arXiv subjects

Yan Xu

Publications and source records attributed to Yan Xu.

At least 217 records · Page 12Linked to original sources

arXiv2021

Wide-Baseline Multi-Camera Calibration using Person Re-Identification

We address the problem of estimating the 3D pose of a network of cameras for large-environment wide-baseline scenarios, e.g., cameras for construction sites, sports stadiums, and public spaces. This task is challenging since detecting and matching the same 3D keypoint observed from two very different camera views is difficult, making standard structure-from-motion (SfM) pipelines inapplicable. In such circumstances, treating people in the scene as "keypoints" and associating them across different camera views can be an alternative method for obtaining correspondences. Based on this intuition, we propose a method that uses ideas from person re-identification (re-ID) for wide-baseline camera calibration. Our method first employs a re-ID method to associate human bounding boxes across cameras, then converts bounding box correspondences to point correspondences, and finally solves for camera pose using multi-view geometry and bundle adjustment. Since our method does not require specialized calibration targets except for visible people, it applies to situations where frequent calibration updates are required. We perform extensive experiments on datasets captured from scenes of different sizes, camera settings (indoor and outdoor), and human activities (walking, playing basketball, construction). Experiment results show that our method achieves similar performance to standard SfM methods relying on manually labeled point correspondences.

cs.CV↗

arXiv2021

Semi-supervised Variational Temporal Convolutional Network for IoT Communication Multi-anomaly Detection

The consumer Internet of Things (IoT) have developed in recent years. Mass IoT devices are constructed to build a huge communications network. But these devices are insecure in reality, it means that the communications network are exposed by the attacker. Moreover, the IoT communication network also faces with variety of sudden errors. Therefore, it easily leads to that is vulnerable with the threat of attacker and system failure. The severe situation of IoT communication network motivates the development of new techniques to automatically detect multi-anomaly. In this paper, we propose SS-VTCN, a semi-supervised network for IoT multiple anomaly detection that works well effectively for IoT communication network. SS-VTCN is designed to capture the normal patterns of the IoT traffic data based on the distribution whether it is labeled or not by learning their representations with key techniques such as Variational Autoencoders and Temporal Convolutional Network. This network can use the encode data to predict preliminary result, and reconstruct input data to determine anomalies by the representations. Extensive evaluation experiments based on a benchmark dataset and a real consumer smart home dataset demonstrate that SS-VTCN is more suitable than supervised and unsupervised method with better performance when compared other state-of-art semi-supervised method.

cs.CR↗

arXiv2021

Dissipative and conservative local discontinuous Galerkin methods for the Fornberg-Whitham type equations

In this paper, we construct high order energy dissipative and conservative local discontinuous Galerkin methods for the Fornberg-Whitham type equations. We give the proofs for the dissipation and conservation for related conservative quantities. The corresponding error estimates are proved for the proposed schemes. The capability of our schemes for different types of solutions is shown via several numerical experiments. The dissipative schemes have good behavior for shock solutions, while for a long time approximation, the conservative schemes can reduce the shape error and the decay of amplitude significantly

math.NA↗

arXiv2021

Large Scale Image Completion via Co-Modulated Generative Adversarial Networks

Numerous task-specific variants of conditional generative adversarial networks have been developed for image completion. Yet, a serious limitation remains that all existing algorithms tend to fail when handling large-scale missing regions. To overcome this challenge, we propose a generic new approach that bridges the gap between image-conditional and recent modulated unconditional generative architectures via co-modulation of both conditional and stochastic style representations. Also, due to the lack of good quantitative metrics for image completion, we propose the new Paired/Unpaired Inception Discriminative Score (P-IDS/U-IDS), which robustly measures the perceptual fidelity of inpainted images compared to real images via linear separability in a feature space. Experiments demonstrate superior performance in terms of both quality and diversity over state-of-the-art methods in free-form image completion and easy generalization to image-to-image translation. Code is available at https://github.com/zsyzzsoft/co-mod-gan.

cs.CV↗

arXiv2021

CelebA-Spoof Challenge 2020 on Face Anti-Spoofing: Methods and Results

As facial interaction systems are prevalently deployed, security and reliability of these systems become a critical issue, with substantial research efforts devoted. Among them, face anti-spoofing emerges as an important area, whose objective is to identify whether a presented face is live or spoof. Recently, a large-scale face anti-spoofing dataset, CelebA-Spoof which comprised of 625,537 pictures of 10,177 subjects has been released. It is the largest face anti-spoofing dataset in terms of the numbers of the data and the subjects. This paper reports methods and results in the CelebA-Spoof Challenge 2020 on Face AntiSpoofing which employs the CelebA-Spoof dataset. The model evaluation is conducted online on the hidden test set. A total of 134 participants registered for the competition, and 19 teams made valid submissions. We will analyze the top ranked solutions and present some discussion on future work directions.

cs.CV↗

arXiv2021

Multi-hop Question Generation with Graph Convolutional Network

Multi-hop Question Generation (QG) aims to generate answer-related questions by aggregating and reasoning over multiple scattered evidence from different paragraphs. It is a more challenging yet under-explored task compared to conventional single-hop QG, where the questions are generated from the sentence containing the answer or nearby sentences in the same paragraph without complex reasoning. To address the additional challenges in multi-hop QG, we propose Multi-Hop Encoding Fusion Network for Question Generation (MulQG), which does context encoding in multiple hops with Graph Convolutional Network and encoding fusion via an Encoder Reasoning Gate. To the best of our knowledge, we are the first to tackle the challenge of multi-hop reasoning over paragraphs without any sentence-level information. Empirical results on HotpotQA dataset demonstrate the effectiveness of our method, in comparison with baselines on automatic evaluation metrics. Moreover, from the human evaluation, our proposed model is able to generate fluent questions with high completeness and outperforms the strongest baseline by 20.8% in the multi-hop evaluation. The code is publicly available at https://github.com/HLTCHKUST/MulQG}{https://github.com/HLTCHKUST/MulQG .

cs.CL↗

arXiv2021

Exploring the Galactic Anticenter substructure with LAMOST & Gaia DR2

We characterize the kinematic and chemical properties of 589 Galactic Anticenter Substructure Stars (GASS) with K-/M- giants in Integrals-of-Motion space. These stars likely include members of previously identified substructures such as Monoceros, A13, and the Triangulum-Andromeda cloud (TriAnd). We show that these stars are on nearly circular orbits on both sides of the Galactic plane. We can see velocity($V_{Z}$) gradient along Y-axis especially for the south GASS members. Our GASS members have similar energy and angular momentum distributions to thin disk stars. Their location in [$α$/M] vs. [M/H] space is more metal poor than typical thin disk stars, with [$α$/M] \textbf{lower} than the thick disk. We infer that our GASS members are part of the outer metal-poor disk stars, and the outer-disk extends to 30 kpc. Considering the distance range and $α$-abundance features, GASS could be formed after the thick disk was formed due to the molecular cloud density decreased in the outer disk where the SFR might be less efficient than the inner disk.

astro-ph.GA↗

arXiv2020

CrossNER: Evaluating Cross-Domain Named Entity Recognition

Cross-domain named entity recognition (NER) models are able to cope with the scarcity issue of NER samples in target domains. However, most of the existing NER benchmarks lack domain-specialized entity types or do not focus on a certain domain, leading to a less effective cross-domain evaluation. To address these obstacles, we introduce a cross-domain NER dataset (CrossNER), a fully-labeled collection of NER data spanning over five diverse domains with specialized entity categories for different domains. Additionally, we also provide a domain-related corpus since using it to continue pre-training language models (domain-adaptive pre-training) is effective for the domain adaptation. We then conduct comprehensive experiments to explore the effectiveness of leveraging different levels of the domain corpus and pre-training strategies to do domain-adaptive pre-training for the cross-domain task. Results show that focusing on the fractional corpus containing domain-specialized entities and utilizing a more challenging pre-training strategy in domain-adaptive pre-training are beneficial for the NER domain adaptation, and our proposed method can consistently outperform existing cross-domain NER baselines. Nevertheless, experiments also illustrate the challenge of this cross-domain NER task. We hope that our dataset and baselines will catalyze research in the NER domain adaptation area. The code and data are available at https://github.com/zliucr/CrossNER.

cs.CL↗

arXiv2020

CAiRE-COVID: A Question Answering and Query-focused Multi-Document Summarization System for COVID-19 Scholarly Information Management

We present CAiRE-COVID, a real-time question answering (QA) and multi-document summarization system, which won one of the 10 tasks in the Kaggle COVID-19 Open Research Dataset Challenge, judged by medical experts. Our system aims to tackle the recent challenge of mining the numerous scientific articles being published on COVID-19 by answering high priority questions from the community and summarizing salient question-related information. It combines information extraction with state-of-the-art QA and query-focused multi-document summarization techniques, selecting and highlighting evidence snippets from existing literature given a query. We also propose query-focused abstractive and extractive multi-document summarization methods, to provide more relevant information related to the question. We further conduct quantitative experiments that show consistent improvements on various metrics for each module. We have launched our website CAiRE-COVID for broader use by the medical community, and have open-sourced the code for our system, to bootstrap further study by other researches.

cs.CL↗

arXiv2020

Hybrid-drive pressure suppressing implosion instabilities and offering nonstagnation hotspot ignition with low convergence ratio for high-gain inertial fusion

In laser-drive ICF, hybrid drive (HD) combined direct drive (DD) and indirect drive (ID) offers a smoothed HD pressure $P_{HD}$, far higher than the ablation pressure in ID and DD, to suppress hydrodynamic instabilities. In this letter, simulations of a new robust HD ignition target show that maximal HD pressure as high as $P_{HD} \sim$ 650 Mbar driven by a novel "bulldozer" effect is achieved, resulting in nonstagnation hotspot ignition at the convergence ratio $C_r \sim $23, and finally, fusion energy gain $\sim$ 10 in total laser energy = 1.42 MJ. Two-dimensional simulations have confirmed that hydrodynamic instabilities are suppressed. A well-fitted scale of maximal HD pressure $P_{HD}$ (Mbar)= $BE_{DD}^{1/4} T_r$ is found from simulations of different targets and laser energies as long as $T_r> 160$ eV, where B is the constant depending on ablator materials, $E_{DD}$ in kJ is DD laser energy and $T_r$ in 100 eV is radiation temperature depending on ID laser energy $E_{ID}$. $P_{HD}\geq$ 450 Mbar is requested for hotspot ignition. This scale from "bulldozer" effect is also available as $E_{DD}$ is reduced to kJ. Experiments have verified $P_{HD}$ about 3.5 times radiation ablation pressure for CH ablator using $E_{ID}=43$ kJ ($T_r \simeq$200 eV) and $E_{DD}$=3.6 kJ, also shown that both backscattering fraction and hot-electron energy fraction for DD laser intensity $\sim 1.8 \times 10^{15} {\rm w\cdot cm^{-2}}$ are about a third of the traditional DD laser-plasma interaction

physics.plasm-ph↗

arXiv2020

Co-optimisation and Settlement of Power-Gas Coupled System in Day-ahead Market under Multiple Uncertainties

The interdependency of power systems and natural gas systems is being reinforced by the emerging power-to-gas facilities (PtGs), and the existing gas-fired generators. To jointly improve the efficiency and security under diverse uncertainties from renewable energy resources and load demands, it is essential to co-optimise these two energy systems for day-ahead market clearance. In this paper, a data-driven integrated electricity-gas system stochastic co-optimisation model is proposed. The model is accurately approximated by sequential mixed integer second-order cone programming, which can then be solved in parallel and decentralised manners by leveraging generalised Benders decomposition. Since the price formation and settlement issues have rarely been investigated for integrated electricity-gas systems in an uncertainty setting, a novel concept of expected locational marginal value is proposed to credit the flexibility of PtGs that helps hedging uncertainties. By comparing with a deterministic model and a distributionally robust model, the advantage of the proposed stochastic model and the efficiency of the proposed solution method are validated. Detailed results of pricing and settlement for PtGs are presented, showing that the expected locational marginal value can fairly credit the contribution of PtGs and reflect the system deficiency of capturing uncertainties.

eess.SY↗

arXiv2020

A Natural Language Processing Pipeline of Chinese Free-text Radiology Reports for Liver Cancer Diagnosis

Despite the rapid development of natural language processing (NLP) implementation in electronic medical records (EMRs), Chinese EMRs processing remains challenging due to the limited corpus and specific grammatical characteristics, especially for radiology reports. In this study, we designed an NLP pipeline for the direct extraction of clinically relevant features from Chinese radiology reports, which is the first key step in computer-aided radiologic diagnosis. The pipeline was comprised of named entity recognition, synonyms normalization, and relationship extraction to finally derive the radiological features composed of one or more terms. In named entity recognition, we incorporated lexicon into deep learning model bidirectional long short-term memory-conditional random field (BiLSTM-CRF), and the model finally achieved an F1 score of 93.00%. With the extracted radiological features, least absolute shrinkage and selection operator and machine learning methods (support vector machine, random forest, decision tree, and logistic regression) were used to build the classifiers for liver cancer prediction. For liver cancer diagnosis, random forest had the highest predictive performance in liver cancer diagnosis (F1 score 86.97%, precision 87.71%, and recall 86.25%). This work was a comprehensive NLP study focusing on Chinese radiology reports and the application of NLP in cancer risk prediction. The proposed NLP pipeline for the radiological feature extraction could be easily implemented in other kinds of Chinese clinical texts and other disease predictive tasks.

cs.CL↗

arXiv2020

Microscopic fine-grained instance classification through deep attention

Fine-grained classification of microscopic image data with limited samples is an open problem in computer vision and biomedical imaging. Deep learning based vision systems mostly deal with high number of low-resolution images, whereas subtle detail in biomedical images require higher resolution. To bridge this gap, we propose a simple yet effective deep network that performs two tasks simultaneously in an end-to-end manner. First, it utilises a gated attention module that can focus on multiple key instances at high resolution without extra annotations or region proposals. Second, the global structural features and local instance features are fused for final image level classification. The result is a robust but lightweight end-to-end trainable deep network that yields state-of-the-art results in two separate fine-grained multi-instance biomedical image classification tasks: a benchmark breast cancer histology dataset and our new fungi species mycology dataset. In addition, we demonstrate the interpretability of the proposed model by visualising the concordance of the learned features with clinically relevant features.

cs.CV↗

arXiv2020

Learning Knowledge Bases with Parameters for Task-Oriented Dialogue Systems

Task-oriented dialogue systems are either modularized with separate dialogue state tracking (DST) and management steps or end-to-end trainable. In either case, the knowledge base (KB) plays an essential role in fulfilling user requests. Modularized systems rely on DST to interact with the KB, which is expensive in terms of annotation and inference time. End-to-end systems use the KB directly as input, but they cannot scale when the KB is larger than a few hundred entries. In this paper, we propose a method to embed the KB, of any size, directly into the model parameters. The resulting model does not require any DST or template responses, nor the KB as input, and it can dynamically update its KB via fine-tuning. We evaluate our solution in five task-oriented dialogue datasets with small, medium, and large KB size. Our experiments show that end-to-end models can effectively embed knowledge bases in their parameters and achieve competitive performance in all evaluated datasets.

cs.CL↗

arXiv2020

Few-Shot Learning with Intra-Class Knowledge Transfer

We consider the few-shot classification task with an unbalanced dataset, in which some classes have sufficient training samples while other classes only have limited training samples. Recent works have proposed to solve this task by augmenting the training data of the few-shot classes using generative models with the few-shot training samples as the seeds. However, due to the limited number of the few-shot seeds, the generated samples usually have small diversity, making it difficult to train a discriminative classifier for the few-shot classes. To enrich the diversity of the generated samples, we propose to leverage the intra-class knowledge from the neighbor many-shot classes with the intuition that neighbor classes share similar statistical information. Such intra-class information is obtained with a two-step mechanism. First, a regressor trained only on the many-shot classes is used to evaluate the few-shot class means from only a few samples. Second, superclasses are clustered, and the statistical mean and feature variance of each superclass are used as transferable knowledge inherited by the children few-shot classes. Such knowledge is then used by a generator to augment the sparse training data to help the downstream classification tasks. Extensive experiments show that our method achieves state-of-the-art across different datasets and $n$-shot settings.

cs.CV↗

arXiv2020

Differential rotation of the halo traced by the K-giant stars

We use K-giant stars selected from the LAMOST DR5 to study the variation of the rotational velocity of the galactic halo at different space positions. Modelling the rotational velocity distribution with both the halo and disk components, we find that the rotational velocity of the halo population decreases almost linearly with increasing vertical distance to the galactic disk plane, $Z$, at fixed galactocentric radius, $R$. The samples are separated into two parts with $6<R<12$ kpc and $12<R<20$ kpc. We derive that the decreasing rates along $Z$ for the two subsamples are $-3.07\pm0.63$ and $-1.89\pm0.37$ km s$^{-1}$ kpc$^{-1}$, respectively. Compared with the TNG simulations, we suggest that this trend is probably caused by the interaction between the disk and halo. The results from the simulations show that only the oblate halo can provide a decreasing rotational velocity with an increasing $Z$. This indicates that the Galactic halo is oblate with galactocentric radius $R<20$ kpc. On the other hand, the flaring of the disk component (mainly the thick disk) is clearly traced by this study, with $R$ between 12 and 20 kpc, the disk can vertically extend to $6\sim10$ kpc above the disk plane. What is more interesting is that, we find the Gaia-Enceladus-Sausage (GES) component has a significant contribution only in the halo with $R<12$ kpc, i.e. a fraction of 23$-$47\%. While in the outer subsample, the contribution is too low to be well constrained.

astro-ph.GA↗

arXiv2020

Structure of minimal 2-spheres of constant curvature in the complex hyperquadric

In this paper, the singular-value decomposition theory of complex matrices is explored to study constantly curved 2-spheres minimal in both $\mathbb{C}P^n$ and the hyperquadric of $\mathbb{C}P^n$. The moduli space of all those noncongruent ones is introduced, which can be described by certain complex symmetric matrices modulo an appropriate group action. Using this description, many examples, such as constantly curved holomorphic 2-spheres of higher degree, nonhomogenous minimal 2-spheres of constant curvature, etc., are constructed. Uniqueness is proven for the totally real constantly curved 2-sphere minimal in both the hyperquadric and $\mathbb{C}P^n$.

math.DG↗

arXiv2020

Machine Learning in Heliophysics and Space Weather Forecasting: A White Paper of Findings and Recommendations

The authors of this white paper met on 16-17 January 2020 at the New Jersey Institute of Technology, Newark, NJ, for a 2-day workshop that brought together a group of heliophysicists, data providers, expert modelers, and computer/data scientists. Their objective was to discuss critical developments and prospects of the application of machine and/or deep learning techniques for data analysis, modeling and forecasting in Heliophysics, and to shape a strategy for further developments in the field. The workshop combined a set of plenary sessions featuring invited introductory talks interleaved with a set of open discussion sessions. The outcome of the discussion is encapsulated in this white paper that also features a top-level list of recommendations agreed by participants.

astro-ph.SR↗