arXiv subjects

Xiao Liu

Publications and source records attributed to Xiao Liu.

At least 487 records · Page 27Linked to original sources

arXiv2019

Strict experimental test of macroscopic realism in a light-matter-interfaced system

Macroscopic realism is a classical worldview that a macroscopic system is always determinately in one of the two or more macroscopically distinguishable states available to it, and so is never in a superposition of these states. The question of whether there is a fundamental limitation on the possibility to observe quantum phenomena at the macroscopic scale remains unclear. Here we implement a strict and simple protocol to test macroscopic realism in a light-matter interfaced system. We create a micro-macro entanglement with two macroscopically distinguishable solid-state components and rule out those theories which would deny coherent superpositions of up to 76 atomic excitations shared by 10^10 ions in two separated solids. These results provide a general method to enhance the size of superposition states of atoms by utilizing quantum memory techniques and to push the envelope of macroscopicity at higher levels.

quant-ph↗

arXiv2019

TruNet: Short Videos Generation from Long Videos via Story-Preserving Truncation

In this work, we introduce a new problem, named as {\em story-preserving long video truncation}, that requires an algorithm to automatically truncate a long-duration video into multiple short and attractive sub-videos with each one containing an unbroken story. This differs from traditional video highlight detection or video summarization problems in that each sub-video is required to maintain a coherent and integral story, which is becoming particularly important for resource-production video sharing platforms such as Youtube, Facebook, TikTok, Kwai, etc. To address the problem, we collect and annotate a new large video truncation dataset, named as TruNet, which contains 1470 videos with on average 11 short stories per video. With the new dataset, we further develop and train a neural architecture for video truncation that consists of two components: a Boundary Aware Network (BAN) and a Fast-Forward Long Short-Term Memory (FF-LSTM). We first use the BAN to generate high quality temporal proposals by jointly considering frame-level attractiveness and boundaryness. We then apply the FF-LSTM, which tends to capture high-order dependencies among a sequence of frames, to decide whether a temporal proposal is a coherent and integral story. We show that our proposed framework outperforms existing approaches for the story-preserving long video truncation problem in both quantitative measures and user-study. The dataset is available for public academic research usage at https://ai.baidu.com/broad/download.

cs.CV↗

arXiv2019

Jointly Learning Entity and Relation Representations for Entity Alignment

Entity alignment is a viable means for integrating heterogeneous knowledge among different knowledge graphs (KGs). Recent developments in the field often take an embedding-based approach to model the structural information of KGs so that entity alignment can be easily performed in the embedding space. However, most existing works do not explicitly utilize useful relation representations to assist in entity alignment, which, as we will show in the paper, is a simple yet effective way for improving entity alignment. This paper presents a novel joint learning framework for entity alignment. At the core of our approach is a Graph Convolutional Network (GCN) based framework for learning both entity and relation representations. Rather than relying on pre-aligned relation seeds to learn relation representations, we first approximate them using entity embeddings learned by the GCN. We then incorporate the relation approximation into entities to iteratively learn better representations for both. Experiments performed on three real-world cross-lingual datasets show that our approach substantially outperforms state-of-the-art entity alignment methods.

cs.CL↗

arXiv2019

Image Inpainting with Learnable Bidirectional Attention Maps

Most convolutional network (CNN)-based inpainting methods adopt standard convolution to indistinguishably treat valid pixels and holes, making them limited in handling irregular holes and more likely to generate inpainting results with color discrepancy and blurriness. Partial convolution has been suggested to address this issue, but it adopts handcrafted feature re-normalization, and only considers forward mask-updating. In this paper, we present a learnable attention map module for learning feature renormalization and mask-updating in an end-to-end manner, which is effective in adapting to irregular holes and propagation of convolution layers. Furthermore, learnable reverse attention maps are introduced to allow the decoder of U-Net to concentrate on filling in irregular holes instead of reconstructing both holes and known regions, resulting in our learnable bidirectional attention maps. Qualitative and quantitative experiments show that our method performs favorably against state-of-the-arts in generating sharper, more coherent and visually plausible inpainting results. The source code and pre-trained models will be available.

cs.CV↗

arXiv2019

Deep Concept-wise Temporal Convolutional Networks for Action Localization

Existing action localization approaches adopt shallow temporal convolutional networks (\ie, TCN) on 1D feature map extracted from video frames. In this paper, we empirically find that stacking more conventional temporal convolution layers actually deteriorates action classification performance, possibly ascribing to that all channels of 1D feature map, which generally are highly abstract and can be regarded as latent concepts, are excessively recombined in temporal convolution. To address this issue, we introduce a novel concept-wise temporal convolution (CTC) layer as an alternative to conventional temporal convolution layer for training deeper action localization networks. Instead of recombining latent concepts, CTC layer deploys a number of temporal filters to each concept separately with shared filter parameters across concepts. Thus can capture common temporal patterns of different concepts and significantly enrich representation ability. Via stacking CTC layers, we proposed a deep concept-wise temporal convolutional network (C-TCN), which boosts the state-of-the-art action localization performance on THUMOS'14 from 42.8 to 52.1 in terms of mAP(\%), achieving a relative improvement of 21.7\%. Favorable result is also obtained on ActivityNet.

cs.CV↗

arXiv2019

Relation-Aware Entity Alignment for Heterogeneous Knowledge Graphs

Entity alignment is the task of linking entities with the same real-world identity from different knowledge graphs (KGs), which has been recently dominated by embedding-based methods. Such approaches work by learning KG representations so that entity alignment can be performed by measuring the similarities between entity embeddings. While promising, prior works in the field often fail to properly capture complex relation information that commonly exists in multi-relational KGs, leaving much room for improvement. In this paper, we propose a novel Relation-aware Dual-Graph Convolutional Network (RDGCN) to incorporate relation information via attentive interactions between the knowledge graph and its dual relation counterpart, and further capture neighboring structures to learn better entity representations. Experiments on three real-world cross-lingual datasets show that our approach delivers better and more robust results over the state-of-the-art alignment methods by learning better KG representations.

cs.CL↗

arXiv2019

Basic Performance Measurements of the Intel Optane DC Persistent Memory Module

Scalable nonvolatile memory DIMMs will finally be commercially available with the release of the Intel Optane DC Persistent Memory Module (or just "Optane DC PMM"). This new nonvolatile DIMM supports byte-granularity accesses with access times on the order of DRAM, while also providing data storage that survives power outages. This work comprises the first in-depth, scholarly, performance review of Intel's Optane DC PMM, exploring its capabilities as a main memory device, and as persistent, byte-addressable memory exposed to user-space applications. This report details the technologies performance under a number of modes and scenarios, and across a wide variety of macro-scale benchmarks. Optane DC PMMs can be used as large memory devices with a DRAM cache to hide their lower bandwidth and higher latency. When used in this Memory (or cached) mode, Optane DC memory has little impact on applications with small memory footprints. Applications with larger memory footprints may experience some slow-down relative to DRAM, but are now able to keep much more data in memory. When used under a file system, Optane DC PMMs can result in significant performance gains, especially when the file system is optimized to use the load/store interface of the Optane DC PMM and the application uses many small, persistent writes. For instance, using the NOVA-relaxed NVMM file system, we can improve the performance of Kyoto Cabinet by almost 2x. Optane DC PMMs can also enable user-space persistence where the application explicitly controls its writes into persistent Optane DC media. In our experiments, modified applications that used user-space Optane DC persistence generally outperformed their file system counterparts. For instance, the persistent version of RocksDB performed almost 2x faster than the equivalent program utilizing an NVMM-aware file system.

cs.DC↗

arXiv2019

BMN: Boundary-Matching Network for Temporal Action Proposal Generation

Temporal action proposal generation is an challenging and promising task which aims to locate temporal regions in real-world videos where action or event may occur. Current bottom-up proposal generation methods can generate proposals with precise boundary, but cannot efficiently generate adequately reliable confidence scores for retrieving proposals. To address these difficulties, we introduce the Boundary-Matching (BM) mechanism to evaluate confidence scores of densely distributed proposals, which denote a proposal as a matching pair of starting and ending boundaries and combine all densely distributed BM pairs into the BM confidence map. Based on BM mechanism, we propose an effective, efficient and end-to-end proposal generation method, named Boundary-Matching Network (BMN), which generates proposals with precise temporal boundaries as well as reliable confidence scores simultaneously. The two-branches of BMN are jointly trained in an unified framework. We conduct experiments on two challenging datasets: THUMOS-14 and ActivityNet-1.3, where BMN shows significant performance improvement with remarkable efficiency and generalizability. Further, combining with existing action classifier, BMN can achieve state-of-the-art temporal action detection performance.

cs.CV↗

arXiv2019

Open Domain Event Extraction Using Neural Latent Variable Models

We consider open domain event extraction, the task of extracting unconstraint types of events from news clusters. A novel latent variable neural model is constructed, which is scalable to very large corpus. A dataset is collected and manually annotated, with task-specific evaluation metrics being designed. Results show that the proposed unsupervised model gives better performance compared to the state-of-the-art method for event schema induction.

cs.CL↗

arXiv2019

Reinforcement Learning in Multiple-UAV Networks: Deployment and Movement Design

A novel framework is proposed for quality of experience (QoE)-driven deployment and dynamic movement of multiple unmanned aerial vehicles (UAVs). The problem of joint non-convex three-dimensional (3D) deployment and dynamic movement of the UAVs is formulated for maximizing the sum mean opinion score (MOS) of ground users, which is proved to be NP-hard. In the aim of solving this pertinent problem, a three-step approach is proposed for attaining 3D deployment and dynamic movement of multiple UAVs. Firstly, genetic algorithm based K-means (GAK-means) algorithm is utilized for obtaining the cell partition of the users. Secondly, Q-learning based deployment algorithm is proposed, in which each UAV acts as an agent, making their own decision for attaining 3D position by learning from trial and mistake. In contrast to conventional genetic algorithm based learning algorithms, the proposed algorithm is capable of training the direction selection strategy offline. Thirdly, Q-learning based movement algorithm is proposed in the scenario that the users are roaming. The proposed algorithm is capable of converging to an optimal state. Numerical results reveal that the proposed algorithms show a fast convergence rate after a small number of iterations. Additionally, the proposed Q-learning based deployment algorithm outperforms K-means algorithms and Iterative-GAKmean (IGK) algorithms with a low complexity.

eess.SP↗

arXiv2019

Trajectory Design and Power Control for Multi-UAV Assisted Wireless Networks: A Machine Learning Approach

A novel framework is proposed for the trajectory design of multiple unmanned aerial vehicles (UAVs) based on the prediction of users' mobility information. The problem of joint trajectory design and power control is formulated for maximizing the instantaneous sum transmit rate while satisfying the rate requirement of users. In an effort to solve this pertinent problem, a three-step approach is proposed which is based on machine learning techniques to obtain both the position information of users and the trajectory design of UAVs. Firstly, a multi-agent Q-learning based placement algorithm is proposed for determining the optimal positions of the UAVs based on the initial location of the users. Secondly, in an effort to determine the mobility information of users based on a real dataset, their position data is collected from Twitter to describe the anonymous user-trajectories in the physical world. In the meantime, an echo state network (ESN) based prediction algorithm is proposed for predicting the future positions of users based on the real dataset. Thirdly, a multi-agent Q-learning based algorithm is conceived for predicting the position of UAVs in each time slot based on the movement of users. In this algorithm, multiple UAVs act as agents to find optimal actions by interacting with their environment and learn from their mistakes. Additionally, we also prove that the proposed multi-agent Q-learning based trajectory design and power control algorithm can converge under mild conditions. Numerical results are provided to demonstrate that as the size of the reservoir increases, the proposed ESN approach improves the prediction accuracy. Finally, we demonstrate that throughput gains of about 17% are achieved.

eess.SP↗

arXiv2019

Identifying Cache-Based Side Channels through Secret-Augmented Abstract Interpretation

Cache-based side channels enable a dedicated attacker to reveal program secrets by measuring the cache access patterns. Practical attacks have been shown against real-world crypto algorithm implementations such as RSA, AES, and ElGamal. By far, identifying information leaks due to cache-based side channels, either in a static or dynamic manner, remains a challenge: the existing approaches fail to offer high precision, full coverage, and good scalability simultaneously, thus impeding their practical use in real-world scenarios. In this paper, we propose a novel static analysis method on binaries to detect cache-based side channels. We use abstract interpretation to reason on program states with respect to abstract values at each program point. To make such abstract interpretation scalable to real-world cryptosystems while offering high precision and full coverage, we propose a novel abstract domain called the Secret-Augmented Symbolic domain (SAS). SAS tracks program secrets and dependencies on them for precision, while it tracks only coarse-grained public information for scalability. We have implemented the proposed technique into a practical tool named CacheS and evaluated it on the implementations of widely-used cryptographic algorithms in real-world crypto libraries, including Libgcrypt, OpenSSL, and mbedTLS. CacheS successfully confirmed a total of 154 information leaks reported by previous research and 54 leaks that were previously unknown. We have reported our findings to the developers. And they confirmed that many of those unknown information leaks do lead to potential side channels.

cs.CR↗

arXiv2019

PANDA: AdaPtive Noisy Data Augmentation for Regularization of Undirected Graphical Models

We propose an AdaPtive Noise Augmentation (PANDA) technique to regularize the estimation and construction of undirected graphical models. PANDA iteratively optimizes the objective function given the noise augmented data until convergence to achieve regularization on model parameters. The augmented noises can be designed to achieve various regularization effects on graph estimation, such as the bridge (including lasso and ridge), elastic net, adaptive lasso, and SCAD penalization; it also realizes the group lasso and fused ridge. We examine the tail bound of the noise-augmented loss function and establish that the noise-augmented loss function and its minimizer converge almost surely to the expected penalized loss function and its minimizer, respectively. We derive the asymptotic distributions for the regularized parameters through PANDA in generalized linear models, based on which, inferences for the parameters can be obtained simultaneously with variable selection. We show the non-inferior performance of PANDA in constructing graphs of different types in simulation studies and apply PANDA to an autism spectrum disorder data to construct a mixed-node graph. We also show that the inferences based on the asymptotic distribution of regularized parameter estimates via PANDA achieve nominal or near-nominal coverage and are far more efficient, compared to some existing post-selection procedures. Computationally, PANDA can be easily programmed in software that implements (GLMs) without resorting to complicated optimization techniques.

stat.ML↗

arXiv2019

AdaPtive Noisy Data Augmentation (PANDA) for Simultaneous Construction of Multiple Graph Models

We extend the data augmentation technique PANDA by Li et al. (2018) that regularizes single graph estimation to jointly learning multiple graphical models with various node types in a unified framework. We design two types of noise to augment the observed data: the first type regularizes the estimation of each graph while the second type promotes either the structural similarity, referred as the \joint group lasso regularization, or the numerical similarity, referred as the joint fused ridge regularization, among the edges in the same position across graphs. The computation in PANDA is straightforward and only involves obtaining maximum likelihood estimator in generalized linear models in an iterative manner. The simulation studies demonstrate PANDA is non-inferior to existing joint estimation approaches for Gaussian graphical models, and significantly improves over the naive differencing approach for non-Gaussian graphical models. We apply PANDA to a real-life lung cancer microarray data to simultaneously construct four protein networks.

stat.ME↗

arXiv2019

Adapting Image Super-Resolution State-of-the-arts and Learning Multi-model Ensemble for Video Super-Resolution

Recently, image super-resolution has been widely studied and achieved significant progress by leveraging the power of deep convolutional neural networks. However, there has been limited advancement in video super-resolution (VSR) due to the complex temporal patterns in videos. In this paper, we investigate how to adapt state-of-the-art methods of image super-resolution for video super-resolution. The proposed adapting method is straightforward. The information among successive frames is well exploited, while the overhead on the original image super-resolution method is negligible. Furthermore, we propose a learning-based method to ensemble the outputs from multiple super-resolution models. Our methods show superior performance and rank second in the NTIRE2019 Video Super-Resolution Challenge Track 1.

cs.CV↗

arXiv2019

STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editing

Arbitrary attribute editing generally can be tackled by incorporating encoder-decoder and generative adversarial networks. However, the bottleneck layer in encoder-decoder usually gives rise to blurry and low quality editing result. And adding skip connections improves image quality at the cost of weakened attribute manipulation ability. Moreover, existing methods exploit target attribute vector to guide the flexible translation to desired target domain. In this work, we suggest to address these issues from selective transfer perspective. Considering that specific editing task is certainly only related to the changed attributes instead of all target attributes, our model selectively takes the difference between target and source attribute vectors as input. Furthermore, selective transfer units are incorporated with encoder-decoder to adaptively select and modify encoder feature for enhanced attribute editing. Experiments show that our method (i.e., STGAN) simultaneously improves attribute manipulation accuracy as well as perception quality, and performs favorably against state-of-the-arts in arbitrary facial attribute editing and season translation.

cs.CV↗

arXiv2019

Determine Arbitrary Feynman Integrals by Vacuum Integrals

By introducing an auxiliary parameter, we find a new representation for Feynman integrals, which defines a Feynman integral by analytical continuation of a series containing only vacuum integrals. The new representation therefore conceptually translates the problem of computing Feynman integrals to the problem of performing analytical continuations. As an application of the new representation, we use it to construct a novel reduction method for multi-loop Feynman integrals, which is expected to be more efficient than known integration-by-parts reduction method. Using the new method, we successfully reduced all complicated two-loop integrals in $gg\to HH$ process and $gg\to ggg$ process.

hep-ph↗

arXiv2019

Analysis of Large Heterogeneous Repairable System Reliability Data with Static System Attributes and Dynamic Sensor Measurement in Big Data Environment

In Big Data environment, one pressing challenge facing engineers is to perform reliability analysis for a large fleet of heterogeneous repairable systems with covariates. In addition to static covariates, which include time-invariant system attributes such as nominal operating conditions, geo-locations, etc., the recent advances of sensing technologies have also made it possible to obtain dynamic sensor measurement of system operating and environmental conditions. As a common practice in the Big Data environment, the massive reliability data are typically stored in some distributed storage systems. Leveraging the power of modern statistical learning, this paper investigates a statistical approach which integrates the Random Forests algorithm and the classical data analysis methodologies for repairable system reliability, such as the nonparametric estimator for the Mean Cumulative Function and the parametric models based on the Nonhomogeneous Poisson Process. We show that the proposed approach effectively addresses some common challenges arising from practice, including system heterogeneity, covariate selection, model specification and data locality due to the distributed data storage. The large sample properties as well as the uniform consistency of the proposed estimator is established. Two numerical examples and a case study are presented to illustrate the application of the proposed approach. The strengths of the proposed approach are demonstrated by comparison studies.

stat.AP↗