arXiv subjects

Xiao Wu

Publications and source records attributed to Xiao Wu.

69 records · Page 4Linked to original sources

arXiv2021

Metaverse for Social Good: A University Campus Prototype

In recent years, the metaverse has attracted enormous attention from around the world with the development of related technologies. The expected metaverse should be a realistic society with more direct and physical interactions, while the concepts of race, gender, and even physical disability would be weakened, which would be highly beneficial for society. However, the development of metaverse is still in its infancy, with great potential for improvement. Regarding metaverse's huge potential, industry has already come forward with advance preparation, accompanied by feverish investment, but there are few discussions about metaverse in academia to scientifically guide its development. In this paper, we highlight the representative applications for social good. Then we propose a three-layer metaverse architecture from a macro perspective, containing infrastructure, interaction, and ecosystem. Moreover, we journey toward both a historical and novel metaverse with a detailed timeline and table of specific attributes. Lastly, we illustrate our implemented blockchain-driven metaverse prototype of a university campus and discuss the prototype design and insights.

cs.MM↗

arXiv2021

Matching on Generalized Propensity Scores with Continuous Exposures

In the context of a binary treatment, matching is a well-established approach in causal inference. However, in the context of a continuous treatment or exposure, matching is still underdeveloped. We propose an innovative matching approach to estimate an average causal exposure-response function under the setting of continuous exposures that relies on the generalized propensity score (GPS). Our approach maintains the following attractive features of matching: a) clear separation between the design and the analysis; b) robustness to model misspecification or to the presence of extreme values of the estimated GPS; c) straightforward assessment of covariate balance. We first introduce an assumption of identifiability, called local weak unconfoundedness. Under this assumption and mild smoothness conditions, we provide theoretical guarantees that our proposed matching estimator attains point-wise consistency and asymptotic normality. In simulations, our proposed matching approach outperforms existing methods under settings of model misspecification or the presence of extreme values of the estimated GPS. We apply our proposed method to estimate the average causal exposure-response function between long-term PM$_{2.5}$ exposure and all-cause mortality among 68.5 million Medicare enrollees, 2000-2016. We found strong evidence of a harmful effect of long-term PM$_{2.5}$ exposure on mortality. Code for the proposed matching approach is provided in the CausalGPS R package, which is available on CRAN and provides a computationally efficient implementation.

stat.ME↗

arXiv2021

Solve routing problems with a residual edge-graph attention neural network

For NP-hard combinatorial optimization problems, it is usually difficult to find high-quality solutions in polynomial time. The design of either an exact algorithm or an approximate algorithm for these problems often requires significantly specialized knowledge. Recently, deep learning methods provide new directions to solve such problems. In this paper, an end-to-end deep reinforcement learning framework is proposed to solve this type of combinatorial optimization problems. This framework can be applied to different problems with only slight changes of input (for example, for a traveling salesman problem (TSP), the input is the two-dimensional coordinates of nodes; while for a capacity-constrained vehicle routing problem (CVRP), the input is simply changed to three-dimensional vectors including the two-dimensional coordinates and the customer demands of nodes), masks and decoder context vectors. The proposed framework is aiming to improve the models in literacy in terms of the neural network model and the training algorithm. The solution quality of TSP and the CVRP up to 100 nodes are significantly improved via our framework. Specifically, the average optimality gap is reduced from 4.53\% (reported best \cite{R22}) to 3.67\% for TSP with 100 nodes and from 7.34\% (reported best \cite{R22}) to 6.68\% for CVRP with 100 nodes when using the greedy decoding strategy. Furthermore, our framework uses about 1/3$\sim$3/4 training samples compared with other existing learning methods while achieving better results. The results performed on randomly generated instances and the benchmark instances from TSPLIB and CVRPLIB confirm that our framework has a linear running time on the problem size (number of nodes) during the testing phase, and has a good generalization performance from random instance training to real-world instance testing.

cs.LG↗

arXiv2020

Adversarial Multimodal Network for Movie Question Answering

Visual question answering by using information from multiple modalities has attracted more and more attention in recent years. However, it is a very challenging task, as the visual content and natural language have quite different statistical properties. In this work, we present a method called Adversarial Multimodal Network (AMN) to better understand video stories for question answering. In AMN, as inspired by generative adversarial networks, we propose to learn multimodal feature representations by finding a more coherent subspace for video clips and the corresponding texts (e.g., subtitles and questions). Moreover, we introduce a self-attention mechanism to enforce the so-called consistency constraints in order to preserve the self-correlation of visual cues of the original video clips in the learned multimodal representations. Extensive experiments on the MovieQA dataset show the effectiveness of our proposed AMN over other published state-of-the-art methods.

cs.CV↗

arXiv2019

Optimizing Interim Analysis Timing for Bayesian Adaptive Commensurate Designs

In developing products for rare diseases, statistical challenges arise due to the limited number of patients available for participation in drug trials and other clinical research. Bayesian adaptive clinical trial designs offer the possibility of increased statistical efficiency, reduced development cost and ethical hazard prevention via their incorporation of evidence from external sources (historical data, expert opinions, and real-world evidence), and flexibility in the specification of interim looks. In this paper, we propose a novel Bayesian adaptive commensurate design that borrows adaptively from historical information and also uses a particular payoff function to optimize the timing of the study's interim analysis. The trial payoff is a function of how many samples can be saved via early stopping and the probability of making correct early decisions for either futility or efficacy. We calibrate our Bayesian algorithm to have acceptable long-run frequentist properties (Type I error and power) via simulation at the design stage. We illustrate our approach using a pediatric trial design setting testing the effect of a new drug for a rare genetic disease. The optimIA R package available at https://github.com/wxwx1993/Bayesian_IA_Timing provides an easy-to-use implementation of our approach.

stat.AP↗

arXiv2019

Improving the Learning of Multi-column Convolutional Neural Network for Crowd Counting

Tremendous variation in the scale of people/head size is a critical problem for crowd counting. To improve the scale invariance of feature representation, recent works extensively employ Convolutional Neural Networks with multi-column structures to handle different scales and resolutions. However, due to the substantial redundant parameters in columns, existing multi-column networks invariably exhibit almost the same scale features in different columns, which severely affects counting accuracy and leads to overfitting. In this paper, we attack this problem by proposing a novel Multi-column Mutual Learning (McML) strategy. It has two main innovations: 1) A statistical network is incorporated into the multi-column framework to estimate the mutual information between columns, which can approximately indicate the scale correlation between features from different columns. By minimizing the mutual information, each column is guided to learn features with different image scales. 2) We devise a mutual learning scheme that can alternately optimize each column while keeping the other columns fixed on each mini-batch training data. With such asynchronous parameter update process, each column is inclined to learn different feature representation from others, which can efficiently reduce the parameter redundancy and improve generalization ability. More remarkably, McML can be applied to all existing multi-column networks and is end-to-end trainable. Extensive experiments on four challenging benchmarks show that McML can significantly improve the original multi-column networks and outperform the other state-of-the-art approaches.

cs.CV↗

arXiv2019

Learning Spatial Awareness to Improve Crowd Counting

The aim of crowd counting is to estimate the number of people in images by leveraging the annotation of center positions for pedestrians' heads. Promising progresses have been made with the prevalence of deep Convolutional Neural Networks. Existing methods widely employ the Euclidean distance (i.e., $L_2$ loss) to optimize the model, which, however, has two main drawbacks: (1) the loss has difficulty in learning the spatial awareness (i.e., the position of head) since it struggles to retain the high-frequency variation in the density map, and (2) the loss is highly sensitive to various noises in crowd counting, such as the zero-mean noise, head size changes, and occlusions. Although the Maximum Excess over SubArrays (MESA) loss has been previously proposed to address the above issues by finding the rectangular subregion whose predicted density map has the maximum difference from the ground truth, it cannot be solved by gradient descent, thus can hardly be integrated into the deep learning framework. In this paper, we present a novel architecture called SPatial Awareness Network (SPANet) to incorporate spatial context for crowd counting. The Maximum Excess over Pixels (MEP) loss is proposed to achieve this by finding the pixel-level subregion with high discrepancy to the ground truth. To this end, we devise a weakly supervised learning scheme to generate such region with a multi-branch architecture. The proposed framework can be integrated into existing deep crowd counting methods and is end-to-end trainable. Extensive experiments on four challenging benchmarks show that our method can significantly improve the performance of baselines. More remarkably, our approach outperforms the state-of-the-art methods on all benchmark datasets.

cs.CV↗

arXiv2019

Rhythm Dungeon: A Blockchain-based Music Roguelike Game

Rhythm Dungeon is a rhythm game which leverages the blockchain as a shared open database. During the gaming session, the player explores a roguelike dungeon by inputting specific sequences in time to music rhythm. By integrating smart contract to the game program, the enemies through the venture are generated from other games which share the identical blockchain. On the other hand, the player may upload their characters at the end of their journey, so that their own character may appear in other games and make an influence. Rhythm Dungeon is designed and implemented to show the potential of decentralized gaming experience, which utilizes the blockchain to provide asynchronous interactions among massive players.

cs.MM↗

arXiv2018

Video2Shop: Exact Matching Clothes in Videos to Online Shopping Images

In recent years, both online retail and video hosting service are exponentially growing. In this paper, we explore a new cross-domain task, Video2Shop, targeting for matching clothes appeared in videos to the exact same items in online shops. A novel deep neural network, called AsymNet, is proposed to explore this problem. For the image side, well-established methods are used to detect and extract features for clothing patches with arbitrary sizes. For the video side, deep visual features are extracted from detected object regions in each frame, and further fed into a Long Short-Term Memory (LSTM) framework for sequence modeling, which captures the temporal dynamics in videos. To conduct exact matching between videos and online shopping images, LSTM hidden states, representing the video, and image features, which represent static object images, are jointly modeled under the similarity network with reconfigurable deep tree structure. Moreover, an approximate training method is proposed to achieve the efficiency when training. Extensive experiments conducted on a large cross-domain dataset have demonstrated the effectiveness and efficiency of the proposed AsymNet, which outperforms the state-of-the-art methods.

cs.CV↗

arXiv2018

Perceiving Physical Equation by Observing Visual Scenarios

Inferring universal laws of the environment is an important ability of human intelligence as well as a symbol of general AI. In this paper, we take a step toward this goal such that we introduce a new challenging problem of inferring invariant physical equation from visual scenarios. For instance, teaching a machine to automatically derive the gravitational acceleration formula by watching a free-falling object. To tackle this challenge, we present a novel pipeline comprised of an Observer Engine and a Physicist Engine by respectively imitating the actions of an observer and a physicist in the real world. Generally, the Observer Engine watches the visual scenarios and then extracting the physical properties of objects. The Physicist Engine analyses these data and then summarizing the inherent laws of object dynamics. Specifically, the learned laws are expressed by mathematical equations such that they are more interpretable than the results given by common probabilistic models. Experiments on synthetic videos have shown that our pipeline is able to discover physical equations on various physical worlds with different visual appearances.

cs.AI↗

arXiv2018

The three-parameter correlations about optical plateaus of gamma-ray bursts

Well-sampled optical light curves of 50 gamma-ray bursts (GRBs) with plateau features are compiled from the literature. By empirical fitting, we obtained the parameters of the optical plateaus, such as the decay slopes ($α_{\rm 1}$ and $α_{\rm 2}$), the break times ($T_{\rm b}$), and the corresponding optical fluxes ($F_{\rm b}$) at the break times. The break time of optical plateaus ranges from tens of seconds to $10^6$ seconds, with a typical value about $10^4$ seconds. We have calculated the break luminosity, and it mainly ranges from $10^{44}$ erg $s^{-1}$ to $10^{47}$ erg $s^{-1}$, which is generally two or three orders of magnitude less than the corresponding break luminosity of the X-ray afterglow plateaus. We reanalyzed the optical plateaus and also found that a significantly tighter correlation exists when we added the isotropic equivalent energy of GRBs $E_{\rm γ,iso}$ into the $L_{\rm b,z}-T_{\rm b,z}$ relation. The best fit correlation is obtained to be $L_{\rm b,z}\propto T_{\rm b,z}^{-0.9}E_{\rm γ,iso}^{0.4}$. We next explored the possible correlations among $L_{\rm b,z}$, $T_{\rm b,z}$ and $E_{\rm p,i}$, and found there is also a tight correlation between them, which takes the form of $L_{\rm b,z}\propto T_{\rm b,z}^{-0.9}E_{\rm p,i}^{0.5}$. We argue that these two tight $L_{\rm b,z}-T_{\rm b,z}-E_{\rm γ,iso}$ and $L_{\rm b,z}-T_{\rm b,z}-E_{\rm p,i}$ correlations are more physical, and it may be directly related to radiation physics of GRBs. The tight correlations are possible to be used as standard candles.

astro-ph.HE↗

arXiv2018

Causal inference in the context of an error prone exposure: air pollution and mortality

We propose a new approach for estimating causal effects when the exposure is measured with error and confounding adjustment is performed via a generalized propensity score (GPS). Using validation data, we propose a regression calibration (RC)-based adjustment for a continuous error-prone exposure combined with GPS to adjust for confounding (RC-GPS). The outcome analysis is conducted after transforming the corrected continuous exposure into a categorical exposure. We consider confounding adjustment in the context of GPS subclassification, inverse probability treatment weighting (IPTW) and matching. In simulations with varying degrees of exposure error and confounding bias, RC-GPS eliminates bias from exposure error and confounding compared to standard approaches that rely on the error-prone exposure. We applied RC-GPS to a rich data platform to estimate the causal effect of long-term exposure to fine particles ($PM_{2.5}$) on mortality in New England for the period from 2000 to 2012. The main study consists of $2,202$ zip codes covered by $217,660$ 1km $\times$ 1km grid cells with yearly mortality rates, yearly $PM_{2.5}$ averages estimated from a spatio-temporal model (error-prone exposure) and several potential confounders. The internal validation study includes a subset of 83 1km $\times$ 1km grid cells within 75 zip codes from the main study with error-free yearly $PM_{2.5}$ exposures obtained from monitor stations. Under assumptions of non-interference and weak unconfoundedness, using matching we found that exposure to moderate levels of $PM_{2.5}$ ($8 <$ $PM_{2.5}$ $\leq 10\ {\rm μg/m^3}$) causes a $2.8\%$ ($95\%$ CI: $0.6\%, 3.6\%$) increase in all-cause mortality compared to low exposure ($PM_{2.5}$ $\leq 8\ {\rm μg/m^3}$).

stat.ME↗

arXiv2018

On the Selection of Anchors and Targets for Video Hyperlinking

A problem not well understood in video hyperlinking is what qualifies a fragment as an anchor or target. Ideally, anchors provide good starting points for navigation, and targets supplement anchors with additional details while not distracting users with irrelevant, false and redundant information. The problem is not trivial for intertwining relationship between data characteristics and user expectation. Imagine that in a large dataset, there are clusters of fragments spreading over the feature space. The nature of each cluster can be described by its size (implying popularity) and structure (implying complexity). A principle way of hyperlinking can be carried out by picking centers of clusters as anchors and from there reach out to targets within or outside of clusters with consideration of neighborhood complexity. The question is which fragments should be selected either as anchors or targets, in one way to reflect the rich content of a dataset, and meanwhile to minimize the risk of frustrating user experience. This paper provides some insights to this question from the perspective of hubness and local intrinsic dimensionality, which are two statistical properties in assessing the popularity and complexity of data space. Based these properties, two novel algorithms are proposed for low-risk automatic selection of anchors and targets.

cs.CV↗

arXiv2018

Multi-View Image Generation from a Single-View

This paper addresses a challenging problem -- how to generate multi-view cloth images from only a single view input. To generate realistic-looking images with different views from the input, we propose a new image generation model termed VariGANs that combines the strengths of the variational inference and the Generative Adversarial Networks (GANs). Our proposed VariGANs model generates the target image in a coarse-to-fine manner instead of a single pass which suffers from severe artifacts. It first performs variational inference to model global appearance of the object (e.g., shape and color) and produce a coarse image with a different view. Conditioned on the generated low resolution images, it then proceeds to perform adversarial learning to fill details and generate images of consistent details with the input. Extensive experiments conducted on two clothing datasets, MVC and DeepFashion, have demonstrated that images of a novel view generated by our model are more plausible than those generated by existing approaches, in terms of more consistent global appearance as well as richer and sharper details.

cs.CV↗

arXiv2017

Diversified Visual Attention Networks for Fine-Grained Object Classification

Fine-grained object classification is a challenging task due to the subtle inter-class difference and large intra-class variation. Recently, visual attention models have been applied to automatically localize the discriminative regions of an image for better capturing critical difference and demonstrated promising performance. However, without consideration of the diversity in attention process, most of existing attention models perform poorly in classifying fine-grained objects. In this paper, we propose a diversified visual attention network (DVAN) to address the problems of fine-grained object classification, which substan- tially relieves the dependency on strongly-supervised information for learning to localize discriminative regions compared with attentionless models. More importantly, DVAN explicitly pursues the diversity of attention and is able to gather discriminative information to the maximal extent. Multiple attention canvases are generated to extract convolutional features for attention. An LSTM recurrent unit is employed to learn the attentiveness and discrimination of attention canvases. The proposed DVAN has the ability to attend the object from coarse to fine granularity, and a dynamic internal representation for classification is built up by incrementally combining the information from different locations and scales of the image. Extensive experiments con- ducted on CUB-2011, Stanford Dogs and Stanford Cars datasets have demonstrated that the proposed diversified visual attention networks achieve competitive performance compared to the state- of-the-art approaches, without using any prior knowledge, user interaction or external resource in training or testing.

cs.CV↗