arXiv subjects

Gang Wang

Publications and source records attributed to Gang Wang.

At least 415 records · Page 23Linked to original sources

arXiv2018

Canonical Correlation Analysis of Datasets with a Common Source Graph

Canonical correlation analysis (CCA) is a powerful technique for discovering whether or not hidden sources are commonly present in two (or more) datasets. Its well-appreciated merits include dimensionality reduction, clustering, classification, feature selection, and data fusion. The standard CCA however, does not exploit the geometry of the common sources, which may be available from the given data or can be deduced from (cross-) correlations. In this paper, this extra information provided by the common sources generating the data is encoded in a graph, and is invoked as a graph regularizer. This leads to a novel graph-regularized CCA approach, that is termed graph (g) CCA. The novel gCCA accounts for the graph-induced knowledge of common sources, while minimizing the distance between the wanted canonical variables. Tailored for diverse practical settings where the number of data is smaller than the data vector dimensions, the dual formulation of gCCA is also developed. One such setting includes kernels that are incorporated to account for nonlinear data dependencies. The resultant graph-kernel (gk) CCA is also obtained in closed form. Finally, corroborating image classification tests over several real datasets are presented to showcase the merits of the novel linear, dual, and kernel approaches relative to competing alternatives.

cs.LG↗

arXiv2018

Stack-Captioning: Coarse-to-Fine Learning for Image Captioning

The existing image captioning approaches typically train a one-stage sentence decoder, which is difficult to generate rich fine-grained descriptions. On the other hand, multi-stage image caption model is hard to train due to the vanishing gradient problem. In this paper, we propose a coarse-to-fine multi-stage prediction framework for image captioning, composed of multiple decoders each of which operates on the output of the previous stage, producing increasingly refined image descriptions. Our proposed learning approach addresses the difficulty of vanishing gradients during training by providing a learning objective function that enforces intermediate supervisions. Particularly, we optimize our model with a reinforcement learning approach which utilizes the output of each intermediate decoder's test-time inference algorithm as well as the output of its preceding decoder to normalize the rewards, which simultaneously solves the well-known exposure bias problem and the loss-evaluation mismatch problem. We extensively evaluate the proposed approach on MSCOCO and show that our approach can achieve the state-of-the-art performance.

cs.CV↗

arXiv2018

Multimodal Recurrent Neural Networks with Information Transfer Layers for Indoor Scene Labeling

This paper proposes a new method called Multimodal RNNs for RGB-D scene semantic segmentation. It is optimized to classify image pixels given two input sources: RGB color channels and Depth maps. It simultaneously performs training of two recurrent neural networks (RNNs) that are crossly connected through information transfer layers, which are learnt to adaptively extract relevant cross-modality features. Each RNN model learns its representations from its own previous hidden states and transferred patterns from the other RNNs previous hidden states; thus, both model-specific and crossmodality features are retained. We exploit the structure of quad-directional 2D-RNNs to model the short and long range contextual information in the 2D input image. We carefully designed various baselines to efficiently examine our proposed model structure. We test our Multimodal RNNs method on popular RGB-D benchmarks and show how it outperforms previous methods significantly and achieves competitive results with other state-of-the-art works.

cs.CV↗

arXiv2018

Lack of superconductivity in the phase diagram of single-crystalline Eu(Fe1-xCox)2As2 grown by transition metal arsenide flux

The interplay of magnetism and superconductivity (SC) has been a focus of interest in condensed matter physics for decades. EuFe2As2 has been identified as a potential platform to investigate interactions between structural, magnetic, electronic effects as well as coexistence of magnetism and SC with similar transition temperatures. However, there are obvious inconsistencies in the reported phase diagrams of Eu(Fe1-xCox)2As2 crystals grown by different methods. For transition metal arsenide (TMA)-flux-grown crystals, even the existence of SC is open for dispute. Here we re-examine the phase diagram of single-crystalline Eu(Fe1-xCox)2As2 grown by TMA flux. We found that the lattice parameter c shrinks linearly with Co doping, almost twice as fast as that of the tin-flux-grown crystals. With Co doping, the spin-density-wave (SDW) order of Fe sublattice is quickly suppressed, being detected only up to x = 0.08. The magnetic ordering temperature of the Eu2+ sublattice (TEu) shows a systematic evolution with Co doping, first going down and reaching a minimum at x = 0.08, then increasing continuously up to x = 0.24. Over the whole composition range investigated, no signature of SC is observed.

cond-mat.supr-con↗

arXiv2018

Towards the Adoption of Anti-spoofing Protocols

Email spoofing is a critical step of phishing, where the attacker impersonates someone the victim knows or trusts. In this paper, we conduct a qualitative study to explore why email spoofing is still possible after years of efforts to develop and deploy anti-spoofing protocols (e.g., SPF, DKIM, DMARC). First, we measure the protocol adoption by scanning 1 million Internet domains. We find the adoption rates are still low, especially for the new DMARC (3.1%). Second, to understand the reasons behind the low-adoption rate, we collect 4293 discussion threads (25.7K messages) from the Internet Engineering Task Force (IETF), a working group formed to develop and promote Internet standards. Our analysis shows key security and usability limitations in the protocol design, which makes it difficult to generate a positive "net effect" for a wide adoption. We validate our results by interviewing email administrators and discuss key implications for future anti-spoofing solutions.

cs.CR↗

arXiv2018

Stochastic Downsampling for Cost-Adjustable Inference and Improved Regularization in Convolutional Networks

It is desirable to train convolutional networks (CNNs) to run more efficiently during inference. In many cases however, the computational budget that the system has for inference cannot be known beforehand during training, or the inference budget is dependent on the changing real-time resource availability. Thus, it is inadequate to train just inference-efficient CNNs, whose inference costs are not adjustable and cannot adapt to varied inference budgets. We propose a novel approach for cost-adjustable inference in CNNs - Stochastic Downsampling Point (SDPoint). During training, SDPoint applies feature map downsampling to a random point in the layer hierarchy, with a random downsampling ratio. The different stochastic downsampling configurations known as SDPoint instances (of the same model) have computational costs different from each other, while being trained to minimize the same prediction loss. Sharing network parameters across different instances provides significant regularization boost. During inference, one may handpick a SDPoint instance that best fits the inference budget. The effectiveness of SDPoint, as both a cost-adjustable inference approach and a regularizer, is validated through extensive experiments on image classification.

cs.LG↗

arXiv2018

Skeleton-Based Human Action Recognition with Global Context-Aware Attention LSTM Networks

Human action recognition in 3D skeleton sequences has attracted a lot of research attention. Recently, Long Short-Term Memory (LSTM) networks have shown promising performance in this task due to their strengths in modeling the dependencies and dynamics in sequential data. As not all skeletal joints are informative for action recognition, and the irrelevant joints often bring noise which can degrade the performance, we need to pay more attention to the informative ones. However, the original LSTM network does not have explicit attention ability. In this paper, we propose a new class of LSTM network, Global Context-Aware Attention LSTM (GCA-LSTM), for skeleton based action recognition. This network is capable of selectively focusing on the informative joints in each frame of each skeleton sequence by using a global context memory cell. To further improve the attention capability of our network, we also introduce a recurrent attention mechanism, with which the attention performance of the network can be enhanced progressively. Moreover, we propose a stepwise training scheme in order to train our network effectively. Our approach achieves state-of-the-art performance on five challenging benchmark datasets for skeleton based action recognition.

cs.CV↗

arXiv2018

A study of the new hemispherical 9-inch PMT

The new hemispherical photomultiplier tubes (PMTs) with 9 inch diameter from Hainan Zhanchuang Photonics Technology Co.,Ltd (HZC) have been studied. Narrow transit time spread (FWHM=2.35 ns) accompanied by small nonlinearity (750 photoelectrons at 5%) and high gain (1E7 ) with good single photoelectron (PE) resolution have been observed. 11 PMTs of this type are deployed and studied in the prototype detector for JUNO at IHEP, China.

physics.ins-det↗

arXiv2018

Learning Hierarchical Features for Visual Object Tracking with Recursive Neural Networks

Recently, deep learning has achieved very promising results in visual object tracking. Deep neural networks in existing tracking methods require a lot of training data to learn a large number of parameters. However, training data is not sufficient for visual object tracking as annotations of a target object are only available in the first frame of a test sequence. In this paper, we propose to learn hierarchical features for visual object tracking by using tree structure based Recursive Neural Networks (RNN), which have fewer parameters than other deep neural networks, e.g. Convolutional Neural Networks (CNN). First, we learn RNN parameters to discriminate between the target object and background in the first frame of a test sequence. Tree structure over local patches of an exemplar region is randomly generated by using a bottom-up greedy search strategy. Given the learned RNN parameters, we create two dictionaries regarding target regions and corresponding local patches based on the learned hierarchical features from both top and leaf nodes of multiple random trees. In each of the subsequent frames, we conduct sparse dictionary coding on all candidates to select the best candidate as the new target location. In addition, we online update two dictionaries to handle appearance changes of target objects. Experimental results demonstrate that our feature learning algorithm can significantly improve tracking performance on benchmark datasets.

cs.CV↗

arXiv2018

Revisiting Email Spoofing Attacks

The email system is the central battleground against phishing and social engineering attacks, and yet email providers still face key challenges to authenticate incoming emails. As a result, attackers can apply spoofing techniques to impersonate a trusted entity to conduct highly deceptive phishing attacks. In this work, we study email spoofing to answer three key questions: (1) How do email providers detect and handle forged emails? (2) Under what conditions can forged emails penetrate the defense to reach user inbox? (3) Once the forged email gets in, how email providers warn users? Is the warning truly effective? We answer these questions through end-to-end measurements on 35 popular email providers (used by billions of users), and extensive user studies (N = 913) that consist of both simulated and real-world phishing experiments. We have four key findings. First, most popular email providers have the necessary protocols to detect spoofing, but still allow forged emails to get into user inbox (e.g., Yahoo Mail, iCloud, Gmail). Second, once a forged email gets in, most email providers have no warnings for users, particularly on mobile email apps. Some providers (e.g., Gmail Inbox) even have misleading UIs that make the forged email look authentic. Third, a few email providers (9/35) have implemented visual security cues for unverified emails, which demonstrate a positive impact to reduce risky user actions. Comparing simulated experiments with realistic phishing tests, we observe that the impact of security cue is less significant when users are caught off guard in the real-world setting.

cs.CR↗

arXiv2017

Compressive Phase Retrieval via Reweighted Amplitude Flow

The problem of reconstructing a sparse signal vector from magnitude-only measurements (a.k.a., compressive phase retrieval), emerges naturally in diverse applications, but it is NP-hard in general. Building on recent advances in nonconvex optimization, this paper puts forth a new algorithm that is termed compressive reweighted amplitude flow and abbreviated as CRAF, for compressive phase retrieval. Specifically, CRAF operates in two stages. The first stage seeks a sparse initial guess via a new spectral procedure. In the second stage, CRAF implements a few hard thresholding based iterations using reweighted gradients. When there are sufficient measurements, CRAF provably recovers the underlying signal vector exactly with high probability under suitable conditions. Moreover, its sample complexity coincides with that of the state-of-the-art procedures. Finally, substantial simulated tests showcase remarkable performance of the new spectral initialization, as well as improved exact recovery relative to competing alternatives.

cs.IT↗

arXiv2017

Numerical simulation of time delay interferometry for new LISA, TAIJI and other LISA-like missions

The success of LISA Pathfinder in demonstrating the LISA drag-free requirement paved the road of using space missions for detecting low-frequency and middle-frequency GWs. The new LISA GW mission proposes to use arm length of 2.5 Gm (1 Gm = 106 km). The TAIJI GW mission proposes to use arm length of 3 Gm. In order to attain the requisite sensitivity, laser frequency noise must be suppressed to below the secondary noises such as the optical path noise, acceleration noise etc. In previous papers, we have performed the numerical simulation of the time delay interferometry (TDI) for original LISA, ASTROD-GW and eLISA together with a LISA-type mission with a nominal arm length of 2 Gm using the CGC 2.7/CGC2.7.1 ephemeris framework. In this paper, we follow the same procedure to simulate the time delay interferometry numerically for the new LISA mission and the TAIJI mission together with LISA-like missions of arm length 1, 2, 4, 5 and 6 Gm. The resulting optical path differences of the second-generation TDI calculated for new LISA, TAIJI, and LISA-like missions or arm length 1, 2, 4, 5 & 6 Gm are well below their respective limits which the laser frequency noise is required to be suppressed. However, for of the first generation X, Y, and Z TDI configurations, the original requirements need to be relaxed by 3 to 30 fold to be satisfied. For the new LISA and TAIJI, about one order of magnitude relaxation would be good and recommended; this could be borne on the laser stability requirement in view of recent progress in laser stability. Compared with X, Y and Z, the X+Y+Z configuration does have a good cancellation of path length differences and could serve as a null string detection check. We compile and compare the resulting differences of various TDI configurations due to the different arm lengths for various LISA-like mission proposals and for the ASTROD-GW mission proposal.

astro-ph.IM↗

arXiv2017

Excitons in atomically thin transition metal dichalcogenides

Atomically thin materials such as graphene and monolayer transition metal dichalcogenides (TMDs) exhibit remarkable physical properties resulting from their reduced dimensionality and crystal symmetry. The family of semiconducting transition metal dichalcogenides is an especially promising platform for fundamental studies of two-dimensional (2D) systems, with potential applications in optoelectronics and valleytronics due to their direct band gap in the monolayer limit and highly efficient light-matter coupling. A crystal lattice with broken inversion symmetry combined with strong spin-orbit interactions leads to a unique combination of the spin and valley degrees of freedom. In addition, the 2D character of the monolayers and weak dielectric screening from the environment yield a significant enhancement of the Coulomb interaction. The resulting formation of bound electron-hole pairs, or excitons, dominates the optical and spin properties of the material. Here we review recent progress in our understanding of the excitonic properties in monolayer TMDs and lay out future challenges. We focus on the consequences of the strong direct and exchange Coulomb interaction, discuss exciton-light interaction and effects of other carriers and excitons on electron-hole pairs in TMDs. Finally, the impact on valley polarization is described and the tuning of the energies and polarization observed in applied electric and magnetic fields is summarized.

cond-mat.mtrl-sci↗

arXiv2017

Event-shape-engineering study of charge separation in heavy-ion collisions

Recent measurements of charge-dependent azimuthal correlations in high-energy heavy-ion collisions have indicated charge-separation signals perpendicular to the reaction plane, and have been related to the chiral magnetic effect (CME). However, the correlation signal is contaminated with the background caused by the collective motion (flow) of the collision system, and an effective approach is needed to remove the flow background from the correlation. We present a method study with simplified Monte Carlo simulations and a multi-phase transport model, and develop a scheme to reveal the true CME signal via the event-shape engineering with the flow vector of the particles of interest.

nucl-th↗

arXiv2017

Sparse Phase Retrieval via Truncated Amplitude Flow

This paper develops a novel algorithm, termed \emph{SPARse Truncated Amplitude flow} (SPARTA), to reconstruct a sparse signal from a small number of magnitude-only measurements. It deals with what is also known as sparse phase retrieval (PR), which is \emph{NP-hard} in general and emerges in many science and engineering applications. Upon formulating sparse PR as an amplitude-based nonconvex optimization task, SPARTA works iteratively in two stages: In stage one, the support of the underlying sparse signal is recovered using an analytically well-justified rule, and subsequently, a sparse orthogonality-promoting initialization is obtained via power iterations restricted on the support; and, in the second stage, the initialization is successively refined by means of hard thresholding based gradient-type iterations. SPARTA is a simple yet effective, scalable, and fast sparse PR solver. On the theoretical side, for any $n$-dimensional $k$-sparse ($k\ll n$) signal $\bm{x}$ with minimum (in modulus) nonzero entries on the order of $(1/\sqrt{k})\|\bm{x}\|_2$, SPARTA recovers the signal exactly (up to a global unimodular constant) from about $k^2\log n$ random Gaussian measurements with high probability. Furthermore, SPARTA incurs computational complexity on the order of $k^2n\log n$ with total runtime proportional to the time required to read the data, which improves upon the state-of-the-art by at least a factor of $k$. Finally, SPARTA is robust against additive noise of bounded support. Extensive numerical tests corroborate markedly improved recovery performance and speedups of SPARTA relative to existing alternatives.

cs.IT↗

arXiv2017

DPCA: Dimensionality Reduction for Discriminative Analytics of Multiple Large-Scale Datasets

Principal component analysis (PCA) has well-documented merits for data extraction and dimensionality reduction. PCA deals with a single dataset at a time, and it is challenged when it comes to analyzing multiple datasets. Yet in certain setups, one wishes to extract the most significant information of one dataset relative to other datasets. Specifically, the interest may be on identifying, namely extracting features that are specific to a single target dataset but not the others. This paper develops a novel approach for such so-termed discriminative data analysis, and establishes its optimality in the least-squares (LS) sense under suitable data modeling assumptions. The criterion reveals linear combinations of variables by maximizing the ratio of the variance of the target data to that of the remainders. The novel approach solves a generalized eigenvalue problem by performing SVD just once. Numerical tests using synthetic and real datasets showcase the merits of the proposed approach relative to its competing alternatives.

cs.LG↗

arXiv2017

Recent Advances in Convolutional Neural Networks

In the last few years, deep learning has led to very good performance on a variety of problems, such as visual recognition, speech recognition and natural language processing. Among different types of deep neural networks, convolutional neural networks have been most extensively studied. Leveraging on the rapid growth in the amount of the annotated data and the great improvements in the strengths of graphics processor units, the research on convolutional neural networks has been emerged swiftly and achieved state-of-the-art results on various tasks. In this paper, we provide a broad survey of the recent advances in convolutional neural networks. We detailize the improvements of CNN on different aspects, including layer design, activation function, loss function, regularization, optimization and fast computation. Besides, we also introduce various applications of convolutional neural networks in computer vision, speech and natural language processing.

cs.CV↗

arXiv2017

Learning Fine-grained Features via a CNN Tree for Large-scale Classification

We propose a novel approach to enhance the discriminability of Convolutional Neural Networks (CNN). The key idea is to build a tree structure that could progressively learn fine-grained features to distinguish a subset of classes, by learning features only among these classes. Such features are expected to be more discriminative, compared to features learned for all the classes. We develop a new algorithm to effectively learn the tree structure from a large number of classes. Experiments on large-scale image classification tasks demonstrate that our method could boost the performance of a given basic CNN model. Our method is quite general, hence it can potentially be used in combination with many other deep learning models.

cs.CV↗