arXiv subjects

Yang Wang

Publications and source records attributed to Yang Wang.

At least 739 records · Page 41Linked to original sources

arXiv2019

Future Frame Prediction Using Convolutional VRNN for Anomaly Detection

Anomaly detection in videos aims at reporting anything that does not conform the normal behaviour or distribution. However, due to the sparsity of abnormal video clips in real life, collecting annotated data for supervised learning is exceptionally cumbersome. Inspired by the practicability of generative models for semi-supervised learning, we propose a novel sequential generative model based on variational autoencoder (VAE) for future frame prediction with convolutional LSTM (ConvLSTM). To the best of our knowledge, this is the first work that considers temporal information in future frame prediction based anomaly detection framework from the model perspective. Our experiments demonstrate that our approach is superior to the state-of-the-art methods on three benchmark datasets.

cs.CV↗

arXiv2019

Alternative Analysis Methods for Time to Event Endpoints under Non-proportional Hazards: A Comparative Analysis

The log-rank test is most powerful under proportional hazards (PH). In practice, non-PH patterns are often observed in clinical trials, such as in immuno-oncology; therefore, alternative methods are needed to restore the efficiency of statistical testing. Three categories of testing methods were evaluated, including weighted log-rank tests, Kaplan-Meier curve-based tests (including weighted Kaplan-Meier and Restricted Mean Survival Time, RMST), and combination tests (including Breslow test, Lee's combo test, and MaxCombo test). Nine scenarios representing the PH and various non-PH patterns were simulated. The power, type I error, and effect estimates of each method were compared. In general, all tests control type I error well. There is not a single most powerful test across all scenarios. In the absence of prior knowledge regarding the PH or non-PH patterns, the MaxCombo test is relatively robust across patterns. Since the treatment effect changes overtime under non-PH, the overall profile of the treatment effect may not be represented comprehensively based on a single measure. Thus, multiple measures of the treatment effect should be pre-specified as sensitivity analyses to evaluate the totality of the data.

stat.AP↗

arXiv2019

Almost everywhere injectivity conditions for the matrix recovery problem

Matrix recovery is raised in many areas. In this paper, we build up a framework for almost everywhere matrix recovery which means to recover almost all the $P\in {\mathcal M}\subset {\mathbb H}^{p\times q}$ from $Tr(A_jP), j=1,\ldots,N$ where $A_j\in V_j\subset {\mathbb H}^{p\times q}$. We mainly focus on the following question: how many measurements are needed to recover almost all the matrices in ${\mathcal M}$? For the case where both ${\mathcal M}$ and $V_j$ are algebraic varieties, we use the tools from algebraic geometry to study the question and present some results to address it under many different settings.

cs.IT↗

arXiv2019

Almost Everywhere Generalized Phase Retrieval

The aim of generalized phase retrieval is to recover $\mathbf{x}\in \mathbb{F}^d$ from the quadratic measurements $\mathbf{x}^*A_1\mathbf{x},\ldots,\mathbf{x}^*A_N\mathbf{x}$, where $A_j\in \mathbf{H}_d(\mathbb{F})$ and $\mathbb{F}=\mathbb{R}$ or $\mathbb{C}$. In this paper, we study the matrix set $\mathcal{A}=(A_j)_{j=1}^N$ which has the almost everywhere phase retrieval property. For the case $\mathbb{F}=\mathbb{R}$, we show that $N\geq d+1$ generic matrices with prescribed ranks have almost everywhere phase retrieval property. We also extend this result to the case where $A_1,\ldots,A_N$ are orthogonal matrices and hence establish the almost everywhere phase retrieval property for the fusion frame phase retrieval. For the case where $\mathbb{F}=\mathbb{C}$, we obtain similar results under the assumption of $N\geq 2d$. We lower the measurement number $d+1$ (resp. $2d$) with showing that there exist $N=d$ (resp. $2d-1$) matrices $A_1,\ldots, A_N\in \mathbf{H}_d(\mathbb{R})$ (resp. $\mathbf{H}_d(\mathbb{C})$) which have the almost everywhere phase retrieval property. Our results are an extension of almost everywhere phase retrieval from the standard phase retrieval to the general setting and the proofs are often based on some new ideas about determinant variety.

math.FA↗

arXiv2019

Few-Shot Deep Adversarial Learning for Video-based Person Re-identification

Video-based person re-identification (re-ID) refers to matching people across camera views from arbitrary unaligned video footages. Existing methods rely on supervision signals to optimise a projected space under which the distances between inter/intra-videos are maximised/minimised. However, this demands exhaustively labelling people across camera views, rendering them unable to be scaled in large networked cameras. Also, it is noticed that learning effective video representations with view invariance is not explicitly addressed for which features exhibit different distributions otherwise. Thus, matching videos for person re-ID demands flexible models to capture the dynamics in time-series observations and learn view-invariant representations with access to limited labeled training samples. In this paper, we propose a novel few-shot deep learning approach to video-based person re-ID, to learn comparable representations that are discriminative and view-invariant. The proposed method is developed on the variational recurrent neural networks (VRNNs) and trained adversarially to produce latent variables with temporal dependencies that are highly discriminative yet view-invariant in matching persons. Through extensive experiments conducted on three benchmark datasets, we empirically show the capability of our method in creating view-invariant temporal features and state-of-the-art performance achieved by our method.

cs.CV↗

arXiv2019

Nb$_{2}$SiTe$_{4}$: A Stable Narrow-Gap Two-Dimensional Material with Ambipolar Transport and Mid-Infrared Response

Two-dimensional (2D) materials with narrow band gaps (~0.3 eV) are of great importance for realizing ambipolar transistors and mid-infrared (MIR) detection. However, most of the 2D materials studied so far have band gaps that are too large. A few of them with suitable band gaps are not stable under ambient conditions. In this study, the layered Nb$_{2}$SiTe$_{4}$ is shown to be a stable 2D material with a band gap of 0.39 eV. Field-effect transistors based on few-layer Nb$_2$SiTe$_4$ show ambipolar transport with similar magnitude of electron and hole current and high charge-carrier mobility of ~ 100 cm$^{2}$V$^{-1}$s$^{-1}$ at room temperature. Optoelectronic measurements of the devices show clear response to MIR wavelength of 3.1 $\mathrmμ$m with a high responsivity of ~ 0.66 AW$^{-1}$. These results establish Nb$_{2}$SiTe$_{4}$ as a good candidate for ambipolar devices and MIR detection.

physics.app-ph↗

arXiv2019

Correlation-based Initialization Algorithm for Tensor-based HSI Compression Methods

Tensor decomposition (TD) is widely used in hyperspectral image (HSI) compression. The initialization of factor matrix in tensor decomposition can determine the HSI compression performance. It is worth noting that HSI is highly correlated in bands. However, this phenomenon is ignored by the previous TD method. Aiming at improving the HSI compression performance, we propose a method called correlation-based TD initialization algorithm. As HSI is well approximated by means of a reference band. In accordance with the SVD result of the reference band, the initialized factor matrices of TD are produced. We compare our methods with random and SVD-based initialization methods. The experimental results reveal that our correlation-based TD initialization method is capable of significantly reducing the computational cost of TD while keeping the initialization quality and compression performance.

eess.IV↗

arXiv2019

A Convolutional Neural Network with Mapping Layers for Hyperspectral Image Classification

In this paper, we propose a convolutional neural network with mapping layers (MCNN) for hyperspectral image (HSI) classification. The proposed mapping layers map the input patch into a low dimensional subspace by multilinear algebra. We use our mapping layers to reduce the spectral and spatial redundancy and maintain most energy of the input. The feature extracted by our mapping layers can also reduce the number of following convolutional layers for feature extraction. Our MCNN architecture avoids the declining accuracy with increasing layers phenomenon of deep learning models for HSI classification and also saves the training time for its effective mapping layers. Furthermore, we impose the 3-D convolutional kernel on convolutional layer to extract the spectral-spatial features for HSI. We tested our MCNN on three datasets of Indian Pines, University of Pavia and Salinas, and we achieved the classification accuracy of 98.3%, 99.5% and 99.3%, respectively. Experimental results demonstrate that the proposed MCNN can significantly improve the classification accuracy and save much time consumption.

eess.IV↗

arXiv2019

Adaptive Structure-constrained Robust Latent Low-Rank Coding for Image Recovery

In this paper, we propose a robust representation learning model called Adaptive Structure-constrained Low-Rank Coding (AS-LRC) for the latent representation of data. To recover the underlying subspaces more accurately, AS-LRC seamlessly integrates an adaptive weighting based block-diagonal structure-constrained low-rank representation and the group sparse salient feature extraction into a unified framework. Specifically, AS-LRC performs the latent decomposition of given data into a low-rank reconstruction by a block-diagonal codes matrix, a group sparse locality-adaptive salient feature part and a sparse error part. To enforce the block-diagonal structures adaptive to different real datasets for the low-rank recovery, AS-LRC clearly computes an auto-weighting matrix based on the locality-adaptive features and multiplies by the low-rank coefficients for direct minimization at the same time. This encourages the codes to be block-diagonal and can avoid the tricky issue of choosing optimal neighborhood size or kernel width for the weight assignment, suffered in most local geometrical structures-preserving low-rank coding methods. In addition, our AS-LRC selects the L2,1-norm on the projection for extracting group sparse features rather than learning low-rank features by Nuclear-norm regularization, which can make learnt features robust to noise and outliers in samples, and can also make the feature coding process efficient. Extensive visualizations and numerical results demonstrate the effectiveness of our AS-LRC for image representation and recovery.

cs.CV↗

arXiv2019

Multi-Task Deep Learning with Dynamic Programming for Embryo Early Development Stage Classification from Time-Lapse Videos

Time-lapse is a technology used to record the development of embryos during in-vitro fertilization (IVF). Accurate classification of embryo early development stages can provide embryologists valuable information for assessing the embryo quality, and hence is critical to the success of IVF. This paper proposes a multi-task deep learning with dynamic programming (MTDL-DP) approach for this purpose. It first uses MTDL to pre-classify each frame in the time-lapse video to an embryo development stage, and then DP to optimize the stage sequence so that the stage number is monotonically non-decreasing, which usually holds in practice. Different MTDL frameworks, e.g., one-to-many, many-to-one, and many-to-many, are investigated. It is shown that the one-to-many MTDL framework achieved the best compromise between performance and computational cost. To our knowledge, this is the first study that applies MTDL to embryo early development stage classification from time-lapse videos.

eess.IV↗

arXiv2019

Learning Structured Twin-Incoherent Twin-Projective Latent Dictionary Pairs for Classification

In this paper, we extend the popular dictionary pair learning (DPL) into the scenario of twin-projective latent flexible DPL under a structured twin-incoherence. Technically, a novel framework called Twin-Projective Latent Flexible DPL (TP-DPL) is proposed, which minimizes the twin-incoherence constrained flexibly-relaxed reconstruction error to avoid the possible over-fitting issue and produce accurate reconstruction. In this setting, our TP-DPL integrates the twin-incoherence based latent flexible DPL and the joint embedding of codes as well as salient features by twin-projection into a unified model in an adaptive neighborhood-preserving manner. As a result, TP-DPL unifies the salient feature extraction, representation and classification. The twin-incoherence constraint on codes and features can explicitly ensure high intra-class compactness and inter-class separation over them. TP-DPL also integrates the adaptive weighting to preserve the local neighborhood of the coefficients and salient features within each class explicitly. For efficiency, TP-DPL uses Frobenius-norm and abandons the costly l0/l1-norm for group sparse representation. Another byproduct is that TP-DPL can directly apply the class-specific twin-projective reconstruction residual to compute the label of data. Extensive results on public databases show that TP-DPL can deliver the state-of-the-art performance.

cs.CV↗

arXiv2019

Exact quantum search based on analytical multiphase matching for known number of target items and the experimental demonstration on IBM Q

In [Phys. Rev. Lett. 113, 210501 (2014)], to achieve the optimal fixed-point quantum search in the case of unknown fraction (denoted by $λ$) of target items, the analytical multiphase matching (AMPM) condition has been proposed. In this paper, we find out that the AMPM condition can also be used to design the exact quantum search algorithm in the case of known $λ$, and the minimum number of iterations reaches the optimal level of existing exact algorithms. Experiments are performed to demonstrate the proposed algorithm on IBM's quantum computer. In addition, we theoretically find two coincidental phases with equal absolute value in our algorithm based on the AMPM condition and that algorithm based on single-phase matching. Our work confirms the practicability of the AMPM condition in the case of known $λ$, and is helpful to understand the mechanism of this condition.

quant-ph↗

arXiv2019

Quantum Error Correction with the GKP Code and Concatenation with Stabilizer Codes

Gottesman, Kitaev and Preskill have proposed a scheme to encode a qubit in a harmonic oscillator, which is called the GKP code. It is designed to be resistant to small shift errors contained in momentum and position quadratures. Thus there's some intrinsic fault tolerance of the GKP code. In this thesis,we propose a method to utilize all the information contained in the continuous shifts, not just simply map a GKP-encoded qubit to a normal qubit. This method enables us to do maximum-likelihood decisions and thus increase fault-tolerance of the GKP code. This thesis shows that the continuous nature of the GKP code is quite useful for quantum error correction.

quant-ph↗

arXiv2019

Alignment between Satellite and Central Galaxies in the EAGLE Simulation: Dependence on the Large-Scale Environments

The alignment between satellite and central galaxies serves as a proxy for addressing the issue of galaxy formation and evolution and has been investigated abundantly in observations and theoretical works. Most scenarios indicate that the satellites preferentially locate along the major axis of their central galaxy. Recent work shows that the strength of alignment signals depends on large-scale environment in observations. We use the publicly-released data from EAGLE to figure out whether the same effect can be found in the hydrodynamic simulation. We found much stronger environmental dependency of alignment signal in simulation. And we also explore change of alignments to address the formation of this effects.

astro-ph.GA↗

arXiv2019

Chemical complexity in high entropy alloys: A pair-interaction perspective

The recently proposed pair-interaction model is applied to study a series of refractory high entropy alloys. The results demonstrate the simplicity, robustness, and high accuracy of this model in predicting the configuration energies of NbMoTaW, NbMoTaWV and NbMoTaWTi. The element-element pair interaction parameters obtained from the linear regression of first-principle data provide a new perspective to understand the strengthening mechanism in HEAs, as revealed by comparing the effects of adding vanadium and titanium. Using the pair-interaction model, an expression for the intrinsic energy fluctuation is derived, which provides guidance on both theoretical modeling and first principles calculation.

cond-mat.mtrl-sci↗

arXiv2019

Cross-Entropy Adversarial View Adaptation for Person Re-identification

Person re-identification (re-ID) is a task of matching pedestrians under disjoint camera views. To recognise paired snapshots, it has to cope with large cross-view variations caused by the camera view shift. Supervised deep neural networks are effective in producing a set of non-linear projections that can transform cross-view images into a common feature space. However, they typically impose a symmetric architecture, yielding the network ill-conditioned on its optimisation. In this paper, we learn view-invariant subspace for person re-ID, and its corresponding similarity metric using an adversarial view adaptation approach. The main contribution is to learn coupled asymmetric mappings regarding view characteristics which are adversarially trained to address the view discrepancy by optimising the cross-entropy view confusion objective. To determine the similarity value, the network is empowered with a similarity discriminator to promote features that are highly discriminant in distinguishing positive and negative pairs. The other contribution includes an adaptive weighing on the most difficult samples to address the imbalance of within/between-identity pairs. Our approach achieves notable improved performance in comparison to state-of-the-arts on benchmark datasets.

cs.CV↗

arXiv2019

Every Pixel Counts ++: Joint Learning of Geometry and Motion with 3D Holistic Understanding

Learning to estimate 3D geometry in a single frame and optical flow from consecutive frames by watching unlabeled videos via deep convolutional network has made significant progress recently. Current state-of-the-art (SoTA) methods treat the two tasks independently. One typical assumption of the existing depth estimation methods is that the scenes contain no independent moving objects. while object moving could be easily modeled using optical flow. In this paper, we propose to address the two tasks as a whole, i.e. to jointly understand per-pixel 3D geometry and motion. This eliminates the need of static scene assumption and enforces the inherent geometrical consistency during the learning process, yielding significantly improved results for both tasks. We call our method as "Every Pixel Counts++" or "EPC++". Specifically, during training, given two consecutive frames from a video, we adopt three parallel networks to predict the camera motion (MotionNet), dense depth map (DepthNet), and per-pixel optical flow between two frames (OptFlowNet) respectively. The three types of information are fed into a holistic 3D motion parser (HMP), and per-pixel 3D motion of both rigid background and moving objects are disentangled and recovered. Comprehensive experiments were conducted on datasets with different scenes, including driving scenario (KITTI 2012 and KITTI 2015 datasets), mixed outdoor/indoor scenes (Make3D) and synthetic animation (MPI Sintel dataset). Performance on the five tasks of depth estimation, optical flow estimation, odometry, moving object segmentation and scene flow estimation shows that our approach outperforms other SoTA methods. Code will be available at: https://github.com/chenxuluo/EPC.

cs.CV↗

arXiv2019

A Targeted Acceleration and Compression Framework for Low bit Neural Networks

1 bit deep neural networks (DNNs), of which both the activations and weights are binarized , are attracting more and more attention due to their high computational efficiency and low memory requirement . However, the drawback of large accuracy dropping also restrict s its application. In this paper, we propose a novel Targeted Acceleration and Compression (TAC) framework to improve the performance of 1 bit deep neural networks W e consider that the acceleration and compression effects of binarizing fully connected layer s are not sufficient to compensate for the accuracy loss caused by it In the proposed framework, t he convolutional and fully connected layer are separated and optimized i ndividually . F or the convolutional layer s , both the activations and weights are binarized. For the fully connected layer s, the binarization operation is re placed by network pruning and low bit quantization. The proposed framework is implemented on the CIFAR 10, CIFAR 100 and ImageNet ( ILSVRC 12 ) datasets , and experimental results show that the proposed TAC can significantly improve the accuracy of 1 bit deep neural networks and outperforms the state of the art by more than 6 percentage points .

cs.CV↗