arXiv subjects

Jiawei Zhang

Publications and source records attributed to Jiawei Zhang.

394 records · Page 22Linked to original sources

arXiv2017

CREST: Convolutional Residual Learning for Visual Tracking

Discriminative correlation filters (DCFs) have been shown to perform superiorly in visual tracking. They only need a small set of training samples from the initial frame to generate an appearance model. However, existing DCFs learn the filters separately from feature extraction, and update these filters using a moving average operation with an empirical weight. These DCF trackers hardly benefit from the end-to-end training. In this paper, we propose the CREST algorithm to reformulate DCFs as a one-layer convolutional neural network. Our method integrates feature extraction, response map generation as well as model update into the neural networks for an end-to-end training. To reduce model degradation during online update, we apply residual learning to take appearance changes into account. Extensive experiments on the benchmark datasets demonstrate that our CREST tracker performs favorably against state-of-the-art trackers.

cs.CV↗

arXiv2017

NPGLM: A Non-Parametric Method for Temporal Link Prediction

In this paper, we try to solve the problem of temporal link prediction in information networks. This implies predicting the time it takes for a link to appear in the future, given its features that have been extracted at the current network snapshot. To this end, we introduce a probabilistic non-parametric approach, called "Non-Parametric Generalized Linear Model" (NP-GLM), which infers the hidden underlying probability distribution of the link advent time given its features. We then present a learning algorithm for NP-GLM and an inference method to answer time-related queries. Extensive experiments conducted on both synthetic data and real-world Sina Weibo social network demonstrate the effectiveness of NP-GLM in solving temporal link prediction problem vis-a-vis competitive baselines.

cs.LG↗

arXiv2016

Learning Fully Convolutional Networks for Iterative Non-blind Deconvolution

In this paper, we propose a fully convolutional networks for iterative non-blind deconvolution We decompose the non-blind deconvolution problem into image denoising and image deconvolution. We train a FCNN to remove noises in the gradient domain and use the learned gradients to guide the image deconvolution step. In contrast to the existing deep neural network based methods, we iteratively deconvolve the blurred images in a multi-stage framework. The proposed method is able to learn an adaptive image prior, which keeps both local (details) and global (structures) information. Both quantitative and qualitative evaluations on benchmark datasets demonstrate that the proposed method performs favorably against state-of-the-art algorithms in terms of quality and speed.

cs.CV↗

arXiv2016

3D Hand Pose Tracking and Estimation Using Stereo Matching

3D hand pose tracking/estimation will be very important in the next generation of human-computer interaction. Most of the currently available algorithms rely on low-cost active depth sensors. However, these sensors can be easily interfered by other active sources and require relatively high power consumption. As a result, they are currently not suitable for outdoor environments and mobile devices. This paper aims at tracking/estimating hand poses using passive stereo which avoids these limitations. A benchmark with 18,000 stereo image pairs and 18,000 depth images captured from different scenarios and the ground-truth 3D positions of palm and finger joints (obtained from the manual label) is thus proposed. This paper demonstrates that the performance of the state-of-the art tracking/estimation algorithms can be maintained with most stereo matching algorithms on the proposed benchmark, as long as the hand segmentation is correct. As a result, a novel stereo-based hand segmentation algorithm specially designed for hand tracking/estimation is proposed. The quantitative evaluation demonstrates that the proposed algorithm is suitable for the state-of-the-art hand pose tracking/estimation algorithms and the tracking quality is comparable to the use of active depth sensors under different challenging scenarios.

cs.CV↗

arXiv2016

RGBD Salient Object Detection via Deep Fusion

Numerous efforts have been made to design different low level saliency cues for the RGBD saliency detection, such as color or depth contrast features, background and color compactness priors. However, how these saliency cues interact with each other and how to incorporate these low level saliency cues effectively to generate a master saliency map remain a challenging problem. In this paper, we design a new convolutional neural network (CNN) to fuse different low level saliency cues into hierarchical features for automatically detecting salient objects in RGBD images. In contrast to the existing works that directly feed raw image pixels to the CNN, the proposed method takes advantage of the knowledge in traditional saliency detection by adopting various meaningful and well-designed saliency feature vectors as input. This can guide the training of CNN towards detecting salient object more effectively due to the reduced learning ambiguity. We then integrate a Laplacian propagation framework with the learned CNN to extract a spatially consistent saliency map by exploiting the intrinsic structure of the input image. Extensive quantitative and qualitative experimental evaluations on three datasets demonstrate that the proposed method consistently outperforms state-of-the-art methods.

cs.CV↗

arXiv2016

Badge System Analysis and Design

To incentivize users' participations and steer their online activities, online social networks start to provide users with various kinds of rewards for their contributions to the sites. The most frequently distributed rewards include account levels, reputation scores, different kinds of badges, and even material awards like small gifts and cash back, etc. Attracted by these rewards, users will spend more time using the network services. In this paper, we will mainly focus on "badges reward systems" but the proposed models can be applied to other reward systems as well. Badges are small icons attached to users' homepages and profiles denoting their achievements. People like to accumulate badge for various reasons and different badges can have specific values for them. Meanwhile, to get badges, they also need to exert efforts to finish the required tasks, which can lead to certain costs. To understand and model users' motivations in badge achievement activities, we will study an existing badge system launched inside a real-world online social network, Foursquare, in this paper. At the same time, to maximize users' contributions to online social networks, social network system designers need to determine the optimal badge system mechanism carefully. Badge system mechanism describes various detailed aspects of the system and can involve many parameters, e.g., categories of existing badges, number of badges available as well as the minimum contributions required to obtain the badges, which all need to be designed with meticulous investigations. Based on the model of users' badges accumulating activities, in this paper, we will also study how to design the badge system that can incentivize the maximum users' contributions to the social networks.

cs.SI↗

arXiv2016

Intertwined Viral Marketing through Online Social Networks

Traditional viral marketing problems aim at selecting a subset of seed users for one single product to maximize its awareness in social networks. However, in real scenarios, multiple products can be promoted in social networks at the same time. At the product level, the relationships among these products can be quite intertwined, e.g., competing, complementary and independent. In this paper, we will study the "interTwined Influence Maximization" (i.e., TIM) problem for one product that we target on in online social networks, where multiple other competing/complementary/independent products are being promoted simultaneously. The TIM problem is very challenging to solve due to (1) few existing models can handle the intertwined diffusion procedure of multiple products concurrently, and (2) optimal seed user selection for the target product may depend on other products' marketing strategies a lot. To address the TIM problem, a unified greedy framework TIER (interTwined Influence EstimatoR) is proposed in this paper. Extensive experiments conducted on four different types of real-world social networks demonstrate that TIER can outperform all the comparison methods with significant advantages in solving the TIM problem.

cs.SI↗

arXiv2016

Multi-Source Multi-View Clustering via Discrepancy Penalty

With the advance of technology, entities can be observed in multiple views. Multiple views containing different types of features can be used for clustering. Although multi-view clustering has been successfully applied in many applications, the previous methods usually assume the complete instance mapping between different views. In many real-world applications, information can be gathered from multiple sources, while each source can contain multiple views, which are more cohesive for learning. The views under the same source are usually fully mapped, but they can be very heterogeneous. Moreover, the mappings between different sources are usually incomplete and partially observed, which makes it more difficult to integrate all the views across different sources. In this paper, we propose MMC (Multi-source Multi-view Clustering), which is a framework based on collective spectral clustering with a discrepancy penalty across sources, to tackle these challenges. MMC has several advantages compared with other existing methods. First, MMC can deal with incomplete mapping between sources. Second, it considers the disagreements between sources while treating views in the same source as a cohesive set. Third, MMC also tries to infer the instance similarities across sources to enhance the clustering performance. Extensive experiments conducted on real-world data demonstrate the effectiveness of the proposed approach.

cs.LG↗

arXiv2016

Bicycle-Sharing System Analysis and Trip Prediction

Bicycle-sharing systems, which can provide shared bike usage services for the public, have been launched in many big cities. In bicycle-sharing systems, people can borrow and return bikes at any stations in the service region very conveniently. Therefore, bicycle-sharing systems are normally used as a short-distance trip supplement for private vehicles as well as regular public transportation. Meanwhile, for stations located at different places in the service region, the bike usages can be quite skewed and imbalanced. Some stations have too many incoming bikes and get jammed without enough docks for upcoming bikes, while some other stations get empty quickly and lack enough bikes for people to check out. Therefore, inferring the potential destinations and arriving time of each individual trip beforehand can effectively help the service providers schedule manual bike re-dispatch in advance. In this paper, we will study the individual trip prediction problem for bicycle-sharing systems. To address the problem, we study a real-world bicycle-sharing system and analyze individuals' bike usage behaviors first. Based on the analysis results, a new trip destination prediction and trip duration inference model will be introduced. Experiments conducted on a real-world bicycle-sharing system demonstrate the effectiveness of the proposed model.

cs.CY↗

arXiv2015

A Survey of Heterogeneous Information Network Analysis

Most real systems consist of a large number of interacting, multi-typed components, while most contemporary researches model them as homogeneous networks, without distinguishing different types of objects and links in the networks. Recently, more and more researchers begin to consider these interconnected, multi-typed data as heterogeneous information networks, and develop structural analysis approaches by leveraging the rich semantic meaning of structural types of objects and links in the networks. Compared to widely studied homogeneous network, the heterogeneous information network contains richer structure and semantic information, which provides plenty of opportunities as well as a lot of challenges for data mining. In this paper, we provide a survey of heterogeneous information network analysis. We will introduce basic concepts of heterogeneous information network analysis, examine its developments on different data mining tasks, discuss some advanced topics, and point out some future research directions.

cs.SI↗

arXiv2015

Organizational Chart Inference

Nowadays, to facilitate the communication and cooperation among employees, a new family of online social networks has been adopted in many companies, which are called the "enterprise social networks" (ESNs). ESNs can provide employees with various professional services to help them deal with daily work issues. Meanwhile, employees in companies are usually organized into different hierarchies according to the relative ranks of their positions. The company internal management structure can be outlined with the organizational chart visually, which is normally confidential to the public out of the privacy and security concerns. In this paper, we want to study the IOC (Inference of Organizational Chart) problem to identify company internal organizational chart based on the heterogeneous online ESN launched in it. IOC is very challenging to address as, to guarantee smooth operations, the internal organizational charts of companies need to meet certain structural requirements (about its depth and width). To solve the IOC problem, a novel unsupervised method Create (ChArT REcovEr) is proposed in this paper, which consists of 3 steps: (1) social stratification of ESN users into different social classes, (2) supervision link inference from managers to subordinates, and (3) consecutive social classes matching to prune the redundant supervision links. Extensive experiments conducted on real-world online ESN dataset demonstrate that Create can perform very well in addressing the IOC problem.

cs.SI↗

arXiv2015

Mutual Community Detection across Multiple Partially Aligned Social Networks

Community detection in online social networks has been a hot research topic in recent years. Meanwhile, to enjoy more social network services, users nowadays are usually involved in multiple online social networks simultaneously, some of which can share common information and structures. Networks that involve some common users are named as multiple "partially aligned networks". In this paper, we want to detect communities of multiple partially aligned networks simultaneously, which is formally defined as the "Mutual Clustering" problem. The "Mutual Clustering" problem is very challenging as it has two important issues to address: (1) how to preserve the network characteristics in mutual community detection? and (2) how to utilize the information in other aligned networks to refine and disambiguate the community structures of the shared users? To solve these two challenges, a novel community detection method, MCD (Mutual Community Detector), is proposed in this paper. MCD can detect social community structures of users in multiple partially aligned networks at the same time with full considerations of (1) characteristics of each network, and (2) information of the shared users across aligned networks. Extensive experiments conducted on two real-world partially aligned heterogeneous social networks demonstrate that MCD can solve the "Mutual Clustering" problem very well.

cs.SI↗

arXiv2015

Partial Network Alignment with Anchor Meta Path and Truncated Generic Stable Matching

To enjoy more social network services, users nowadays are usually involved in multiple online social networks simultaneously. The shared users between different networks are called anchor users, while the remaining unshared users are named as non-anchor users. Connections between accounts of anchor users in different networks are defined as anchor links and networks partially aligned by anchor links can be represented as partially aligned networks. In this paper, we want to predict anchor links between partially aligned social networks, which is formally defined as the partial network alignment problem. The partial network alignment problem is very difficult to solve because of the following two challenges: (1) the lack of general features for anchor links, and (2) the "one-to-one$_\le$" (one to at most one) constraint on anchor links. To address these two challenges, a new method PNA (Partial Network Aligner) is proposed in this paper. PNA (1) extracts a set of explicit anchor adjacency features and latent topological features for anchor links based on the anchor meta path concept and tensor decomposition techniques, and (2) utilizes the generic stable matching to identify the non-anchor users to prune the redundant anchor links attached to them. Extensive experiments conducted on two real-world partially aligned social networks demonstrate that PNA can solve the partial network alignment problem very well and outperform all the other comparison methods with significant advantages.

cs.SI↗

arXiv2014

An Improved Algorithm for Fixed-Hub Single Allocation Problem

This paper discusses the fixed-hub single allocation problem (FHSAP). In this problem, a network consists of hub nodes and terminal nodes. Hubs are fixed and fully connected; each terminal node is connected to a single hub which routes all its traffic. The goal is to minimize the cost of routing the traffic in the network. In this paper, we propose a linear programming (LP)-based rounding algorithm. The algorithm is based on two ideas. First, we modify the LP relaxation formulation introduced in Ernst and Krishnamoorthy (1996, 1999) by incorporating a set of validity constraints. Then, after obtaining a fractional solution to the LP relaxation, we make use of a geometric rounding algorithm to obtain an integral solution. We show that by incorporating the validity constraints, the strengthened LP often provides much tighter upper bounds than the previous methods with a little more computational effort, and the solution obtained often has a much smaller gap with the optimal solution. We also formulate a robust version of the FHSAP and show that it can guard against data uncertainty with little cost.

cs.DS↗

arXiv2013

Predicting Social Links for New Users across Aligned Heterogeneous Social Networks

Online social networks have gained great success in recent years and many of them involve multiple kinds of nodes and complex relationships. Among these relationships, social links among users are of great importance. Many existing link prediction methods focus on predicting social links that will appear in the future among all users based upon a snapshot of the social network. In real-world social networks, many new users are joining in the service every day. Predicting links for new users are more important. Different from conventional link prediction problems, link prediction for new users are more challenging due to the following reasons: (1) differences in information distributions between new users and the existing active users (i.e., old users); (2) lack of information from the new users in the network. We propose a link prediction method called SCAN-PS (Supervised Cross Aligned Networks link prediction with Personalized Sampling), to solve the link prediction problem for new users with information transferred from both the existing active users in the target network and other source networks through aligned accounts. We proposed a within-target-network personalized sampling method to process the existing active users' information in order to accommodate the differences in information distributions before the intra-network knowledge transfer. SCAN-PS can also exploit information in other source networks, where the user accounts are aligned with the target network. In this way, SCAN-PS could solve the cold start problem when information of these new users is total absent in the target network.

cs.SI↗

arXiv2007

An Improved Procedure for Selecting the Profiles of Perfectly Matched Layers

The perfectly matched layers (PMLs), as a boundary termination over an unbounded spatial domain, are widely used in numerical simulations of wave propagation problems. Given a set of discretization parameters, a procedure to select the PML profiles based on minimizing the discrete reflectivity is established for frequency domain simulations. We, by extending the function class and adopting a direct search method, improve the former procedure for traveling waves.

math.NA↗