arXiv subjects

Shuang Li

Publications and source records attributed to Shuang Li.

At least 253 records · Page 14Linked to original sources

arXiv2018

Question-Guided Hybrid Convolution for Visual Question Answering

In this paper, we propose a novel Question-Guided Hybrid Convolution (QGHC) network for Visual Question Answering (VQA). Most state-of-the-art VQA methods fuse the high-level textual and visual features from the neural network and abandon the visual spatial information when learning multi-modal features.To address these problems, question-guided kernels generated from the input question are designed to convolute with visual features for capturing the textual and visual relationship in the early stage. The question-guided convolution can tightly couple the textual and visual information but also introduce more parameters when learning kernels. We apply the group convolution, which consists of question-independent kernels and question-dependent kernels, to reduce the parameter size and alleviate over-fitting. The hybrid convolution can generate discriminative multi-modal features with fewer parameters. The proposed approach is also complementary to existing bilinear pooling fusion and attention based VQA methods. By integrating with them, our method could further boost the performance. Extensive experiments on public VQA datasets validate the effectiveness of QGHC.

cs.CV↗

arXiv2018

Production of open-charm mesons in relativistic heavy-ion collisions

We present a theoretical framework to study open charm production in relativistic heavy-ion collisions. The coupling strength between the charm quarks and the QGP constituents, quantified by the spatial diffusion coefficient $2πTD_{s}$, is obtained by performing a phenomenological fit analysis to the lattice QCD calculations, resulting in $2πTD_{s}=const.$ (\textbf{Model-A}) and $2πTD_{s}=1.3 + (T/T_{c})^2$ (\textbf{Model-B}). We find that the relative azimuthal distribution of the initially back-to-back generated $c\bar{c}$ pairs presents a broadening behaviour, which is more pronounced for $c\bar{c}$ pairs with small initial $p_{\rm T}$, and when the Model-B approach is adopted. The competition between the initial drag and the subsequent collective effects tends to restrict the time dependence of charm quark $R_{\rm AA}$. Concerning the theoretical uncertainty on final D-meson nuclear modification, the nuclear shadowing and pp baseline components are dominat at high and low $p_{\rm T}$ ($p_{\rm T}\lesssim3~{\rm GeV/{\it c}}$), respectively. The measured D-meson $R_{\rm AA}(p_{\rm T})$ favors Model-A assumption for the diffusion coefficient both at RHIC and LHC, while their $v_{2}(p_{\rm T})$ prefer Model-B at moderate $p_{\rm T}$. These results confirm the necessity to consider the temperature- and/or momentum-dependence of $2πTD_{s}$ to describe well the D-meson $R_{\rm AA}$ and $v_{\rm 2}$ simultaneously.

hep-ph↗

arXiv2018

Compressed Anomaly Detection with Multiple Mixed Observations

We consider a collection of independent random variables that are identically distributed, except for a small subset which follows a different, anomalous distribution. We study the problem of detecting which random variables in the collection are governed by the anomalous distribution. Recent work proposes to solve this problem by conducting hypothesis tests based on mixed observations (e.g. linear combinations) of the random variables. Recognizing the connection between taking mixed observations and compressed sensing, we view the problem as recovering the "support" (index set) of the anomalous random variables from multiple measurement vectors (MMVs). Many algorithms have been developed for recovering jointly sparse signals and their support from MMVs. We establish the theoretical and empirical effectiveness of these algorithms at detecting anomalies. We also extend the LASSO algorithm to an MMV version for our purpose. Further, we perform experiments on synthetic data, consisting of samples from the random variables, to explore the trade-off between the number of mixed observations per sample and the number of samples required to detect anomalies.

cs.IT↗

arXiv2018

Sparse Randomized Kaczmarz for Support Recovery of Jointly Sparse Corrupted Multiple Measurement Vectors

While single measurement vector (SMV) models have been widely studied in signal processing, there is a surging interest in addressing the multiple measurement vectors (MMV) problem. In the MMV setting, more than one measurement vector is available and the multiple signals to be recovered share some commonalities such as a common support. Applications in which MMV is a naturally occurring phenomenon include online streaming, medical imaging, and video recovery. This work presents a stochastic iterative algorithm for the support recovery of jointly sparse corrupted MMV. We present a variant of the Sparse Randomized Kaczmarz algorithm for corrupted MMV and compare our proposed method with an existing Kaczmarz type algorithm for MMV problems. We also showcase the usefulness of our approach in the online (streaming) setting and provide empirical evidence that suggests the robustness of the proposed method to the distribution of the corruption and the number of corruptions occurring.

eess.SP↗

arXiv2018

Diversity Regularized Spatiotemporal Attention for Video-based Person Re-identification

Video-based person re-identification matches video clips of people across non-overlapping cameras. Most existing methods tackle this problem by encoding each video frame in its entirety and computing an aggregate representation across all frames. In practice, people are often partially occluded, which can corrupt the extracted features. Instead, we propose a new spatiotemporal attention model that automatically discovers a diverse set of distinctive body parts. This allows useful information to be extracted from all frames without succumbing to occlusions and misalignments. The network learns multiple spatial attention models and employs a diversity regularization term to ensure multiple models do not discover the same body part. Features extracted from local image regions are organized by spatial attention model and are combined using temporal attention. As a result, the network learns latent representations of the face, torso and other body parts using the best available image patches from the entire video sequence. Extensive evaluations on three datasets show that our framework outperforms the state-of-the-art approaches by large margins on multiple metrics.

cs.CV↗

arXiv2017

Origins and dissociation of pyramidal dislocations in magnesium and its alloys

Alloying magnesium (Mg) with rare earth elements such as yttrium (Y) has been reported to activate the pyramidal slip systems and improve the plasticity of Mg at room temperature. However, the origins of such dislocations and their dissociation mechanisms remain poorly understood. Here, we systematically investigate these mechanisms using dispersion-inclusive density functional theory, in combination with molecular dynamics simulations. We find that dislocations form more readily on the pyramidal I plane than on the pyramidal II plane in Mg. The addition of Y atoms in Mg facilitates the dissociation of dislocations on pyramidal II, leading to the easier formation of the pyramidal II than pyramidal I in Mg-Y alloy. Importantly, in pyramidal II slip plane, a flat potential-energy surface (PES) exists around the position of stable stacking fault energy (SFE), which allows cooperative movement of atoms within the slip plane. Alloying Mg with Y atoms increases the range of the PES, and ultimately promotes different sliding pathways in the Mg-Y alloy. These findings are consistent with experimentally observed activation of the pyramidal II slip system in Mg-Y alloys, and provide important insight into the relationship between dislocation structure and macroscopic enhancement of plasticity.

cond-mat.mtrl-sci↗

arXiv2017

Atomic Norm Minimization for Modal Analysis from Random and Compressed Samples

Modal analysis is the process of estimating a system's modal parameters such as its natural frequencies and mode shapes. One application of modal analysis is in structural health monitoring (SHM), where a network of sensors may be used to collect vibration data from a physical structure such as a building or bridge. There is a growing interest in developing automated techniques for SHM based on data collected in a wireless sensor network. In order to conserve power and extend battery life, however, it is desirable to minimize the amount of data that must be collected and transmitted in such a sensor network. In this paper, we highlight the fact that modal analysis can be formulated as an atomic norm minimization (ANM) problem, which can be solved efficiently and in some cases recover perfectly a structure's mode shapes and frequencies. We survey a broad class of sampling and compression strategies that one might consider in a physical sensor network, and we provide bounds on the sample complexity of these compressive schemes in order to recover a structure's mode shapes and frequencies via ANM. A main contribution of our paper is to establish a bound on the sample complexity of modal analysis with random temporal compression, and in this scenario we prove that the samples per sensor can actually decrease as the number of sensors increases. We also extend an atomic norm denoising problem to the multiple measurement vector (MMV) setting in the case of uniform sampling.

cs.IT↗

arXiv2017

Quantum Clique Gossiping

This paper establishes a framework for the acceleration of quantum gossip algorithms by introducing local clique operations to networks of interconnected qubits. Cliques are local structures in complex networks being complete subgraphs. Based on cyclic permutations, clique gossiping leads to collective multi-party qubit interactions. This type of algorithm can be physically realized by a series of local environments using coherent methods. First of all, we show that at reduced states, these cliques have the same acceleration effects as their roles in accelerating classical gossip algorithms, which can even make possible finite-time convergence for suitable network structures. Next, for randomized selection of cliques where node updates enjoy a more self-organized and scalable sequencing, we show that the rate of convergence is precisely improved by $\mathcal{O}(k/n)$ at the reduced states, where $k$ is the size of the cliques and $n$ is the number of qubits in the network. The rate of convergence at the coherent states of the overall quantum network is proven to be decided by the spectrum of a mean-square error evolution matrix. Explicit calculation of such matrix is rather challenging, nonetheless, the effect of cliques on the coherent states' dynamics is illustrated via numerical examples. Interestingly, the use of larger quantum cliques does not necessarily increase the speed of the network density aggregation, suggesting quantum network dynamics is not entirely decided by its classical topology.

quant-ph↗

arXiv2017

Can Image Retrieval help Visual Saliency Detection?

We propose a novel image retrieval framework for visual saliency detection using information about salient objects contained within bounding box annotations for similar images. For each test image, we train a customized SVM from similar example images to predict the saliency values of its object proposals and generate an external saliency map (ES) by aggregating the regional scores. To overcome limitations caused by the size of the training dataset, we also propose an internal optimization module which computes an internal saliency map (IS) by measuring the low-level contrast information of the test image. The two maps, ES and IS, have complementary properties so we take a weighted combination to further improve the detection performance. Experimental results on several challenging datasets demonstrate that the proposed algorithm performs favorably against the state-of-the-art methods.

cs.CV↗

arXiv2017

Identity-Aware Textual-Visual Matching with Latent Co-attention

Textual-visual matching aims at measuring similarities between sentence descriptions and images. Most existing methods tackle this problem without effectively utilizing identity-level annotations. In this paper, we propose an identity-aware two-stage framework for the textual-visual matching problem. Our stage-1 CNN-LSTM network learns to embed cross-modal features with a novel Cross-Modal Cross-Entropy (CMCE) loss. The stage-1 network is able to efficiently screen easy incorrect matchings and also provide initial training point for the stage-2 training. The stage-2 CNN-LSTM network refines the matching results with a latent co-attention mechanism. The spatial attention relates each word with corresponding image regions while the latent semantic attention aligns different sentence structures to make the matching results more robust to sentence structure variations. Extensive experiments on three datasets with identity-level annotations show that our framework outperforms state-of-the-art approaches by large margins.

cs.CV↗

arXiv2017

Learning Feature Pyramids for Human Pose Estimation

Articulated human pose estimation is a fundamental yet challenging task in computer vision. The difficulty is particularly pronounced in scale variations of human body parts when camera view changes or severe foreshortening happens. Although pyramid methods are widely used to handle scale changes at inference time, learning feature pyramids in deep convolutional neural networks (DCNNs) is still not well explored. In this work, we design a Pyramid Residual Module (PRMs) to enhance the invariance in scales of DCNNs. Given input features, the PRMs learn convolutional filters on various scales of input features, which are obtained with different subsampling ratios in a multi-branch network. Moreover, we observe that it is inappropriate to adopt existing methods to initialize the weights of multi-branch networks, which achieve superior performance than plain networks in many tasks recently. Therefore, we provide theoretic derivation to extend the current weight initialization scheme to multi-branch network structures. We investigate our method on two standard benchmarks for human pose estimation. Our approach obtains state-of-the-art results on both benchmarks. Code is available at https://github.com/bearpaw/PyraNet.

cs.CV↗

arXiv2017

Fake News Mitigation via Point Process Based Intervention

We propose the first multistage intervention framework that tackles fake news in social networks by combining reinforcement learning with a point process network activity model. The spread of fake news and mitigation events within the network is modeled by a multivariate Hawkes process with additional exogenous control terms. By choosing a feature representation of states, defining mitigation actions and constructing reward functions to measure the effectiveness of mitigation activities, we map the problem of fake news mitigation into the reinforcement learning framework. We develop a policy iteration method unique to the multivariate networked point process, with the goal of optimizing the actions for maximal total reward under budget constraints. Our method shows promising performance in real-time intervention experiments on a Twitter network to mitigate a surrogate fake news campaign, and outperforms alternatives on synthetic datasets.

cs.LG↗

arXiv2017

Joint Detection and Identification Feature Learning for Person Search

Existing person re-identification benchmarks and methods mainly focus on matching cropped pedestrian images between queries and candidates. However, it is different from real-world scenarios where the annotations of pedestrian bounding boxes are unavailable and the target person needs to be searched from a gallery of whole scene images. To close the gap, we propose a new deep learning framework for person search. Instead of breaking it down into two separate tasks---pedestrian detection and person re-identification, we jointly handle both aspects in a single convolutional neural network. An Online Instance Matching (OIM) loss function is proposed to train the network effectively, which is scalable to datasets with numerous identities. To validate our approach, we collect and annotate a large-scale benchmark dataset for person search. It contains 18,184 images, 8,432 identities, and 96,143 pedestrian bounding boxes. Experiments show that our framework outperforms other separate approaches, and the proposed OIM loss function converges much faster and better than the conventional Softmax loss.

cs.CV↗

arXiv2017

Person Search with Natural Language Description

Searching persons in large-scale image databases with the query of natural language description has important applications in video surveillance. Existing methods mainly focused on searching persons with image-based or attribute-based queries, which have major limitations for a practical usage. In this paper, we study the problem of person search with natural language description. Given the textual description of a person, the algorithm of the person search is required to rank all the samples in the person database then retrieve the most relevant sample corresponding to the queried description. Since there is no person dataset or benchmark with textual description available, we collect a large-scale person description dataset with detailed natural language annotations and person samples from various sources, termed as CUHK Person Description Dataset (CUHK-PEDES). A wide range of possible models and baselines have been evaluated and compared on the person search benchmark. An Recurrent Neural Network with Gated Neural Attention mechanism (GNA-RNN) is proposed to establish the state-of-the art performance on person search.

cs.CV↗

arXiv2017

Multi-configuration Dirac-Hartree-Fock calculations of forbidden transitions within the 3d^k ground configurations of highly charged ions (Z=72-83)

Extensive self-consistent multi-configuration Dirac-Hartree-Fock (MCDHF) calculations are performed for the $3s^2 3p^6 3d^k$ ($k=1-9$) ground configurations of highly charged ions ($Z=72-83$). Complete and consistent data sets of \textbf{excitation energies}, wavelengths, line strengths, oscillator strengths, and magnetic dipole (M1) and electric quadrupole (E2) transition rates among all these levels are given. We have compared our results with the results available in the literature and the accuracy of the data is assessed. We predict new energy levels and transition probabilities where no other experimental or theoretical results are available, which will form the basis for future experimental work.

physics.atom-ph↗

arXiv2017

Low-field electron mobility of InSb nanowires: Numerical efforts to larger cross sections

Within the framework of Boltzmann equation, we present a $\mathbf{k\cdot p}$ theory based study for the low-field mobilities of InSb nanowires (InSb NWs) with relatively large cross sectional sizes (with diameters up to 51.8 nm). For such type of large size nanowires, the intersubband electron-phonon scattering is of crucial importance to affect the scattering rate and then the mobility. In our simulation, the lowest 15 electron subbands and 50 transverse modes of phonons are carefully accounted for. We find that, up to the 51.84 nm diameter, the mobility monotonously increases with the diameter, not yet showing any saturated behavior. We also find that, while the bulk InSb mobility is considerably higher than the bulk Si, the small size (e.g. $\sim 3$ nm diameter) nanowires from both materials have similar magnitude of mobilities. This implies, importantly, that the mobility of the InSb NWs would decrease faster than the SiNWs as we reduce the cross sectional size of the nanowires.

cond-mat.mes-hall↗

arXiv2016

Data-Driven Threshold Machine: Scan Statistics, Change-Point Detection, and Extreme Bandits

We present a novel distribution-free approach, the data-driven threshold machine (DTM), for a fundamental problem at the core of many learning tasks: choose a threshold for a given pre-specified level that bounds the tail probability of the maximum of a (possibly dependent but stationary) random sequence. We do not assume data distribution, but rather relying on the asymptotic distribution of extremal values, and reduce the problem to estimate three parameters of the extreme value distributions and the extremal index. We specially take care of data dependence via estimating extremal index since in many settings, such as scan statistics, change-point detection, and extreme bandits, where dependence in the sequence of statistics can be significant. Key features of our DTM also include robustness and the computational efficiency, and it only requires one sample path to form a reliable estimate of the threshold, in contrast to the Monte Carlo sampling approach which requires drawing a large number of sample paths. We demonstrate the good performance of DTM via numerical examples in various dependent settings.

cs.LG↗

arXiv2016

Detecting weak changes in dynamic events over networks

Large volume of networked streaming event data are becoming increasingly available in a wide variety of applications, such as social network analysis, Internet traffic monitoring and healthcare analytics. Streaming event data are discrete observation occurred in continuous time, and the precise time interval between two events carries a great deal of information about the dynamics of the underlying systems. How to promptly detect changes in these dynamic systems using these streaming event data? In this paper, we propose a novel change-point detection framework for multi-dimensional event data over networks. We cast the problem into sequential hypothesis test, and derive the likelihood ratios for point processes, which are computed efficiently via an EM-like algorithm that is parameter-free and can be computed in a distributed fashion. We derive a highly accurate theoretical characterization of the false-alarm-rate, and show that it can achieve weak signal detection by aggregating local statistics over time and networks. Finally, we demonstrate the good performance of our algorithm on numerical examples and real-world datasets from twitter and Memetracker.

cs.LG↗