arXiv subjects

Chen Chen

Publications and source records attributed to Chen Chen.

At least 955 records · Page 53Linked to original sources

arXiv2019

Deep learning for cardiac image segmentation: A review

Deep learning has become the most widely used approach for cardiac image segmentation in recent years. In this paper, we provide a review of over 100 cardiac image segmentation papers using deep learning, which covers common imaging modalities including magnetic resonance imaging (MRI), computed tomography (CT), and ultrasound (US) and major anatomical structures of interest (ventricles, atria and vessels). In addition, a summary of publicly available cardiac image datasets and code repositories are included to provide a base for encouraging reproducible research. Finally, we discuss the challenges and limitations with current deep learning-based approaches (scarcity of labels, model generalizability across different domains, interpretability) and suggest potential directions for future research.

eess.IV↗

arXiv2019

Multilingual Dialogue Generation with Shared-Private Memory

Existing dialog systems are all monolingual, where features shared among different languages are rarely explored. In this paper, we introduce a novel multilingual dialogue system. Specifically, we augment the sequence to sequence framework with improved shared-private memory. The shared memory learns common features among different languages and facilitates a cross-lingual transfer to boost dialogue systems, while the private memory is owned by each separate language to capture its unique feature. Experiments conducted on Chinese and English conversation corpora of different scales show that our proposed architecture outperforms the individually learned model with the help of the other language, where the improvement is particularly distinct when the training data is limited.

cs.CL↗

arXiv2019

Essentia: Mining Domain-Specific Paraphrases with Word-Alignment Graphs

Paraphrases are important linguistic resources for a wide variety of NLP applications. Many techniques for automatic paraphrase mining from general corpora have been proposed. While these techniques are successful at discovering generic paraphrases, they often fail to identify domain-specific paraphrases (e.g., {staff, concierge} in the hospitality domain). This is because current techniques are often based on statistical methods, while domain-specific corpora are too small to fit statistical methods. In this paper, we present an unsupervised graph-based technique to mine paraphrases from a small set of sentences that roughly share the same topic or intent. Our system, Essentia, relies on word-alignment techniques to create a word-alignment graph that merges and organizes tokens from input sentences. The resulting graph is then used to generate candidate paraphrases. We demonstrate that our system obtains high-quality paraphrases, as evaluated by crowd workers. We further show that the majority of the identified paraphrases are domain-specific and thus complement existing paraphrase databases.

cs.CL↗

arXiv2019

Form factors for the Nucleon-to-Roper electromagnetic transition at large-$Q^2$

We report on a recent calculation of all Roper-related electromagnetic transtions form factors, covering the range of energies that next-to-come planned experiments are expected to map. Direct reliable calculations were performed, within a Poincaré covariant approach of the three-body bound-state problem, up to $Q^2/m^2_N$=6; approximated then by applying the Schlessinger point method and the results eventually extended up to $Q^2/m^2_N\simeq$12 via analytic continuation.

nucl-th↗

arXiv2019

Renyi Differentially Private ADMM for Non-Smooth Regularized Optimization

In this paper we consider the problem of minimizing composite objective functions consisting of a convex differentiable loss function plus a non-smooth regularization term, such as $L_1$ norm or nuclear norm, under Rényi differential privacy (RDP). To solve the problem, we propose two stochastic alternating direction method of multipliers (ADMM) algorithms: ssADMM based on gradient perturbation and mpADMM based on output perturbation. Both algorithms decompose the original problem into sub-problems that have closed-form solutions. The first algorithm, ssADMM, applies the recent privacy amplification result for RDP to reduce the amount of noise to add. The second algorithm, mpADMM, numerically computes the sensitivity of ADMM variable updates and releases the updated parameter vector at the end of each epoch. We compare the performance of our algorithms with several baseline algorithms on both real and simulated datasets. Experimental results show that, in high privacy regimes (small $ε$), ssADMM and mpADMM outperform other baseline algorithms in terms of classification and feature selection performance, respectively.

cs.LG↗

arXiv2019

Pose Estimation for Texture-less Shiny Objects in a Single RGB Image Using Synthetic Training Data

In the industrial domain, the pose estimation of multiple texture-less shiny parts is a valuable but challenging task. In this particular scenario, it is impractical to utilize keypoints or other texture information because most of them are not actual features of the target but the reflections of surroundings. Moreover, the similarity of color also poses a challenge in segmentation. In this article, we propose to divide the pose estimation process into three stages: object detection, features detection and pose optimization. A convolutional neural network was utilized to perform object detection. Concerning the reliability of surface texture, we leveraged the contour information for estimating pose. Since conventional contour-based methods are inapplicable to clustered metal parts due to the difficulties in segmentation, we use the dense discrete points along the metal part edges as semantic keypoints for contour detection. Afterward, we exploit both keypoint information and CAD model to calculate the 6D pose of each object in view. A typical implementation of deep learning methods not only requires a large amount of training data, but also relies on intensive human labor for labeling the datasets. Therefore, we propose an approach to generate datasets and label them automatically. Despite not using any real-world photos for training, a series of experiments showed that the algorithm built on synthetic data perform well in the real environment.

cs.RO↗

arXiv2019

3D Dilated Multi-Fiber Network for Real-time Brain Tumor Segmentation in MRI

Brain tumor segmentation plays a pivotal role in medical image processing. In this work, we aim to segment brain MRI volumes. 3D convolution neural networks (CNN) such as 3D U-Net and V-Net employing 3D convolutions to capture the correlation between adjacent slices have achieved impressive segmentation results. However, these 3D CNN architectures come with high computational overheads due to multiple layers of 3D convolutions, which may make these models prohibitive for practical large-scale applications. To this end, we propose a highly efficient 3D CNN to achieve real-time dense volumetric segmentation. The network leverages the 3D multi-fiber unit which consists of an ensemble of lightweight 3D convolutional networks to significantly reduce the computational cost. Moreover, 3D dilated convolutions are used to build multi-scale feature representations. Extensive experimental results on the BraTS-2018 challenge dataset show that the proposed architecture greatly reduces computation cost while maintaining high accuracy for brain tumor segmentation. The source code can be found at https://github.com/China-LiuXiaopeng/BraTS-DMFNet

cs.CV↗

arXiv2019

Pion and Kaon Structure at the Electron-Ion Collider

Understanding the origin and dynamics of hadron structure and in turn that of atomic nuclei is a central goal of nuclear physics. This challenge entails the questions of how does the roughly 1 GeV mass-scale that characterizes atomic nuclei appear; why does it have the observed value; and, enigmatically, why are the composite Nambu-Goldstone (NG) bosons in quantum chromodynamics (QCD) abnormally light in comparison? In this perspective, we provide an analysis of the mass budget of the pion and proton in QCD; discuss the special role of the kaon, which lies near the boundary between dominance of strong and Higgs mass-generation mechanisms; and explain the need for a coherent effort in QCD phenomenology and continuum calculations, in exa-scale computing as provided by lattice QCD, and in experiments to make progress in understanding the origins of hadron masses and the distribution of that mass within them. We compare the unique capabilities foreseen at the electron-ion collider (EIC) with those at the hadron-electron ring accelerator (HERA), the only previous electron-proton collider; and describe five key experimental measurements, enabled by the EIC and aimed at delivering fundamental insights that will generate concrete answers to the questions of how mass and structure arise in the pion and kaon, the Standard Model's NG modes, whose surprisingly low mass is critical to the evolution of our Universe.

nucl-ex↗

arXiv2019

Spectrum and structure of octet and decuplet baryons and their positive-parity excitations

A continuum approach to the three valence-quark bound-state problem in quantum field theory, employing parametrisations of the necessary kernel elements, is used to compute the spectrum and Poincaré-covariant wave functions for all flavour-$SU(3)$ octet and decuplet baryons and their first positive-parity excitations. Such analyses predict the existence of nonpointlike, dynamical quark-quark (diquark) correlations within all baryons; and a uniformly sound description of the systems studied is obtained by retaining flavour-antitriplet--scalar and flavour-sextet--pseudovector diquarks. Thus constituted, the rest-frame wave function of every system studied is primarily $S$-wave in character; and the first positive-parity excitation of each octet or decuplet baryon exhibits the characteristics of a radial excitation. Importantly, every ground-state octet and decuplet baryon possesses a radial excitation. Hence, the analysis predicts the existence of positive-parity excitations of the $Ξ$, $Ξ^\ast$, $Ω$ baryons, with masses, respectively (in GeV): 1.84(08), 1.89(04), 2.05(02). These states have not yet been empirically identified. This body of analysis suggests that the expression of emergent mass generation is the same in all $u$, $d$, $s$ baryons and, notably, that dynamical quark-quark correlations play an essential role in the structure of each one. It also provides the basis for developing an array of predictions that can be tested in new generation experiments.

nucl-th↗

arXiv2019

Vehicular Edge Computing and Networking: A Survey

As one key enabler of Intelligent Transportation System (ITS), Vehicular Ad Hoc Network (VANET) has received remarkable interest from academia and industry. The emerging vehicular applications and the exponential growing data have naturally led to the increased needs of communication, computation and storage resources, and also to strict performance requirements on response time and network bandwidth. In order to deal with these challenges, Mobile Edge Computing (MEC) is regarded as a promising solution. MEC pushes powerful computational and storage capacities from the remote cloud to the edge of networks in close proximity of vehicular users, which enables low latency and reduced bandwidth consumption. Driven by the benefits of MEC, many efforts have been devoted to integrating vehicular networks into MEC, thereby forming a novel paradigm named as Vehicular Edge Computing (VEC). In this paper, we provide a comprehensive survey of state-of-art research on VEC. First of all, we provide an overview of VEC, including the introduction, architecture, key enablers, advantages, challenges as well as several attractive application scenarios. Then, we describe several typical research topics where VEC is applied. After that, we present a careful literature review on existing research work in VEC by classification. Finally, we identify open research issues and discuss future research directions.

eess.SP↗

arXiv2019

An Efficient 3D CNN for Action/Object Segmentation in Video

Convolutional Neural Network (CNN) based image segmentation has made great progress in recent years. However, video object segmentation remains a challenging task due to its high computational complexity. Most of the previous methods employ a two-stream CNN framework to handle spatial and motion features separately. In this paper, we propose an end-to-end encoder-decoder style 3D CNN to aggregate spatial and temporal information simultaneously for video object segmentation. To efficiently process video, we propose 3D separable convolution for the pyramid pooling module and decoder, which dramatically reduces the number of operations while maintaining the performance. Moreover, we also extend our framework to video action segmentation by adding an extra classifier to predict the action label for actors in videos. Extensive experiments on several video datasets demonstrate the superior performance of the proposed approach for action and object segmentation compared to the state-of-the-art.

cs.CV↗

arXiv2019

Jo: The Smart Journal

We introduce Jo, a mobile application that attempts to improve user's well-being. Jo is a journaling application--users log their important moments via short texts and optionally an attached photo. Unlike a static journal, Jo analyzes these moments and helps users take action towards increased well-being. For example, Jo annotates each moment with a set of values (e.g., family, socialization, mindfulness), thereby giving the user insights about the balance in their lives. In addition, Jo helps the user create reminders that enable them to create additional happy moments. We describe the results of fielding Jo in a study of 39 participants. The results illustrate the promise of a journaling application that provides personalized feedback, and points at further research.

cs.HC↗

arXiv2019

Electronic Transport Evidence for Topological Nodal-Line Semimetals of ZrGeSe single crystals

Although the band topology of ZrGeSe has been studied via magnetic torque technique, the electronic transport behaviors related to the relativistic Fermions in ZrGeSe are still unknown. Here, we first report systematic electronic transport properties of high-quality ZrGeSe single crystals under magnetic fields up to 14 T. Resistivity plateaus of temperature dependent resistivity curves both in the presence and absence of magnetic fields as well as large, non-saturating magnetoresistance in low-temperature region were observed. By analyzing the temperature- and angular-dependent Shubnikov-de Haas oscillations and fitting it via the Lifshitz-Kosevich (LK) formula with the Berry phase being taken into account, we proved that Dirac fermions dominate the electronic transport behaviors of ZrGeSe and the presence of non-trivial Berry phase. First principles calculations demonstrate that ZrGeSe possesses Dirac bands and normal bands near Fermi surface, resulting in the observed magnetotransport phenomena. These results demonstrate that ZrGeSe is a topological nodal-line semimetal, which provides a fundamentally important platform to study the quantum physics of topological semimetals.

cond-mat.mtrl-sci↗

arXiv2019

Radiality Constraints for Resilient Reconfiguration of Distribution Systems: Formulation and Application to Microgrid Formation

Network reconfiguration is an effective strategy for different purposes of distribution systems (DSs), e.g., resilience enhancement. In particular, DS automation, distributed generation integration and microgrid (MG) technology development, etc., are empowering much more flexible reconfiguration and operation of the system, e.g., DSs or MGs with flexible boundaries. However, the formulation of DS reconfiguration-related optimization problems to include those new flexibilities is non-trivial, especially for the issue of topology, which has to be radial. That is, existing methods of formulating radiality constraints can cause underutilization of DS flexibilities. Thus, this work proposes a new method for radiality constraints formulation fully enabling the topological and some other related flexibilities of DSs, so that the reconfiguration-related optimization problems can have extended feasibility and enhanced optimality. Graph-theoretic supports are provided to certify its theoretical validity. As integer variables are involved, we also analyze the tightness and compactness issues. The proposed radiality constraints are specifically applied to post-disaster MG formation, which is involved in many DS resilience-oriented service restoration and/or infrastructure recovery problems. The resulting new MG formation model, which allows more flexible merge and/or separation of sub-grids, etc., establishes superiority over the models in the literature. Case studies are conducted on two test systems.

math.OC↗

arXiv2019

Self-Supervised Learning for Cardiac MR Image Segmentation by Anatomical Position Prediction

In the recent years, convolutional neural networks have transformed the field of medical image analysis due to their capacity to learn discriminative image features for a variety of classification and regression tasks. However, successfully learning these features requires a large amount of manually annotated data, which is expensive to acquire and limited by the available resources of expert image analysts. Therefore, unsupervised, weakly-supervised and self-supervised feature learning techniques receive a lot of attention, which aim to utilise the vast amount of available data, while at the same time avoid or substantially reduce the effort of manual annotation. In this paper, we propose a novel way for training a cardiac MR image segmentation network, in which features are learnt in a self-supervised manner by predicting anatomical positions. The anatomical positions serve as a supervisory signal and do not require extra manual annotation. We demonstrate that this seemingly simple task provides a strong signal for feature learning and with self-supervised learning, we achieve a high segmentation accuracy that is better than or comparable to a U-net trained from scratch, especially at a small data setting. When only five annotated subjects are available, the proposed method improves the mean Dice metric from 0.811 to 0.852 for short-axis image segmentation, compared to the baseline U-net.

cs.CV↗

arXiv2019

Improving the generalizability of convolutional neural network-based segmentation on CMR images

Convolutional neural network (CNN) based segmentation methods provide an efficient and automated way for clinicians to assess the structure and function of the heart in cardiac MR images. While CNNs can generally perform the segmentation tasks with high accuracy when training and test images come from the same domain (e.g. same scanner or site), their performance often degrades dramatically on images from different scanners or clinical sites. We propose a simple yet effective way for improving the network generalization ability by carefully designing data normalization and augmentation strategies to accommodate common scenarios in multi-site, multi-scanner clinical imaging data sets. We demonstrate that a neural network trained on a single-site single-scanner dataset from the UK Biobank can be successfully applied to segmenting cardiac MR images across different sites and different scanners without substantial loss of accuracy. Specifically, the method was trained on a large set of 3,975 subjects from the UK Biobank. It was then directly tested on 600 different subjects from the UK Biobank for intra-domain testing and two other sets for cross-domain testing: the ACDC dataset (100 subjects, 1 site, 2 scanners) and the BSCMR-AS dataset (599 subjects, 6 sites, 9 scanners). The proposed method produces promising segmentation results on the UK Biobank test set which are comparable to previously reported values in the literature, while also performing well on cross-domain test sets, achieving a mean Dice metric of 0.90 for the left ventricle, 0.81 for the myocardium and 0.82 for the right ventricle on the ACDC dataset; and 0.89 for the left ventricle, 0.83 for the myocardium on the BSCMR-AS dataset. The proposed method offers a potential solution to improve CNN-based model generalizability for the cross-scanner and cross-site cardiac MR image segmentation task.

eess.IV↗

arXiv2019

K-Core Maximization through Edge Additions

A popular model to measure the stability of a network is k-core - the maximal induced subgraph in which every vertex has at least k neighbors. Many studies maximize the number of vertices in k-core to improve the stability of a network. In this paper, we study the edge k-core problem: Given a graph G, an integer k and a budget b, add b edges to non-adjacent vertex pairs in G such that the k-core is maximized. We prove the problem is NP-hard and APX-hard. A heuristic algorithm is proposed on general graphs with effective optimization techniques. Comprehensive experiments on 9 real-life datasets demonstrate the effectiveness and the efficiency of our proposed methods.

cs.SI↗

arXiv2019

Critical Edge Identification: A K-Truss Based Model

In a social network, the strength of relationships between users can significantly affect the stability of the network. In this paper, we use the k-truss model to measure the stability of a social network. To identify critical connections, we propose a novel problem, named k-truss minimization. Given a social network G and a budget b, it aims to find b edges for deletion which can lead to the maximum number of edge breaks in the k-truss of G. We show that the problem is NP-hard. To accelerate the computation, novel pruning rules are developed to reduce the candidate size. In addition, we propose an upper bound based strategy to further reduce the searching space. Comprehensive experiments are conducted over real social networks to demonstrate the efficiency and effectiveness of the proposed techniques.

cs.SI↗