Jin Tang

Large-Scale Graph Database Indexing Based on T-mixture Model and ICA

This paper proposes an indexing scheme based on t- mixture model and ICA, which is more robust than Gaussian mixture modeling when atypical points (or outliers) exist or the set of data has heavy tail. This indexing scheme combines optimized vector quantizer and probabilistic approximate-based indexing scheme. Experimental results on large-scale graph database show a notable efficiency improvement with optimistic precision.

Graph-Laplacian PCA: Closed-Form Solution and Robustness

Principal Component Analysis (PCA) is a widely used to learn a low-dimensional representation. In many applications, both vector data X and graph data W are available. Laplacian embedding is widely used for embedding graph data. We propose a graph-Laplacian PCA (gLPCA) to learn a low dimensional representation of X that incorporates graph structures encoded in W. This model has several advantages: (1) It is a data representation model. (2) It has a compact closed-form solution and can be efficiently computed. (3) It is capable to remove corruptions. Extensive experiments on 8 datasets show promising results on image reconstruction and significant improvement on clustering and classification.

SOLD: Sub-optimal low-rank decomposition for efficient video segmentation

This paper investigates how to perform robust and efficient unsupervised video segmentation while suppressing the effects of data noises and/or corruptions. We propose a general algorithm, called Sub-Optimal Low-rank Decomposition (SOLD), which pursues the low-rank representation for video segmentation. Given the supervoxels affinity matrix of an observed video sequence, SOLD seeks a sub-optimal solution by making the matrix rank explicitly determined. In particular, the affinity matrix with the rank fixed can be decomposed into two sub-matrices of low rank, and then we iteratively optimize them with closed-form solutions. Moreover, we incorporate a discriminative replication prior into our framework based on the obervation that small-size video patterns tend to recur frequently within the same object. The video can be segmented into several spatio-temporal regions by applying the Normalized-Cut (NCut) algorithm with the solved low-rank representation. To process the streaming videos, we apply our algorithm sequentially over a batch of frames over time, in which we also develop several temporal consistent constraints improving the robustness. Extensive experiments on the public benchmarks demonstrate superior performance of our framework over other state-of-the-art approaches.

Learning Collaborative Sparse Representation for Grayscale-Thermal Tracking

Integrating multiple different yet complementary feature representations has been proved to be an effective way for boosting tracking performance. This paper investigates how to perform robust object tracking in challenging scenarios by adaptively incorporating information from grayscale and thermal videos, and proposes a novel collaborative algorithm for online tracking. In particular, an adaptive fusion scheme is proposed based on collaborative sparse representation in Bayesian filtering framework. We jointly optimize sparse codes and the reliable weights of different modalities in an online way. In addition, this paper contributes a comprehensive video benchmark, which includes 50 grayscale-thermal sequences and their ground truth annotations for tracking purpose. The videos are with high diversity and the annotations were finished by one single person to guarantee consistency. Extensive experiments against other state-of-the-art trackers with both grayscale and grayscale-thermal inputs demonstrate the effectiveness of the proposed tracking approach. Through analyzing quantitative results, we also provide basic insights and potential future research directions in grayscale-thermal tracking.Integrating multiple different yet complementary feature representations has been proved to be an effective way for boosting tracking performance. This paper investigates how to perform robust object tracking in challenging scenarios by adaptively incorporating information from grayscale and thermal videos, and proposes a novel collaborative algorithm for online tracking. In particular, an adaptive fusion scheme is proposed based on collaborative sparse representation in Bayesian filtering framework. We jointly optimize sparse codes and the reliable weights of different modalities in an online way. In addition, this paper contributes a comprehensive video benchmark, which includes 50 grayscale-thermal sequences and their ground truth annotations for tracking purpose. The videos are with high diversity and the annotations were finished by one single person to guarantee consistency. Extensive experiments against other state-of-the-art trackers with both grayscale and grayscale-thermal inputs demonstrate the effectiveness of the proposed tracking approach. Through analyzing quantitative results, we also provide basic insights and potential future research directions in grayscale-thermal tracking.

Weighted Low-Rank Decomposition for Robust Grayscale-Thermal Foreground Detection

This paper investigates how to fuse grayscale and thermal video data for detecting foreground objects in challenging scenarios. To this end, we propose an intuitive yet effective method called weighted low-rank decomposition (WELD), which adaptively pursues the cross-modality low-rank representation. Specifically, we form two data matrices by accumulating sequential frames from the grayscale and the thermal videos, respectively. Within these two observing matrices, WELD detects moving foreground pixels as sparse outliers against the low-rank structure background and incorporates the weight variables to make the models of two modalities complementary to each other. The smoothness constraints of object motion are also introduced in WELD to further improve the robustness to noises. For optimization, we propose an iterative algorithm to efficiently solve the low-rank models with three subproblems. Moreover, we utilize an edge-preserving filtering-based method to substantially speed up WELD while preserving its accuracy. To provide a comprehensive evaluation benchmark of grayscale-thermal foreground detection, we create a new data set including 25 aligned grayscale-thermal video pairs with high diversity. Our extensive experiments on both the newly created data set and the public data set OSU3 suggest that WELD achieves superior performance and comparable efficiency against other state-of-the-art approaches.

An Approach to Streaming Video Segmentation With Sub-Optimal Low-Rank Decomposition

This paper investigates how to perform robust and efficient video segmentation while suppressing the effects of data noises and/or corruptions, and an effective approach is introduced to this end. First, a general algorithm, called sub-optimal low-rank decomposition (SOLD), is proposed to pursue the low-rank representation for video segmentation. Given the data matrix formed by supervoxel features of an observed video sequence, SOLD seeks a sub-optimal solution by making the matrix rank explicitly determined. In particular, the representation coefficient matrix with the fixed rank can be decomposed into two sub-matrices of low rank, and then we iteratively optimize them with closed-form solutions. Moreover, we incorporate a discriminative replication prior into SOLD based on the observation that small-size video patterns tend to recur frequently within the same object. Second, based on SOLD, we present an efficient inference algorithm to perform streaming video segmentation in both unsupervised and interactive scenarios. More specifically, the constrained normalized-cut algorithm is adopted by incorporating the low-rank representation with other low level cues and temporal consistent constraints for spatio-temporal segmentation. Extensive experiments on two public challenging data sets VSB100 and SegTrack suggest that our approach outperforms other video segmentation approaches in both accuracy and efficiency.

A sparse nonnegative matrix factorization technique for graph matching problems

Graph matching problem that incorporates pairwise constraints can be cast as an Integer Quadratic Programming (IQP). Since it is NP-hard, approximate methods are required. In this paper, a new approximate method based on nonnegative matrix factorization with sparse constraints is presented. Firstly, the graph matching is formulated as an optimization problem with nonnegative and sparse constraints, followed by an efficient algorithm to solve this constrained problem. Then, we show the strong relationship between the sparsity of the relaxation solution and its effectiveness for graph matching based on our model. A key benefit of our method is that the solution is sparse and thus can approximately impose the one-to-one mapping constraints in the optimization process naturally. Therefore, our method can approximate the original IQP problem more closely than other approximate methods. Extensive and comparative experimental results on both synthetic and real-world data demonstrate the effectiveness of our graph matching method. We present a graph matching method based on NMF with sparse constraints.Our sparse model can incorporate the mapping constraints approximately.We show the link between the sparsity of the solution and its effectiveness.Experimental results show the effectiveness of our graph matching method.

Graph structure analysis based on complex network

In this paper, we propose a novel method to characterize graph structures based on complex network model. First, we show that a structural graph can be modeled as a small-world complex network, and, then, Complex Network Characteristics (including topological and dynamic characteristics) Representation of a Graph (CNCRG) is obtained. Based on these characteristics, graph classification/clustering for objects viewed from different directions and characteristic views identification for single objects are investigated on one synthetic image dataset and two real image datasets. Our experimental results showed that CNCRG achieves better object classification/clustering performance and also provides well-structured view spaces based on multi-dimensional scaling (MDS) and principal component analysis (PCA) embedding methods for graphs extracted from 2D views of 3D objects.

Robust Feature Point Matching With Sparse Model

Feature point matching that incorporates pairwise constraints can be cast as an integer quadratic programming (IQP) problem. Since it is NP-hard, approximate methods are required. The optimal solution for IQP matching problem is discrete, binary, and thus sparse in nature. This motivates us to use sparse model for feature point matching problem. The main advantage of the proposed sparse feature point matching (SPM) method is that it generates sparse solution and thus naturally imposes the discrete mapping constraints approximately in the optimization process. Therefore, it can optimize the IQP matching problem in an approximate discrete domain. In addition, an efficient algorithm can be derived to solve SPM problem. Promising experimental results on both synthetic points sets matching and real-world image feature sets matching tasks show the effectiveness of the proposed feature point matching method.

Real-Time Grayscale-Thermal Tracking via Laplacian Sparse Representation

Grayscale and thermal data can complement to each other to improve tracking performance in some challenging scenarios. In this paper, we propose a real-time online grayscale-thermal tracking method via Laplacian sparse representation in Bayesian filtering framework. Specifically, a generative multimodal feature model is induced by the Laplacian sparse representation, which makes the best use of similarities among local patches to refine their sparse codes, so that different source data can be seamlessly fused for object tracking. In particular, the multimodal feature model encodes both the spatial local information and occlusion handling to improve its robustness. With such feature representation, the confidence of each candidate is computed by the sparse feature similarity with the object template. Given the motion model, object tracking is then carried out in Bayesian filtering framework by maximizing the observation likelihood, i.e., finding the candidate with highest confidence. In addition, to achieve real-time demand in related visual information processing systems, we adopt the reverse representation and the parallel computation to improve tracking efficiency. Extensive experiments on both public and collected grayscale-thermal video sequences demonstrate accuracy and efficiency of the proposed method against other state-of-the-art sparse representation based trackers.