurements using Looking Glasses (LG), and data-plane traceroute measurements using RIPE Atlas. We focus on Hurricane Electric (AS6939) because it is a global ISP that connects with hundreds of major exchange points and exchanges IP traffic with thousands of different networks. And more importantly, we find that this ISP has by far the largest number of M-BGP deployments among autonomous systems with LG servers. Specifically, Hurricane Electric has deployed M-BGP with 512 of its peering ASes at 58 PoPs around the world, including many top ASes and content providers. We also observe that most of its M-BGP deployments involve IXP interconnections. Our work provides insights into the latest deployment of M-BGP in a major ISP network and it highlights the characteristics and effectiveness of M-BGP as a means to realize load sharing.

cs.NI↗

arXiv2020

Spectral Response Function Guided Deep Optimization-driven Network for Spectral Super-resolution

Hyperspectral images are crucial for many research works. Spectral super-resolution (SSR) is a method used to obtain high spatial resolution (HR) hyperspectral images from HR multispectral images. Traditional SSR methods include model-driven algorithms and deep learning. By unfolding a variational method, this paper proposes an optimization-driven convolutional neural network (CNN) with a deep spatial-spectral prior, resulting in physically interpretable networks. Unlike the fully data-driven CNN, auxiliary spectral response function (SRF) is utilized to guide CNNs to group the bands with spectral relevance. In addition, the channel attention module (CAM) and reformulated spectral angle mapper loss function are applied to achieve an effective reconstruction model. Finally, experiments on two types of datasets, including natural and remote sensing images, demonstrate the spectral enhancement effect of the proposed method. And the classification results on the remote sensing dataset also verified the validity of the information enhanced by the proposed method.

eess.IV↗

arXiv2020

Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completion

LiDAR point cloud analysis is a core task for 3D computer vision, especially for autonomous driving. However, due to the severe sparsity and noise interference in the single sweep LiDAR point cloud, the accurate semantic segmentation is non-trivial to achieve. In this paper, we propose a novel sparse LiDAR point cloud semantic segmentation framework assisted by learned contextual shape priors. In practice, an initial semantic segmentation (SS) of a single sweep point cloud can be achieved by any appealing network and then flows into the semantic scene completion (SSC) module as the input. By merging multiple frames in the LiDAR sequence as supervision, the optimized SSC module has learned the contextual shape priors from sequential LiDAR data, completing the sparse single sweep point cloud to the dense one. Thus, it inherently improves SS optimization through fully end-to-end training. Besides, a Point-Voxel Interaction (PVI) module is proposed to further enhance the knowledge fusion between SS and SSC tasks, i.e., promoting the interaction of incomplete local geometry of point cloud and complete voxel-wise global structure. Furthermore, the auxiliary SSC and PVI modules can be discarded during inference without extra burden for SS. Extensive experiments confirm that our JS3C-Net achieves superior performance on both SemanticKITTI and SemanticPOSS benchmarks, i.e., 4% and 3% improvement correspondingly.

cs.CV↗

arXiv2020

Generative and Discriminative Learning for Distorted Image Restoration

Liquify is a common technique for image editing, which can be used for image distortion. Due to the uncertainty in the distortion variation, restoring distorted images caused by liquify filter is a challenging task. To edit images in an efficient way, distorted images are expected to be restored automatically. This paper aims at the distorted image restoration, which is characterized by seeking the appropriate warping and completion of a distorted image. Existing methods focus on the hardware assistance or the geometric principle to solve the specific regular deformation caused by natural phenomena, but they cannot handle the irregularity and uncertainty of artificial distortion in this task. To address this issue, we propose a novel generative and discriminative learning method based on deep neural networks, which can learn various reconstruction mappings and represent complex and high-dimensional data. This method decomposes the task into a rectification stage and a refinement stage. The first stage generative network predicts the mapping from the distorted images to the rectified ones. The second stage generative network then further optimizes the perceptual quality. Since there is no available dataset or benchmark to explore this task, we create a Distorted Face Dataset (DFD) by forward distortion mapping based on CelebA dataset. Extensive experimental evaluation on the proposed benchmark and the application demonstrates that our method is an effective way for distorted image restoration.

eess.IV↗

arXiv2020

A Systematic Construction of MDS Codes With Small Sub-packetization Level and Near-Optimal Repair Bandwidth

In the literature, all the known high-rate MDS codes with the optimal repair bandwidth possess a significantly large sub-packetization level, which may prevent the codes to be implemented in practical systems. To build MDS codes with small sub-packetization level, existing constructions and theoretical bounds imply that one may sacrifice the optimality of the repair bandwidth. Partly motivated by the work of Tamo et al. (IEEE Trans. Inform. Theory, 59(3), 1597-1616, 2013), in this paper, we present a transformation that can greatly reduce the sub-packetization level of MDS codes with the optimal repair bandwidth with respect to the same code length n. As applications of the transformation, four high-rate MDS codes having both small sub-packetization level and near-optimal repair bandwidth can be obtained, where three of them are explicit and the required field sizes are around or even smaller than the code length n. Additionally, we propose another explicit MDS code which has a similar structure as that of the first resultant code obtained by the generic transformation, but can be built on a smaller finite field.

cs.IT↗

arXiv2020

Metal-organic Frameworks: Possible New Two-Dimensional Magnetic and Topological materials

Finding new two-dimensional (2D) materials with novel quantum properties is highly desirable for technological innovations. In this work, we studied a series of metal-organic frameworks (MOFs) with different metal cores and discovered various attractive properties, such as room-temperature magnetic ordering, strong perpendicular magnetic anisotropy, huge topological band gap (>200meV), and excellent spin-filtering performance. As many MOFs have been successfully synthesized in experiments, our results suggest realistic new 2D functional materials for the design of spintronic nanodevices.

cond-mat.mtrl-sci↗

arXiv2020

The Occurrence of Rocky Habitable Zone Planets Around Solar-Like Stars from Kepler Data

We present occurrence rates for rocky planets in the habitable zones (HZ) of main-sequence dwarf stars based on the Kepler DR25 planet candidate catalog and Gaia-based stellar properties. We provide the first analysis in terms of star-dependent instellation flux, which allows us to track HZ planets. We define $η_\oplus$ as the HZ occurrence of planets with radius between 0.5 and 1.5 $R_\oplus$ orbiting stars with effective temperatures between 4800 K and 6300 K. We find that $η_\oplus$ for the conservative HZ is between $0.37^{+0.48}_{-0.21}$ (errors reflect 68\% credible intervals) and $0.60^{+0.90}_{-0.36}$ planets per star, while the optimistic HZ occurrence is between $0.58^{+0.73}_{-0.33}$ and $0.88^{+1.28}_{-0.51}$ planets per star. These bounds reflect two extreme assumptions about the extrapolation of completeness beyond orbital periods where DR25 completeness data are available. The large uncertainties are due to the small number of detected small HZ planets. We find similar occurrence rates using both a Poisson likelihood Bayesian analysis and Approximate Bayesian Computation. Our results are corrected for catalog completeness and reliability. Both completeness and the planet occurrence rate are dependent on stellar effective temperature. We also present occurrence rates for various stellar populations and planet size ranges. We estimate with $95\%$ confidence that, on average, the nearest HZ planet around G and K dwarfs is about 6 pc away, and there are about 4 HZ rocky planets around G and K dwarfs within 10 pc of the Sun.

astro-ph.EP↗

arXiv2020

A Framework of Randomized Selection Based Certified Defenses Against Data Poisoning Attacks

Neural network classifiers are vulnerable to data poisoning attacks, as attackers can degrade or even manipulate their predictions thorough poisoning only a few training samples. However, the robustness of heuristic defenses is hard to measure. Random selection based defenses can achieve certified robustness by averaging the classifiers' predictions on the sub-datasets sampled from the training set. This paper proposes a framework of random selection based certified defenses against data poisoning attacks. Specifically, we prove that the random selection schemes that satisfy certain conditions are robust against data poisoning attacks. We also derive the analytical form of the certified radius for the qualified random selection schemes. The certified radius of bagging derived by our framework is tighter than the previous work. Our framework allows users to improve robustness by leveraging prior knowledge about the training set and the poisoning model. Given higher level of prior knowledge, we can achieve higher certified accuracy both theoretically and practically. According to the experiments on three benchmark datasets: MNIST 1/7, MNIST, and CIFAR-10, our method outperforms the state-of-the-art.

cs.LG↗

arXiv2020

Einstein-Podolsky-Rosen entanglement and asymmetric steering between distant macroscopic mechanical and magnonic systems

We propose a deterministic scheme for establishing hybrid Einstein-Podolsky-Rosen (EPR) entanglement channel between a macroscopic mechanical oscillator and a magnon mode in a distant yttrium-iron-garnet (YIG) sphere across about ten gigahertz of frequency difference. The system consists of a driven electromechanical cavity which is unidirectionally coupled to a distant electromagnonical cavity inside which a YIG sphere is placed. We find that far beyond the sideband-resolved regime in the electromechanical subsystem, stationary phonon-magnon EPR entanglement can be achieved. This is realized by utilizing the output field of the electromechanical cavity being an intermediary which distributes the electromechanical entanglement to the magnons, thus establishing a remote phonon-magnon entanglement. The EPR entanglement is strong enough such that phonon-magnon quantum steering can be attainable in an asymmetric manner. This long-distance macroscopic hybrid EPR entanglement and steering enable potential applications not only in fundamental tests of quantum mechanics at the macro scale, but also in quantum networking and one-sided device-independent quantum cryptography based on magnonics and electromechanics.

quant-ph↗

arXiv2020

Image Fine-grained Inpainting

Image inpainting techniques have shown promising improvement with the assistance of generative adversarial networks (GANs) recently. However, most of them often suffered from completed results with unreasonable structure or blurriness. To mitigate this problem, in this paper, we present a one-stage model that utilizes dense combinations of dilated convolutions to obtain larger and more effective receptive fields. Benefited from the property of this network, we can more easily recover large regions in an incomplete image. To better train this efficient generator, except for frequently-used VGG feature matching loss, we design a novel self-guided regression loss for concentrating on uncertain areas and enhancing the semantic details. Besides, we devise a geometrical alignment constraint item to compensate for the pixel-based distance between prediction features and ground-truth ones. We also employ a discriminator with local and global branches to ensure local-global contents consistency. To further improve the quality of generated images, discriminator feature matching on the local branch is introduced, which dynamically minimizes the similarity of intermediate features between synthetic and ground-truth patches. Extensive experiments on several public datasets demonstrate that our approach outperforms current state-of-the-art methods. Code is available at https://github.com/Zheng222/DMFN.

cs.CV↗

arXiv2020

Intercultural Science-Art Project 'Magritte Meet Science'

In this manuscript a joint project between young researchers from all around the world, the Intercultural Science-Art Project, is presented, in which all participants interpreted their own research with art. Art is meant in the most inclusive way possible, including drawings and digital works, but also songs and confectionary art. This project has two main goals. On the one hand it creates tools for young scientists to communicate their research to society by artistic means. On the other hand it tries to bring together different cultures and to strengthen ties between them.

math.HO↗