arXiv subjects

Wei Wu

Publications and source records attributed to Wei Wu.

At least 397 records · Page 22Linked to original sources

arXiv2021

Digital Quantum Simulation of Hadronization in Yang-Mills Theory

A quantum algorithm of SU(N) Yang-Mills theory is formulated in terms of quantum circuits. It can nonperturbatively calculate the Dyson series and scattering amplitudes with polynomial complexity. The gauge fields in the interaction picture are discretized on the same footing with the lattice fermions in momentum space to avoid the fermion doubling and the gauge symmetry breaking problems. Applying the algorithm to the quantum simulation of quantum chromodynamics, the quark and gluon's wave functions evolved from the initial states by the interactions can be observed and the information from wave functions can be extracted at any discrete time. This may help us understand the natures of the hadronization which has been an outstanding question of significant implication on high energy phenomenological studies.

quant-ph↗

arXiv2021

Open Domain Dialogue Generation with Latent Images

We consider grounding open domain dialogues with images. Existing work assumes that both an image and a textual context are available, but image-grounded dialogues by nature are more difficult to obtain than textual dialogues. Thus, we propose learning a response generation model with both image-grounded dialogues and textual dialogues by assuming that the visual scene information at the time of a conversation can be represented by an image, and trying to recover the latent images of the textual dialogues through text-to-image generation techniques. The likelihood of the two types of dialogues is then formulated by a response generator and an image reconstructor that are learned within a conditional variational auto-encoding framework. Empirical studies are conducted in both image-grounded conversation and text-based conversation. In the first scenario, image-grounded dialogues, especially under a low-resource setting, can be effectively augmented by textual dialogues with latent images; while in the second scenario, latent images can enrich the content of responses and at the same time keep them relevant to contexts.

cs.CL↗

arXiv2021

A Novel Automatic Modulation Classification Scheme Based on Multi-Scale Networks

Automatic modulation classification enables intelligent communications and it is of crucial importance in today's and future wireless communication networks. Although many automatic modulation classification schemes have been proposed, they cannot tackle the intra-class diversity problem caused by the dynamic changes of the wireless communication environment. In order to overcome this problem, inspired by face recognition, a novel automatic modulation classification scheme is proposed by using the multi-scale network in this paper. Moreover, a novel loss function that combines the center loss and the cross entropy loss is exploited to learn both discriminative and separable features in order to further improve the classification performance. Extensive simulation results demonstrate that our proposed automatic modulation classification scheme can achieve better performance than the benchmark schemes in terms of the classification accuracy. The influence of the network parameters and the loss function with the two-stage training strategy on the classification accuracy of our proposed scheme are investigated.

eess.SP↗

arXiv2021

Two-dimensional Ferroelectric Ferromagnetic Half Semiconductor in VOF monolayer

Two-dimensional (2D) multiferroics have been casted great attention owing to their promising prospects for miniaturized electronic and memory devices.Here, we proposed a highly stable 2D multiferroic, VOF monolayer, which is an intrinsic ferromagnetic half semiconductor with large spin polarization ~2 $μ_{B}/V$ atom and a significant uniaxial magnetic anisotropy along a-axis (410 $μeV/V$ atom). Meanwhile, it shows excellent ferroelectricity with a large spontaneous polarization 32.7 $μC/cm^{2}$ and a moderate energy barrier (~43 meV/atom) between two ferroelectric states, which can be ascribed to the Jahn-Teller distortion.Moreover, VOF monolayer harbors an ultra-large negative Poisson's ratio in the in-plane direction (~-0.34). The Curie temperature evaluated from the Monte Carlo simulations based on the Ising model is about 215 K, which can be enhanced room temperature under -4% compressive biaxial strain.The combination of ferromagnetism and ferroelectricity in the VOF monolayer could provide a promising platform for future study of multiferroic effects and next-generation multifunctional nanoelectronic device applications.

cond-mat.mtrl-sci↗

arXiv2021

Hashing-Accelerated Graph Neural Networks for Link Prediction

Networks are ubiquitous in the real world. Link prediction, as one of the key problems for network-structured data, aims to predict whether there exists a link between two nodes. The traditional approaches are based on the explicit similarity computation between the compact node representation by embedding each node into a low-dimensional space. In order to efficiently handle the intensive similarity computation in link prediction, the hashing technique has been successfully used to produce the node representation in the Hamming space. However, the hashing-based link prediction algorithms face accuracy loss from the randomized hashing techniques or inefficiency from the learning to hash techniques in the embedding process. Currently, the Graph Neural Network (GNN) framework has been widely applied to the graph-related tasks in an end-to-end manner, but it commonly requires substantial computational resources and memory costs due to massive parameter learning, which makes the GNN-based algorithms impractical without the help of a powerful workhorse. In this paper, we propose a simple and effective model called #GNN, which balances the trade-off between accuracy and efficiency. #GNN is able to efficiently acquire node representation in the Hamming space for link prediction by exploiting the randomized hashing technique to implement message passing and capture high-order proximity in the GNN framework. Furthermore, we characterize the discriminative power of #GNN in probability. The extensive experimental results demonstrate that the proposed #GNN algorithm achieves accuracy comparable to the learning-based algorithms and outperforms the randomized algorithm, while running significantly faster than the learning-based algorithms. Also, the proposed algorithm shows excellent scalability on a large-scale network with the limited resources.

cs.LG↗

arXiv2021

ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation Transfer

Learning high-quality sentence representations benefits a wide range of natural language processing tasks. Though BERT-based pre-trained language models achieve high performance on many downstream tasks, the native derived sentence representations are proved to be collapsed and thus produce a poor performance on the semantic textual similarity (STS) tasks. In this paper, we present ConSERT, a Contrastive Framework for Self-Supervised Sentence Representation Transfer, that adopts contrastive learning to fine-tune BERT in an unsupervised and effective way. By making use of unlabeled texts, ConSERT solves the collapse issue of BERT-derived sentence representations and make them more applicable for downstream tasks. Experiments on STS datasets demonstrate that ConSERT achieves an 8\% relative improvement over the previous state-of-the-art, even comparable to the supervised SBERT-NLI. And when further incorporating NLI supervision, we achieve new state-of-the-art performance on STS tasks. Moreover, ConSERT obtains comparable results with only 1000 samples available, showing its robustness in data scarcity scenarios.

cs.CL↗

arXiv2021

A unified framework on defining depth for point process using function smoothing

The notion of statistical depth has been extensively studied in multivariate and functional data over the past few decades. In contrast, the depth on temporal point process is still under-explored. The problem is challenging because a point process has two types of randomness: 1) the number of events in a process, and 2) the distribution of these events. Recent studies proposed depths in a weighted product of two terms, describing the above two types of randomness, respectively. In this paper, we propose to unify these two randomnesses under one framework by a smoothing procedure. Basically, we transform the point process observations into functions using conventional kernel smoothing methods, and then adopt the well-known functional $h$-depth and its modified, center-based, version to describe the center-outward rank in the original data. To do so, we define a proper metric on the point processes with smoothed functions. We then propose an efficient algorithm to estimated the defined "center". We further explore the mathematical properties of the newly defined depths and study asymptotics. Simulation results show that the proposed depths can properly rank the point process observations. Finally, we demonstrate the new method in a classification task using a real neuronal spike train dataset.

stat.ME↗

arXiv2021

Threshold for a discrete-variable sensor of quantum reservoirs

Quantum sensing employs quantum resources of a sensor to attain a smaller estimation error of physical quantities than the limit constrained by classical physics. To measure a quantum reservoir, which is significant in decoherence control, a nonunitary-encoding sensing scheme becomes necessary. However, previous studies showed that the reservoir-induced degradation to quantum resources of the sensor makes the errors divergent with the increase of encoding time. We here propose a scheme to use $N$ two-level systems as the sensor to measure a quantum reservoir. A threshold, above which the shot-noise-limited sensing error saturates or even persistently decreases with the encoding time, is uncovered. Our analysis reveals that it is due to the formation of a bound state of the total sensor-reservoir system. Solving the outstanding error-divergency problem in previous studies, our result supplies an insightful guideline in realizing a sensitive measurement of quantum reservoirs.

quant-ph↗

arXiv2021

Zero-Resource Knowledge-Grounded Dialogue Generation

While neural conversation models have shown great potentials towards generating informative and engaging responses via introducing external knowledge, learning such a model often requires knowledge-grounded dialogues that are difficult to obtain. To overcome the data challenge and reduce the cost of building a knowledge-grounded dialogue system, we explore the problem under a zero-resource setting by assuming no context-knowledge-response triples are needed for training. To this end, we propose representing the knowledge that bridges a context and a response and the way that the knowledge is expressed as latent variables, and devise a variational approach that can effectively estimate a generation model from a dialogue corpus and a knowledge corpus that are independent with each other. Evaluation results on three benchmarks of knowledge-grounded dialogue generation indicate that our model can achieve comparable performance with state-of-the-art methods that rely on knowledge-grounded dialogues for training, and exhibits a good generalization ability over different topics and different datasets.

cs.CL↗

arXiv2021

ASAP: A Chinese Review Dataset Towards Aspect Category Sentiment Analysis and Rating Prediction

Sentiment analysis has attracted increasing attention in e-commerce. The sentiment polarities underlying user reviews are of great value for business intelligence. Aspect category sentiment analysis (ACSA) and review rating prediction (RP) are two essential tasks to detect the fine-to-coarse sentiment polarities. %Considering the sentiment of the aspects(ACSA) and the overall review rating(RP) simultaneously has the potential to improve the overall performance. ACSA and RP are highly correlated and usually employed jointly in real-world e-commerce scenarios. While most public datasets are constructed for ACSA and RP separately, which may limit the further exploitation of both tasks. To address the problem and advance related researches, we present a large-scale Chinese restaurant review dataset \textbf{ASAP} including $46,730$ genuine reviews from a leading online-to-offline (O2O) e-commerce platform in China. Besides a $5$-star scale rating, each review is manually annotated according to its sentiment polarities towards $18$ pre-defined aspect categories. We hope the release of the dataset could shed some light on the fields of sentiment analysis. Moreover, we propose an intuitive yet effective joint model for ACSA and RP. Experimental results demonstrate that the joint model outperforms state-of-the-art baselines on both tasks.

cs.CL↗

arXiv2021

Incorporating Convolution Designs into Visual Transformers

Motivated by the success of Transformers in natural language processing (NLP) tasks, there emerge some attempts (e.g., ViT and DeiT) to apply Transformers to the vision domain. However, pure Transformer architectures often require a large amount of training data or extra supervision to obtain comparable performance with convolutional neural networks (CNNs). To overcome these limitations, we analyze the potential drawbacks when directly borrowing Transformer architectures from NLP. Then we propose a new \textbf{Convolution-enhanced image Transformer (CeiT)} which combines the advantages of CNNs in extracting low-level features, strengthening locality, and the advantages of Transformers in establishing long-range dependencies. Three modifications are made to the original Transformer: \textbf{1)} instead of the straightforward tokenization from raw input images, we design an \textbf{Image-to-Tokens (I2T)} module that extracts patches from generated low-level features; \textbf{2)} the feed-froward network in each encoder block is replaced with a \textbf{Locally-enhanced Feed-Forward (LeFF)} layer that promotes the correlation among neighboring tokens in the spatial dimension; \textbf{3)} a \textbf{Layer-wise Class token Attention (LCA)} is attached at the top of the Transformer that utilizes the multi-level representations. Experimental results on ImageNet and seven downstream tasks show the effectiveness and generalization ability of CeiT compared with previous Transformers and state-of-the-art CNNs, without requiring a large amount of training data and extra CNN teachers. Besides, CeiT models also demonstrate better convergence with $3\times$ fewer training iterations, which can reduce the training cost significantly\footnote{Code and models will be released upon acceptance.}.

cs.CV↗

arXiv2021

General Analytical Method of Kibble-Zurek Mechanism for Exact Prediction of Topological Defects Production

In the field of non-equilibrium phase transitions, the Kibble-Zurek mechanism (KZM) is undoubtedly an important discovery, pointing out that some universal scaling rules are applied to a wide range of physical systems from quantum to the cosmos in complex non-equilibrium continuous phase transitions. However, except for some scaling relations in specific cases, the algebraic-based KZM can not provide further details on the topological defect generation laws. In this work, we propose an analytical-based KZM that can accurately predict topological defect generation for a given quenching condition. Compared with the conventional KZM, our theory is more accurate and more widely applicable, especially in non-linear quenching conditions and inhomogeneous structural systems, where it has more obvious advantages. Our work reveals a fundamental and intrinsic mechanism in non-equilibrium phase transitions, blazing a new trail for accurate description and manipulation of topological defect generation.

quant-ph↗

arXiv2021

Spatial-Temporal Correlation and Topology Learning for Person Re-Identification in Videos

Video-based person re-identification aims to match pedestrians from video sequences across non-overlapping camera views. The key factor for video person re-identification is to effectively exploit both spatial and temporal clues from video sequences. In this work, we propose a novel Spatial-Temporal Correlation and Topology Learning framework (CTL) to pursue discriminative and robust representation by modeling cross-scale spatial-temporal correlation. Specifically, CTL utilizes a CNN backbone and a key-points estimator to extract semantic local features from human body at multiple granularities as graph nodes. It explores a context-reinforced topology to construct multi-scale graphs by considering both global contextual information and physical connections of human body. Moreover, a 3D graph convolution and a cross-scale graph convolution are designed, which facilitate direct cross-spacetime and cross-scale information propagation for capturing hierarchical spatial-temporal dependencies and structural information. By jointly performing the two convolutions, CTL effectively mines comprehensive clues that are complementary with appearance information to enhance representational capacity. Extensive experiments on two video benchmarks have demonstrated the effectiveness of the proposed method and the state-of-the-art performance.

cs.CV↗

arXiv2021

Geometrical and topological properties of transmission resonance and artificial mirage

Transmission eigenfunctions are certain interior resonant modes that are of central importance to the wave scattering theory. In this paper, we present the discovery of novel global rigidity properties of the transmission eigenfunctions associated with the Maxwell system. It is shown that the transmission eigenfunctions carry the geometrical and topological information of the underlying domain. We present both analytical and numerical results of these intriguing rigidity properties. As an interesting application, we propose an illusion scheme of artificially generating a mirage image of any given optical object.

physics.optics↗

arXiv2021

Active plasmon interference control on ultrafast time scales by free electrons

Interference between light waves is one of the widely known phenomena in physics, which is widely used in modern optics, ranging from precise detection at the nanoscale to gravitational-wave observation. Akin to light, both classical and quantum interferences between surface plasmon polaritons (SPPs) have been demonstrated. However, to actively control the SPP interference within subcycle in time (usually less than several femtoseconds in the visible range) is still missing, which hinders the ultimate manipulation of SPP interference on ultrafast time scale. In this paper, the interference between SPPs launched by a hole dimer, which was excited by a grazing incident free electron beam without direct contact, was manipulated through both propagation and initial phase difference control. Particularly, using cathodoluminescence spectroscopy, the appearance of higher-order interference orders was obtained through propagation phase control by increasing separation distances of the dimer. Meanwhile, the peak-valley-peak evolution at a certain wavelength through changing the accelerating voltages was observed, which originates from the initial phase difference control of hole launched SPPs. In particular, the time resolution of this kind of control is shown to be in the ultrafast attosecond (as) region. Our work suggests that fast electron beams can be an efficient tool to control polarition interference in subcycle temporal scale, which can be potentially used in ultrafast optical processing or sensing.

physics.optics↗

arXiv2021

Temporal Context Aggregation Network for Temporal Action Proposal Refinement

Temporal action proposal generation aims to estimate temporal intervals of actions in untrimmed videos, which is a challenging yet important task in the video understanding field. The proposals generated by current methods still suffer from inaccurate temporal boundaries and inferior confidence used for retrieval owing to the lack of efficient temporal modeling and effective boundary context utilization. In this paper, we propose Temporal Context Aggregation Network (TCANet) to generate high-quality action proposals through "local and global" temporal context aggregation and complementary as well as progressive boundary refinement. Specifically, we first design a Local-Global Temporal Encoder (LGTE), which adopts the channel grouping strategy to efficiently encode both "local and global" temporal inter-dependencies. Furthermore, both the boundary and internal context of proposals are adopted for frame-level and segment-level boundary regressions, respectively. Temporal Boundary Regressor (TBR) is designed to combine these two regression granularities in an end-to-end fashion, which achieves the precise boundaries and reliable confidence of proposals through progressive refinement. Extensive experiments are conducted on three challenging datasets: HACS, ActivityNet-v1.3, and THUMOS-14, where TCANet can generate proposals with high precision and recall. By combining with the existing action classifier, TCANet can obtain remarkable temporal action detection performance compared with other methods. Not surprisingly, the proposed TCANet won the 1$^{st}$ place in the CVPR 2020 - HACS challenge leaderboard on temporal action localization task.

cs.CV↗

arXiv2021

Higher Performance Visual Tracking with Dual-Modal Localization

Visual Object Tracking (VOT) has synchronous needs for both robustness and accuracy. While most existing works fail to operate simultaneously on both, we investigate in this work the problem of conflicting performance between accuracy and robustness. We first conduct a systematic comparison among existing methods and analyze their restrictions in terms of accuracy and robustness. Specifically, 4 formulations-offline classification (OFC), offline regression (OFR), online classification (ONC), and online regression (ONR)-are considered, categorized by the existence of online update and the types of supervision signal. To account for the problem, we resort to the idea of ensemble and propose a dual-modal framework for target localization, consisting of robust localization suppressing distractors via ONR and the accurate localization attending to the target center precisely via OFC. To yield a final representation (i.e, bounding box), we propose a simple but effective score voting strategy to involve adjacent predictions such that the final representation does not commit to a single location. Operating beyond the real-time demand, our proposed method is further validated on 8 datasets-VOT2018, VOT2019, OTB2015, NFS, UAV123, LaSOT, TrackingNet, and GOT-10k, achieving state-of-the-art performance.

cs.CV↗

arXiv2021

Real-Time Visual Object Tracking via Few-Shot Learning

Visual Object Tracking (VOT) can be seen as an extended task of Few-Shot Learning (FSL). While the concept of FSL is not new in tracking and has been previously applied by prior works, most of them are tailored to fit specific types of FSL algorithms and may sacrifice running speed. In this work, we propose a generalized two-stage framework that is capable of employing a large variety of FSL algorithms while presenting faster adaptation speed. The first stage uses a Siamese Regional Proposal Network to efficiently propose the potential candidates and the second stage reformulates the task of classifying these candidates to a few-shot classification problem. Following such a coarse-to-fine pipeline, the first stage proposes informative sparse samples for the second stage, where a large variety of FSL algorithms can be conducted more conveniently and efficiently. As substantiation of the second stage, we systematically investigate several forms of optimization-based few-shot learners from previous works with different objective functions, optimization methods, or solution space. Beyond that, our framework also entails a direct application of the majority of other FSL algorithms to visual tracking, enabling mutual communication between researchers on these two topics. Extensive experiments on the major benchmarks, VOT2018, OTB2015, NFS, UAV123, TrackingNet, and GOT-10k are conducted, demonstrating a desirable performance gain and a real-time speed.

cs.CV↗