Chang Tang

Bio: Chang Tang is an academic researcher from China University of Geosciences (Wuhan). The author has contributed to research in topics: Cluster analysis & Graph (abstract data type). The author has an hindex of 25, co-authored 67 publications receiving 2034 citations. Previous affiliations of Chang Tang include Information Technology University & Tianjin University.

Robust graph regularized unsupervised feature selection

Abstract: Recent research indicates the critical importance of preserving local geometric structure of data in unsupervised feature selection (UFS), and the well studied graph Laplacian is usually deployed to capture this property. By using a squared l2-norm, we observe that conventional graph Laplacian is sensitive to noisy data, leading to unsatisfying data processing performance. To address this issue, we propose a unified UFS framework via feature self-representation and robust graph regularization, with the aim at reducing the sensitivity to outliers from the following two aspects: i) an l2, 1-norm is used to characterize the feature representation residual matrix; and ii) an l1-norm based graph Laplacian regularization term is adopted to preserve the local geometric structure of data. By this way, the proposed framework is able to reduce the effect of noisy data on feature selection. Furthermore, the proposed l1-norm based graph Laplacian is readily extendible, which can be easily integrated into other UFS methods and machine learning tasks with local geometrical structure of data being preserved. As demonstrated on ten challenging benchmark data sets, our algorithm significantly and consistently outperforms state-of-the-art UFS methods in the literature, suggesting the effectiveness of the proposed UFS framework.

Consensus learning guided multi-view unsupervised feature selection

Abstract: Multi-view unsupervised feature selection has been proven to be an effective approach to reduce the dimensionality of multi-view data. One of its key issues is how to exploit the underlying common structures across different views. In this paper, we propose a consensus learning guided multi-view unsupervised feature selection method, which embeds multi-view feature selection into a non-negative matrix factorization based clustering with sparse constrain. The proposed method learns latent feature matrices from all the views, and optimizes a consensus matrix such that the difference between the cluster indicator matrix of each view and the consensus matrix is minimized. The parameters for balancing the weights of different views are automatically adjusted, and a sparse constraint is imposed on the latent feature matrices to perform feature selection. After that, we design an effective iterative algorithm to solve the resultant optimization problem. Extensive experiments have been conducted on six publicly multi-view datasets, and the results demonstrate that the proposed algorithm outperforms several other state-of-the-art single view and multi-view unsupervised feature selection methods in terms of clustering tasks, validating the effectiveness of the proposed multi-view unsupervised feature selection method. The source code of our algorithm will be available on our on-line page: http://tangchang.net/ .

DeFusionNET: Defocus Blur Detection via Recurrently Fusing and Refining Multi-Scale Deep Features

Abstract: Defocus blur detection aims to detect out-of-focus regions from an image. Although attracting more and more attention due to its widespread applications, defocus blur detection still confronts several challenges such as the interference of background clutter, sensitivity to scales and missing boundary details of defocus blur regions. To deal with these issues, we propose a deep neural network which recurrently fuses and refines multi-scale deep features (DeFusionNet) for defocus blur detection. We firstly utilize a fully convolutional network to extract multi-scale deep features. The features from bottom layers are able to capture rich low-level features for details preservation, while the features from top layers can characterize the semantic information to locate blur regions. These features from different layers are fused as shallow features and semantic features, respectively. After that, the fused shallow features are propagated to top layers for refining the fine details of detected defocus blur regions, and the fused semantic features are propagated to bottom layers to assist in better locating the defocus regions. The feature fusing and refining are carried out in a recurrent manner. Also, we finally fuse the output of each layer at the last recurrent step to obtain the final defocus blur map by considering the sensitivity to scales of the defocus degree. Experiments on two commonly used defocus blur detection benchmark datasets are conducted to demonstrate the superority of DeFusionNet when compared with other 10 competitors. Code and more results can be found at: http://tangchang.net

Salient Object Detection via Weighted Low Rank Matrix Recovery

Abstract: Image-based salient object detection is a useful and important technique, which can promote the efficiency of several applications such as object detection, image classification/retrieval, object co-segmentation, and content-based image editing. In this letter, we present a novel weighted low-rank matrix recovery (WLRR) model for salient object detection. In order to facilitate efficient salient objects-background separation, a high-level background prior map is estimated by employing the property of the color, location, and boundary connectivity, and then this prior map is ensembled into a weighting matrix which indicates the likelihood that each image region belongs to the background. The final salient object detection task is formulated as the WLRR model with the weighting matrix. Both quantitative and qualitative experimental results on three challenging datasets show competitive results as compared with 24 state-of-the-art methods.

Deep Convolutional Neural Networks for Action Recognition Using Depth Map Sequences

Abstract: Recently, deep learning approach has achieved promising results in various fields of computer vision. In this paper, a new framework called Hierarchical Depth Motion Maps (HDMM) + 3 Channel Deep Convolutional Neural Networks (3ConvNets) is proposed for human action recognition using depth map sequences. Firstly, we rotate the original depth data in 3D pointclouds to mimic the rotation of cameras, so that our algorithms can handle view variant cases. Secondly, in order to effectively extract the body shape and motion information, we generate weighted depth motion maps (DMM) at several temporal scales, referred to as Hierarchical Depth Motion Maps (HDMM). Then, three channels of ConvNets are trained on the HDMMs from three projected orthogonal planes separately. The proposed algorithms are evaluated on MSRAction3D, MSRAction3DExt, UTKinect-Action and MSRDailyActivity3D datasets respectively. We also combine the last three datasets into a larger one (called Combined Dataset) and test the proposed method on it. The results show that our approach can achieve state-of-the-art results on the individual datasets and without dramatical performance degradation on the Combined Dataset.

NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis

Abstract: Recent approaches in depth-based human activity analysis achieved outstanding performance and proved the effectiveness of 3D representation for classification of action classes. Currently available depth-based and RGB+D-based action recognition benchmarks have a number of limitations, including the lack of training samples, distinct class labels, camera views and variety of subjects. In this paper we introduce a large-scale dataset for RGB+D human action recognition with more than 56 thousand video samples and 4 million frames, collected from 40 distinct subjects. Our dataset contains 60 different action classes including daily, mutual, and health-related actions. In addition, we propose a new recurrent neural network structure to model the long-term temporal correlation of the features for each body part, and utilize them for better action classification. Experimental results show the advantages of applying deep learning methods over state-of-the-art hand-crafted features on the suggested cross-subject and cross-view evaluation criteria for our dataset. The introduction of this large scale dataset will enable the community to apply, develop and adapt various data-hungry learning techniques for the task of depth-based and RGB+D-based human activity analysis.

NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis

Abstract: Recent approaches in depth-based human activity analysis achieved outstanding performance and proved the effectiveness of 3D representation for classification of action classes. Currently available depth-based and RGB+Dbased action recognition benchmarks have a number of limitations, including the lack of training samples, distinct class labels, camera views and variety of subjects. In this paper we introduce a large-scale dataset for RGB+D human action recognition with more than 56 thousand video samples and 4 million frames, collected from 40 distinct subjects. Our dataset contains 60 different action classes including daily, mutual, and health-related actions. In addition, we propose a new recurrent neural network structure to model the long-term temporal correlation of the features for each body part, and utilize them for better action classification. Experimental results show the advantages of applying deep learning methods over state-of-the-art handcrafted features on the suggested cross-subject and crossview evaluation criteria for our dataset. The introduction of this large scale dataset will enable the community to apply, develop and adapt various data-hungry learning techniques for the task of depth-based and RGB+D-based human activity analysis.

Recent Advances in Convolutional Neural Networks

Abstract: In the last few years, deep learning has led to very good performance on a variety of problems, such as visual recognition, speech recognition and natural language processing. Among different types of deep neural networks, convolutional neural networks have been most extensively studied. Leveraging on the rapid growth in the amount of the annotated data and the great improvements in the strengths of graphics processor units, the research on convolutional neural networks has been emerged swiftly and achieved state-of-the-art results on various tasks. In this paper, we provide a broad survey of the recent advances in convolutional neural networks. We detailize the improvements of CNN on different aspects, including layer design, activation function, loss function, regularization, optimization and fast computation. Besides, we also introduce various applications of convolutional neural networks in computer vision, speech and natural language processing.

Measuring statistical dependence with Hilbert-Schmidt norms

Abstract: We propose an independence criterion based on the eigen-spectrum of covariance operators in reproducing kernel Hilbert spaces (RKHSs), consisting of an empirical estimate of the Hilbert-Schmidt norm of the cross-covariance operator (we term this a Hilbert-Schmidt Independence Criterion, or HSIC). This approach has several advantages, compared with previous kernel-based independence criteria. First, the empirical estimate is simpler than any other kernel dependence test, and requires no user-defined regularisation. Second, there is a clearly defined population quantity which the empirical estimate approaches in the large sample limit, with exponential convergence guaranteed between the two: this ensures that independence tests based on HSIC do not suffer from slow learning rates. Finally, we show in the context of independent component analysis (ICA) that the performance of HSIC is competitive with that of previously published kernel-based criteria, and of other recently published ICA methods.