Search

As an innovative technology for the stimulation of coalbed methane, liquid nitrogen cold soaking can produce more fractures in coal body and effectively increase the permeability of coal seam. The pore structure distribution of coal affects the permeability of coal and determines the flow and occurrence state of coalbed methane and other fluids in coal. This paper carries out a number of nuclear magnetic resonance tests on coal samples with different coal qualities treated by liquid nitrogen cold soaking and studies the influence law of liquid nitrogen soaking on coal pore structures. It is found that the liquid nitrogen makes the T2 spectral peak shifts to the right, and the anthracite changes from interval T2 spectrum to type T2. It indicates that liquid nitrogen cold soaking in the transformation of pore size to large size improves the pore connectivity and leads to more pore structures. With an increase in times of liquid nitrogen cold soaking, the size and number of coal pore structures gradually increase, and the increasing size is on the order of anthracite > bituminous > lignite. There is a positive correlation between the peak area and the times of liquid nitrogen cold soaking. The porosity and permeability of each coal sample increase with the times of liquid nitrogen cold soaking. From the MRI images of coal samples, it can be found that the liquid nitrogen cold soaking makes the microcracks extend and forms a crack network with other cracks, thereby causing macroscopic damage. The research results are helpful to further reveal the microscopic mechanism of liquid nitrogen cold soaking on coal damage. [ABSTRACT FROM AUTHOR]

Dimension reduction is a critical technology for high-dimensional data processing, where Linear Discriminant Analysis (LDA) and its variants are effective supervised methods. However, LDA prefers to feature with smaller variance, which causes feature with weak discriminative ability retained. In this paper, we propose a novel Ratio Sum for Linear Discriminant Analysis (RSLDA), which aims at maximizing discriminative ability of each feature in subspace. To be specific, it maximizes the sum of ratio of the between-class distance to the within-class distance in each dimension of subspace. Since the original RSLDA problem is difficult to obtain the closed solution, an equivalent problem is developed which can be solved by an alternative optimization algorithm. For solving the equivalent problem, it is transformed into two sub-problems, one of which can be solved directly, the other is changed into a convex optimization problem, where singular value decomposition is employed instead of matrix inversion. Consequently, performance of algorithm cannot be affected by the non-singularity of covariance matrix. Furthermore, Kernel RSLDA (KRSLDA) is presented to improve the robustness of RSLDA. Additionally, time complexity of RSLDA and KRSLDA are analyzed. Extensive experiments show that RSLDA and KRSLDA outperforms other comparison methods on toy datasets and multiple public datasets. [ABSTRACT FROM AUTHOR]

Linear discriminant analysis (LDA) has been proven to be effective in dimensionality reduction. However, the performance of LDA depends on the consistency assumption of the global structure and the local structure. Some work extended LDA along this line of research and proposed local formulations of LDA. Unfortunately, the learning scheme of these algorithms is suboptimal in that the intrinsic relationship between data points is pre-learned in the original space, which is usually affected by the noise and redundant features. Besides, the time cost is relatively high. To alleviate these drawbacks, we propose a Fast Locality Discriminant Analysis framework (FLDA), which has three advantages: (1) It can divide a non-Gaussian distribution class into many sub-blocks that obey Gaussian distributions by using the anchor-based strategy. (2) It captures the manifold structure of data by learning the fuzzy membership relationship between data points and the corresponding anchor points, which can reduce computation time. (3) The weights between data points and anchor points are adaptively updated in the subspace where the irrelevant information and the noise in high-dimensional space have been effectively suppressed. Extensive experiments on toy data sets, UCI benchmark data sets and imbalanced data sets demonstrate the efficiency and effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Linear discriminant analysis (LDA) has been proven to be effective in dimensionality reduction. However, the performance of LDA depends on the consistency assumption of the global structure and the local structure. Some work extended LDA along this line of research and proposed local formulations of LDA. Unfortunately, the learning scheme of these algorithms is suboptimal in that the intrinsic relationship between data points is pre-learned in the original space, which is usually affected by the noise and redundant features. Besides, the time cost is relatively high. To alleviate these drawbacks, we propose a Fast Locality Discriminant Analysis framework (FLDA), which has three advantages: (1) It can divide a non-Gaussian distribution class into many sub-blocks that obey Gaussian distributions by using the anchor-based strategy. (2) It captures the manifold structure of data by learning the fuzzy membership relationship between data points and the corresponding anchor points, which can reduce computation time. (3) The weights between data points and anchor points are adaptively updated in the subspace where the irrelevant information and the noise in high-dimensional space have been effectively suppressed. Extensive experiments on toy data sets, UCI benchmark data sets and imbalanced data sets demonstrate the efficiency and effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Dimension reduction is a critical technology for high-dimensional data processing, where Linear Discriminant Analysis (LDA) and its variants are effective supervised methods. However, LDA prefers to feature with smaller variance, which causes feature with weak discriminative ability retained. In this paper, we propose a novel Ratio Sum for Linear Discriminant Analysis (RSLDA), which aims at maximizing discriminative ability of each feature in subspace. To be specific, it maximizes the sum of ratio of the between-class distance to the within-class distance in each dimension of subspace. Since the original RSLDA problem is difficult to obtain the closed solution, an equivalent problem is developed which can be solved by an alternative optimization algorithm. For solving the equivalent problem, it is transformed into two sub-problems, one of which can be solved directly, the other is changed into a convex optimization problem, where singular value decomposition is employed instead of matrix inversion. Consequently, performance of algorithm cannot be affected by the non-singularity of covariance matrix. Furthermore, Kernel RSLDA (KRSLDA) is presented to improve the robustness of RSLDA. Additionally, time complexity of RSLDA and KRSLDA are analyzed. Extensive experiments show that RSLDA and KRSLDA outperforms other comparison methods on toy datasets and multiple public datasets. [ABSTRACT FROM AUTHOR]

Our social interactions vary over time and they depend on various factors that determine our preferences and goals, both in personal and professional terms. Researches have shown that this plays an important role in promoting cooperation and prosocial behavior in general. Indeed, it is natural to assume that ties among cooperators would become stronger over time, while ties with defectors (non-cooperators) would eventually be severed. Here we introduce reinforcement learning as a determinant of adaptive interaction intensity in social dilemmas and study how this translates into the structure of the social network and its propensity to sustain cooperation. We merge the iterated prisoner's dilemma game with the Bush-Mostelle reinforcement learning model and show that there exists a moderate switching dynamics of the interaction intensity that is optimal for the evolution of cooperation. Besides, the results of Monte Carlo simulations are further supported by the calculations of dynamical pair approximation. These observations show that reinforcement learning is sufficient for the emergence of optimal social interaction patterns that facilitate cooperation. This in turn supports the social capital hypothesis with a minimal set of assumptions that guide the self-organization of our social fabric. [ABSTRACT FROM AUTHOR]

Binarized neural networks (BNNs) have drawn significant attention in recent years, owing to great potential in reducing computation and storage consumption. While it is attractive, traditional BNNs usually suffer from slow convergence speed and dramatical accuracy-degradation on large-scale classification datasets. To minimize the gap between BNNs and deep neural networks (DNNs), we propose a new framework of designing BNNs, dubbed Hyper-BinaryNet, from the aspect of enhanced information-flow. Our contributions are threefold: 1) Considering the capacity-limitation in the backward pass, we propose an 1-bit convolution module named HyperConv. By exploiting the capacity of auxiliary neural networks, BNNs gain better performance on large-scale image classification task. 2) Considering the slow convergence speed in BNNs, we rethink the gradient accumulation mechanism and propose a hyper accumulation technique. By accumulating gradients in multiple variables rather than one as before, the gradient paths for each weight increase, which escapes BNNs from the gradient bottleneck problem during training. 3) Considering the ill-posed optimization problem, a novel gradient estimation warmup strategy, dubbed STE-Warmup, is developed. This strategy prevents BNNs from the unstable optimization process by progressively transferring neural networks from 32-bit to 1-bit. We conduct evaluations with variant architectures on three public datasets: CIFAR-10/100 and ImageNet. Compared with state-of-the-art BNNs, Hyper-BinaryNet shows faster convergence speed and outperforms existing BNNs by a large margin. [ABSTRACT FROM AUTHOR]

• The rock layer between the two coal seams is affected by repeated mining and is prone to rotation instability. • Based on the "block-dispersions" theory, the structure and failure process of the roof of the roadway under the gob is analyzed. • The floor stress distribution law after mining in the upper coal seam is calculated according to the elastic theory. With the increase in energy demand and in mining intensity, the phenomenon of multiple coal seam mining has appeared in major coal mining countries. While the downward mining method is generally adopted and under the damage of the upper coal seam, the structure and stress environment of the coal roof are very different from those of a single coal seam in remining. The rock layer between the two coal seams is affected by repeated mining and is prone to rotation instability, which makes it more difficult to reserve gob-side entries along the gob in the lower coal seams. This article mainly targets the case of the gob in the Panel #11426 of Xieqiao Mine, and studies the failure mechanism and control technology of the gob-side entry retaining in short-distance coal seam. First, the floor stress distribution law after mining in the upper coal seam is calculated according to the elastic theory, and verified by FLAC3D numerical simulation; secondly, the floor failure depth after the upper coal seam is calculated according to the elastic–plastic theory. Based on the "block-dispersions" structure, the failure process of the roof of the roadway under close gob is analyzed. Further, it is proposed during the roadway excavation, to adopt support methods such as erecting U-steel retractable supports and back-wall filling; during the mining and before the gob-side entry retaining, the installation of roof bolts (cables), the reinforcement of the roof of the area to be filled and the in-wall filling techniques etc. to control the surrounding rock of gob-side entry. The engineering test was carried out along the track at the Panel #11426 of Xieqiao Mine. The onsite monitoring showed that: the maximum subsidence of the reserved gob-side entry roof along the gob was 180 mm, and the maximum approaching distance of the two banks was 328 mm, which met the engineering requirements. The research results can provide guidance for the design gob-side entry retaining along gobs under similar mining geological conditions. [ABSTRACT FROM AUTHOR]

Linear Discriminant Analysis (LDA) is one of the most representative supervised robust dimensionality reduction methods for handling high-dimensional data. High-dimensional datasets tend to contain more outliers and other sorts of noise, whereas most of the existing LDA models incorrectly consider the arithmetic mean of samples as the optimal mean, leading to the deviation of the data mean and thus reduce the robustness of LDA. In this paper, we propose a novel robust trace ratio objective in which the calculation of the difference between sample and class mean is converted to the calculation of the difference between each pair of samples. Besides, the within-class scatter and the total scatter are measured by capped ℓ p -norm. As a result, this novel reformulation can automatically avoid mean calculation and meanwhile mitigate the negative effect of outliers on the objective function. Furthermore, an iterative optimization algorithm is derived to obtain the solution of the model. Extensive experimental results on several benchmark datasets show the superior performance of the proposed method. [ABSTRACT FROM AUTHOR]

Cooperative behavior is essential for conflicts between collective and individual benefits, and evolutionary game theory provides a key framework to solve this problem. Decision-making of human or automata agent occurs not only in a static environment, but also in the dynamic interactive environment. Since the reinforcement learning algorithm is well performed at explaining the problem in regard to state, action, and environment, we propose a game model with individual state transition which is influenced by the self-regarding Q -learning algorithm. In detail, we at the first time investigate a two-state two-action game, where agents can choose either to participate in the network game (i.e., active agent) or to cut off all the links based on its Q -table (i.e., inactive agent), involving in a dynamic interactive environment. Through numerical simulations, it is shown that cooperation can reach the maximal level in the moderate value space of fixed reward obtained by inactive agents. In particular, long-term expectations and large learning rates are more productive in promoting cooperation. Furthermore, when the dynamic interactive environment reaches a stable state, the number of active neighbors of active cooperators is larger than that of active defectors, which is further larger than the number of active neighbors of inactive agents. Finally, we testify the results of theoretical analysis from the perspective of state transition. [ABSTRACT FROM AUTHOR]

Semi-supervised learning as one of most attractive problems in machine learning research field has aroused broad attentions in recent years. In this paper, we propose a novel locality preserved dimensionality reduction framework, named Semi-supervised Adaptive Local Embedding learning (SALE), which learns a local discriminative embedding by constructing a $k_1$ k 1 Nearest Neighbors ($k_1$ k 1 NN) graph on labeled data, so as to explore the intrinsic structure, i.e., sub-manifolds from non-Gaussian labeled data. Then, mapping all samples into learned embedding and constructing another $k_2$ k 2 NN graph on all embedded data to explore the global structure of all samples. Therefore, the unlabeled data and their corresponding labeled neighbors can be clustered into same sub-manifold, so as to improve the discriminative power of embedded data. Furthermore, we propose two semi-supervised dimensionality reduction methods with orthogonal and whitening constraints based on proposed SALE framework. An efficient alternatively iterative optimization algorithm is developed to solve the NP-hard problem in our models. Extensive experiments conducted on several synthetic and real-world data sets demonstrate the superiorities of our methods on local structure exploration and classification task. [ABSTRACT FROM AUTHOR]

Detecting objects and providing their 2D information (e.g., size and center) are crucial for outdoor visual surveillance. Because the cameras are static and their distances to background are fixed in the scenario of surveillance, we argue that, compared to 3D object detection, 2D object detection is usually enough in visual surveillance. To a great extent, determining the existence of objects is more important than determining their precise 3D shapes and locations. In the field of visual surveillance, almost all methods employ a single camera (or independently employing several cameras) to determine the existence and 2D information of objects. In this paper, we propose to improve the performance of the 2D object detection by binocular cameras (images) for the scenario of outdoor surveillance where RGB-D and depth cameras are not applicable due to their low resolutions and high expense. In the proposed binocular-image based 2D object detection framework, most of existing monocular-image based 2D object detection modules can be integrated in. Once integrated in the proposed framework, the object detection accuracy can significantly and consistently be improved. Experimental results on the challenging datasets of Cityscapes and KITTI demonstrate the superiority of the proposed method. [ABSTRACT FROM AUTHOR]

Semi-supervised feature selection alleviates the annotation burden of supervised feature learning by exploiting data under a handful of supervision information. The mainstream technique is to employ a linear regression framework that jointly learns labeled and unlabeled samples. However, existing approaches always encounter the deficiencies in two aspects: 1) the performance of models are severely degenerated once predicted labels are unreliable; 2) the balance of objectives in regards to two types of data are not well considered. In the article, we propose unified dual-label semi-supervised learning for top- k feature selection. The technique defines a soft label matrix to indicate the probability of samples belonging to each class. From the probability, the model could recognize unclassifiable samples that lay around the boundaries. Meanwhile, the label matrix is equipped with an exponent parameter γ. It endows the soft labels dual effects that the labeled and unlabeled data are tactfully discriminated. For the purpose of feature selection, we impose the ℓ 2 , 0 -norm constraint on the projection matrix, such that the exact top- k features are picked out. An iteration algorithm is designed to solve the given problem, by which large-scale data are facilely tackled. We conduct experiments that validate the superiority of the proposed method against the state-of-the-art competitors. [ABSTRACT FROM AUTHOR]

Scoliosis is a disease caused by deformation of the spine, and precise imaging of human spine tissues is crucial and instructive for the subsequent treatment. Currently, radiographs are clinically used to monitor disease progress. However, radiation exposure is a safety concern and is undesirable for regular monitoring during rehabilitation intervention. In this study, we developed a novel technique to generate the 3D structure of human spine from a tracked freehand ultrasound scanning. First of all, we designed an approach for detection and location of every vertebra in the spine by firstly detecting the vertebral landmarks from the ultrasound B-scan sequence, then computing the size, location and posture of every vertebra and finally using a method of interpolation to form the whole spine according to the prior knowledge of vertebral anatomical structure. Deep learning based object detection methods were used to find the landmarks of the vertebrae, and those landmarks were then clustered to model every vertebra (i.e. computing its location, posture and real size). Due to the situations where the vertebra is not clearly seen, we therefore used the technique of interpolation to estimate the location of those missing vertebrae with respect to the anatomical prior. In addition, we reconnected all vertebral models and reappeared the whole spine in 3D space. With that, the Cobb angle could be easily measured. The phantom and in vivo experiments were also conducted to further verify the precision of the proposed approaches. The results have demonstrated its feasibility in the clinical practice of adolescent idiopathic scoliosis patients (R 2 = 0. 9780 ,p < 0. 001), which is beneficial for the regular quantitative monitoring of disease progression. [ABSTRACT FROM AUTHOR]

The kernel principal component analysis (KPCA) serves as an efficient approach for dimensionality reduction. However, the KPCA method is sensitive to the outliers since the large square errors tend to dominate the loss of KPCA. To strengthen the robustness of KPCA method, we propose a novel robust kernel principal component analysis with optimal mean (RKPCA-OM) method. RKPCA-OM not only possesses stronger robustness for outliers than the conventional KPCA method, but also can eliminate the optimal mean automatically. What is more, the theoretical proof proves the convergence of the algorithm to guarantee that the optimal subspaces and means are obtained. Lastly, exhaustive experimental results verify the superiority of our method. [ABSTRACT FROM AUTHOR]

Deep neural networks (DNNs) have now demonstrated state-of-the-art detection performance on pedestrian datasets. However, because of their high computational complexity, detection efficiency is still a frustrating problem even with the help of Graphics Processing Units (GPUs). To improve detection efficiency, this paper proposes to share features across a group of DNNs that correspond to pedestrian models of different sizes. By sharing features, the computational burden for extracting features from an image pyramid can be significantly reduced. Simultaneously, we can detect pedestrians of several different scales on one single layer of an image pyramid. Furthermore, the improvement of detection efficiency is achieved with negligible loss of detection accuracy. Experimental results demonstrate the robustness and efficiency of the proposed algorithm. [ABSTRACT FROM AUTHOR]

Effective representation of image texture is important for an image-classification task. Statistical modelling in wavelet domains has been widely used to image texture representation. However, due to the intraclass complexity and interclass diversity of textures, it is hard to use a predefined probability distribution function to fit adaptively all wavelet subband coefficients of different textures. In this article, we propose a novel modelling approach, Heterogeneous and Incrementally Generated Histogram (HIGH), to indirectly model the wavelet coefficients by use of four local features in wavelet subbands. By concatenating all the HIGHs in all wavelet subbands of a texture, we can construct a nonnegative multiresolution vector (NMV) to represent a texture image. Considering the NMV’s high dimensionality and nonnegativity, we further propose a Hessian regularized discriminative nonnegative matrix factorization to compute a low-dimensional basis of the linear subspace of NMVs. Finally, we present a texture classification approach by projecting NMVs on the low-dimensional basis. Experimental results show that our proposed texture classification method outperforms seven representative approaches. [ABSTRACT FROM AUTHOR]

Dense feature extraction is becoming increasingly popular in face recognition tasks. Systems based on this approach have demonstrated impressive performance in a range of challenging scenarios. However, improvements in discriminative power come at a computational cost and with a risk of over-fitting. In this paper, we propose a new approach to dense feature extraction for face recognition, which consists of two steps. First, an encoding scheme is devised that compresses high-dimensional dense features into a compact representation by maximizing the intrauser correlation. Second, we develop an adaptive feature matching algorithm for effective classification. This matching method, in contrast to the previous methods, constructs and chooses a small subset of training samples for adaptive matching, resulting in further performance gains. Experiments using several challenging face databases, including labeled Faces in the Wild data set, Morph Album 2, CUHK optical-infrared, and FERET, demonstrate that the proposed approach consistently outperforms the current state of the art. [ABSTRACT FROM AUTHOR]

In order to analyze system performance and develop model-based control algorithms for turbocharged spark ignition and direct injection (SIDI) gasoline engines, a control oriented mean value model is developed and validated. The model is constructed based on theoretical analysis for the different components, including the compressor, turbine, air filter, intercooler, throttle, manifold, and combustion chamber. Compressor mass flow and efficiency are modeled as parameterized functions. A standard nozzle model is used to approximate the mass flow through the turbine, and the turbine efficiency is modeled as a function of blade speed ratio (BSR). The air filter is modeled as a tube for capturing its pressure drop feature. The effectiveness number of transfer units (NTU) modeling method is utilized for the intercooler. The throttle model consists of the standard nozzle model with an effective area regressed to throttle position. Manifolds are modeled for their dynamically varying pressure state. For the cylinder, the air mass flow into cylinders, fuel mass, torque, and exhaust temperature are modeled. Compared to the conventional lookup table approach, transient dynamics error can be improved significantly through using the model from this work. [ABSTRACT FROM AUTHOR]

Bridging visual and textual representations plays a central role in delving into multimedia data understanding. The main challenge arises from that images and texts exist in heterogeneous spaces, leading to the difficulty to preserve the semantic consistency between both modalities. To narrow the modality gap, most recent methods resort to extra object detectors or parsers to obtain the hierarchical representations. In this work, we address this problem by introducing our Multi-Task Hierarchical Convolutional Neural Network (MT-HCN). It is characterized by mining the hierarchical semantic information without the aid of any extra supervisions. Firstly, from the perspective of representing architecture, we leverage the intrinsic hierarchical structure of Convolutional Neural Networks (CNNs) to decompose the representations of both modalities into two semantically complementary levels, i.e. , exterior representations and concept representations. The former focuses on discovering the fine-grained low-level associations between both modalities, meanwhile the latter underlines capturing more high-level abstract semantics. Specifically, we present a Self-Supervised Clustering (SSC) loss to preserve more fine-grained semantic clues in exterior representations. It is constituted on the basis of viewing multiple image/text pairs with similar exterior as a category. In addition, a novel harmonious bidirectional triplet ranking (HBTR) loss is proposed, which mitigate the adverse effects brought about by the biased and noisy negative samples. Besides hardest negatives, it also imposes the constraints on the distance between the positive pairs and the centroid of negative pairs. Extensive experimental results on two popular cross-modal retrieval benchmarks demonstrate our proposed MT-HCN can achieve the competitive results compared with the state-of-the-art methods. • This paper proposes a novel Multi-Task Hierarchical Convolutional Network (MT-HCN) for visual-semantic cross-modal retrieval, which is characterized by adopting classification task to improve the hierarchical multi-modal representation learning. • This paper proposes a novel Self-Supervision Clustering (SSC) loss to learn the exterior representations that fully exploits low-level fine-grained correlation for associating images and texts. • This paper presents an effective bidirectional ranking loss, namely Harmonious Bidirectional Ranking (HBR) for cross-modal correlation preserving. It not only efficiently assists us to seek out more representative hard negative samples, but also leverages the category center of negatives to enhance the robustness of cross-modal representations. • Extensive experiments on two benchmark datasets validate the superiority of our proposed model in comparison to the state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

Ensemble clustering (EC) gains more and more attention because it can improve the effectiveness and robustness of single clustering methods. A popular ensemble approach is to construct a co-association matrix which represents the possibility that the sample pair is divided into different clusters by base clusterings. Then, some single clustering methods could be performed on it. However, this approach separates the construction of the co-association matrix from the generation of clustering results. Besides, the importance of base clusterings and clusters are often regarded as the same but their performance or quality is different actually. Although some weighted ensemble clustering methods have been proposed, typically, the weights are calculated based on certain criteria and then fixed. To cope with these issues, we propose a Parameter-Free Ensemble Clustering (PFEC) with dynamic weighting mechanism, which is capable of dynamically adjusting the weights of base clusterings and clusters. Firstly, the self-weighted framework is applied in our method to weight base clusterings automatically. Furthermore, an additional weight is assigned to each cluster in the base clustering, which can also be dynamically adjusted. This can help alleviate the issue of imbalanced clusters as well. Finally, a structured affinity graph is learned from the results of base clusterings through rank constraint and no post-processing is required. The experimental results on synthetic and real datasets illustrate the effectiveness of our proposed method. • A parameter-free weighted ensemble clustering method is proposed. • Dual weights are added from the partition and cluster level. • Experimental results indicate the effectiveness of our proposed method. [ABSTRACT FROM AUTHOR]

Linear discriminant analysis (LDA) uses labeled samples for acquiring a discriminant projection direction, by which data of different categories are separated into distinct groups in a lower-dimensional subspace. In response to the issue that LDA lacks robustness to non-Gaussian data with rich local information, improvements on LDA explore the subspace manifold structure by building a fully connected similarity graph. However, these methods are vulnerable to the interference of noisy and redundant information. In this paper, we propose a new local LDA method, named adaptive and fuzzy locality discriminant analysis (AFLDA), which aims at extracting precise and compact features. Firstly, an adaptive and fuzzy k-means strategy is adopted, where the membership between data and corresponding subclass centers for each class is learned to establish a hybrid bipartite graph and capture local information. Secondly, we design a discrete and probability constraint imposed on the membership matrix to explore the intricate structure of multimodal data. Moreover, the subblock partition for each class makes data accommodate to multimodal subclasses. Thirdly, the maximum total scatter regularization term is introduced, which amply disperses the data to enhance the recognition of local structure and avoid trivial solutions. Finally, to eliminate the interference of noisy and redundant information, AFLDA learns an optimized subspace, where cluster centers and the membership matrix are updated alternately. Promising results in experiments illustrate the efficacy of the model. • We propose a subclass partition strategy to learn potential submanifold structures. • Subclass partition provides a concise representation of data for each class. • Fuzzy membership between instances and subclass centers for each class is learned. • A discrete tactic is adopted on memberships to obtain a pseudo-label for each sample. • The membership matrix can be updated adaptively and independently through each class. • The model could handle non-Gaussian data and identify potential subclusters. [ABSTRACT FROM AUTHOR]

In recent years, anomaly events detection in crowd scenes attracts many researchers' attentions, because of its importance to public safety. Existing methods usually exploit visual information to analyze whether any abnormal events have occurred due to only visual sensors are generally equipped in public places. However, when an abnormal event in crowds occurs, sound information may be discriminative to assist the crowd analysis system to determine whether there is an abnormality. Compared with vision information that is easily occluded, audio signals have a certain degree of penetration. Thus, this paper attempt to exploit multi-modal learning for modeling the audio and visual signals simultaneously. To be specific, we design a two-branch network to model different types of information. The first is a typical 3D CNN model to extract temporal appearance feature from video clips. The second is an audio CNN for encoding Log Mel-Spectrogram of audio signals. Finally, by fusing the above features, the more accurate prediction will be produced. We conduct the experiments on SHADE dataset, a synthetic audio–visual dataset in surveillance scenes, and find introducing audio signals effectively improves the performance of anomaly events detection and outperforms other state-of-the-art methods. Furthermore, we will release the code and the pre-trained models as soon as possible. [ABSTRACT FROM AUTHOR]

As a promising field, Multi-Query Image Retrieval (MQIR) aims at searching for the semantically relevant image given multiple region-specific text queries. Existing works mainly focus on a single-level similarity between image regions and text queries, which neglect the hierarchical guidance of multi-level similarities and result in incomplete alignments. Besides, the high-level semantic correlations that intrinsically connect different region–query pairs are rarely considered. To address above limitations, we propose a novel Hierarchical Matching and Reasoning Network (HMRN) for MQIR. It disentangles MQIR into three hierarchical semantic representations, which is responsible to capture fine-grained local details, contextual global scopes, and high-level inherent correlations. HMRN consists of two modules: Scalar-based Matching (SM) module and Vector-based Reasoning (VR) module. Specifically, the SM module characterizes the multi-level alignment similarity, which consists of a fine-grained local-level similarity and a context-aware global-level similarity. Afterwards, the VR module is developed to excavate the potential semantic correlations among multiple region–query pairs, which further explores the high-level reasoning similarity. Finally, these three-level similarities are aggregated into a joint similarity space to form the ultimate similarity. Extensive experiments on the benchmark dataset demonstrate that our HMRN substantially surpasses the current state-of-the-art methods. For instance, compared with the existing best method Drill-down, the metric R@1 in the last round is improved by 23.4%. Our source codes will be released at https://github.com/LZH-053/HMRN. • Cope with the difficulties arising from the heterogeneous gap between images and multiple detailed text queries. • Design a hierarchical structure to explore and aggregate diverse semantical characteristics. • Perform multi-level matching to facilitate the fine-grained alignments. • Conduct high-level reasoning to mine the inherent intra-correlations and inter-correlations. • Significantly outperform the state-of-the-art methods by more than 20% on the R@1 metric. [ABSTRACT FROM AUTHOR]

As a multivariate data analysis tool, canonical correlation analysis (CCA) has been widely used in computer vision and pattern recognition. However, CCA uses Euclidean distance as a metric, which is sensitive to noise or outliers in the data. Furthermore, CCA demands that the two training sets must have the same number of training samples, which limits the performance of CCA-based methods. To overcome these limitations of CCA, two novel canonical correlation learning methods based on low-rank learning are proposed in this paper for image representation, named robust canonical correlation analysis (robust-CCA) and low-rank representation canonical correlation analysis (LRR-CCA). By introducing two regular matrices, the training sample numbers of the two training datasets can be set as any values without any limitation in the two proposed methods. Specifically, robust-CCA uses low-rank learning to remove the noise in the data and extracts the maximization correlation features from the two learned clean data matrices. The nuclear norm and $L_{1}$ -norm are used as constraints for the learned clean matrices and noise matrices, respectively. LRR-CCA introduces low-rank representation into CCA to ensure that the correlative features can be obtained in low-rank representation. To verify the performance of the proposed methods, five publicly image databases are used to conduct extensive experiments. The experimental results demonstrate the proposed methods outperform state-of-the-art CCA-based and low-rank learning methods. [ABSTRACT FROM AUTHOR]

Principal component analysis (PCA) is warmly welcomed in dimensionality reduction and its applications. Due to the high sensitivity of PCA to outliers, a series of PCA methods are proposed to enhance the robustness of PCA. Besides, the representation ability of the existing PCA methods has limitations as well. To enhance the robustness and representation ability of robust PCA, we elaborate a novel Graph Convolution Robust PCA method (GRPCA) to incorporate the manifold structure into PCA. It constructs a sparse graph based on the local connectivity structure of samples. Graph auto-encoder is utilized to solve the robust PCA problem under the low-rank and sparse constraints. With the dual-decoder, GRPCA learns the low-dimensional embeddings that reconstruct the manifold structure and low-rank approximation simultaneously. Furthermore, since the graph suffers from misconnection triggered by occlusions, the local connectivity structure of low-dimensional embeddings is utilized to modify the graph. Our proposed method excels in both the clustering of low-dimensional embeddings and the low-rank recovery. Lastly, extensive experiments conducted on six real-world datasets demonstrated the efficiency and superiority of the proposed GRPCA. [ABSTRACT FROM AUTHOR]

Domain adaptation leverages rich knowledge from a related source domain so that it can be used to perform tasks in a target domain. For more knowledge to be obtained under relaxed conditions, domain adaptation methods have been widely used in pattern recognition and image classification. However, most of the existing domain adaptation methods only consider how to minimize different distributions of the source and target domains, which neglects what should be transferred for a specific task and suffers negative transfer by distribution outliers. To address these problems, in this paper, we propose a novel domain adaptation method called weighted correlation embedding learning (WCEL) for image classification. In the WCEL approach, we seamlessly integrated correlation learning, graph embedding, and sample reweighting into a unified learning model. Specifically, we extracted the maximum correlated features from the source and target domains for image classification tasks. In addition, two graphs were designed to preserve the discriminant information from interclass samples and neighborhood relations in intraclass samples. Furthermore, to prevent the negative transfer problem, we developed an efficient sample reweighting strategy to predict the target with different confidence levels. To verify the performance of the proposed method in image classification, extensive experiments were conducted with several benchmark databases, verifying the superiority of the WCEL method over other state-of-the-art domain adaptation algorithms. [ABSTRACT FROM AUTHOR]

The multiple kernel $k$ -means (MKKM) and its variants utilize complementary information from different sources, achieving better performance than kernel $k$ -means (KKM). However, the optimization procedures of most previous works comprise two stages, learning the continuous relaxation matrix and obtaining the discrete one by extra discretization procedures. Such a two-stage strategy gives rise to a mismatched problem and severe information loss. Even worse, most existing MKKM methods overlook the correlation among prespecified kernels, which leads to the fusion of mutually redundant kernels and bad effects on the diversity of information sources, finally resulting in unsatisfying results. To address these issues, we elaborate a novel Discrete and Parameter-free Multiple Kernel $k$ -means (DPMKKM) model solved by an alternative optimization method, which can directly obtain the cluster assignment results without subsequent discretization procedure. Moreover, DPMKKM can measure the correlation among kernels by implicitly introducing a regularization term, which is able to enhance kernel fusion by reducing redundancy and improving diversity. Noteworthily, the time complexity of optimization algorithm is successfully reduced, through masterly utilizing of coordinate descent technique, which contributes to higher algorithm efficiency and broader applications. What’s more, our proposed model is parameter-free avoiding intractable hyperparameter tuning, which makes it feasible in practical applications. Lastly, extensive experiments conducted on a number of real-world datasets illustrated the effectiveness and superiority of the proposed DPMKKM model. [ABSTRACT FROM AUTHOR]

Cartoonization as a special type of artistic style transfer is a difficult image processing task. The current existing artistic style transfer methods cannot generate satisfactory cartoon-style images due to that artistic style images often have delicate strokes and rich hierarchical color changes while cartoon-style images have smooth surfaces without obvious color changes, and sharp edges. To this end, we propose a cartoon loss based generative adversarial network (CartoonLossGAN) for cartoonization. Particularly, we first reuse the encoder part of the discriminator to build a compact generative adversarial network (GAN) based cartoonization architecture. Then we propose a novel cartoon loss function for the architecture. It can imitate the process of sketching to learn the smooth surface of the cartoon image, and imitate the coloring process to learn the coloring of the cartoon image. Furthermore, we also propose an initialization strategy, which is used in the scenario of reusing the discriminator to make our model training easier and more stable. Extensive experimental results demonstrate that our proposed CartoonLossGAN can generate fantastic cartoon-style images, and outperforms four representative methods. [ABSTRACT FROM AUTHOR]

Fuzzy K-Means clustering has been an attractive research area for many multimedia tasks. Due to the interference of the noise and outliers, the performance of fuzzy K-Means clustering has been limited. In this paper, a projected fuzzy K-Means clustering method, referred to as Robust Projected Fuzzy K-Means (RPFKM) is proposed as a response to such a challenge. RPFKM improves fuzzy K-Means clustering in three perspectives. First, unlike existing fuzzy K-Means algorithms where the clustering process is conducted in the original space, RPFKM learns the fuzzy membership relationship between samples and prototypes in the low-dimensional space to eliminate the influence of the noise and irrelevant features. Second, it employs the ℓ 21 norm to reduce the contribution of outliers to the learning of prototypes. Third, it also considers the sensitivity of fuzzy clustering to the number of reduced dimensions, and the reconstruction term is introduced to hold the main energy of the original data. Furthermore, an iterative re-weighted algorithm is developed to solve the proposed method. The evaluation results of our proposed method and the state-of-the-art methods on real-world and synthetic data sets show the effectiveness and efficiency of our approach. [ABSTRACT FROM AUTHOR]

With the coming of big data era, multi-view data represented by multiple features have been involved in many terms, such as machine learning, data mining and computer vision and so on. Due to the complex structure hidden in data, how to utilize the complementary and correlative information among multiple view features to improve classification performance is a challenging task. Moreover, the another challenging task is how to assign an appropriate weight for each classifier on the basis of its performance. To solve above problems, we proposed a supervised multi-view classification method based on Least Square Regression (LSR) and Ensemble Learning. To be specific, all samples for each view firstly can be classified by using Multi-class Support Vector Machine (MSVM); Then, to evaluate the classification results of different views for each sample, the optimal weight of each sample classification result is learned; Furthermore, considering the view difference with different classification quality, the view weights are assigned adaptively; Finally, we adopt the decision function values to determine the final classification results. Extensive experimental results show that the proposed method outperforms most state-of-the-art multi-view classification methods. [ABSTRACT FROM AUTHOR]

To achieve high value of classification results by using a limited number of training samples, designing a multi-view semi-supervised classification model is extremely urgent. Moreover, considering that graph learning can fully capture the complex data structure information, we propose a graph-based multi-view semi-supervised classification approach named as Semi-supervised Classification based on Intra-view Heterogeneity and Inter-view Compatibility (SSC_IHIC). Specifically, the similarity between two samples can be measured based on the Euclidean distance. Considering that heterogeneity exists in intra-view sub-features, hence, the weights are learned adaptively. Besides, based on the inter-view compatibility, the consensus similarity graph is constructed on which the labels are propagated. To verify the effectiveness, the proposed approach is conducted on four data sets including MSRC-v1, Handwritten (HW), Cal101-7 and Cal101-20. From the experimental results, we can see that the classification performance about proposed method outperforms the single view classification methods and the state-of-the-art multi-view classification methods. [ABSTRACT FROM AUTHOR]

Visual tracking is a very critical issue in computer vision and video processing. For Discriminative Correlation Filter (DCF)-based tracking methods, it is very essential and meaningful to adaptively incorporate reliable target and surrounding information from video frames. However, most existing DCF-based trackers solely rely on pre-defined and fixed constraints such as a binary mask or quadratic function-based regularization to improve the discrimination. Unfortunately, such attempts fail to adjust the constraints according to the change of tracking circumstance in the video sequence, and thus lead to the lack of reliability of learned filters. To mitigate these problems, we present a novel DCF-based tracking method that introduces an adaptive target-and-surrounding soft mask (ATSM) into the learning formula. The adaptive soft mask that is represented by float numbers contains the detail information for both target region and its surrounding information: first, for the background area, it introduces meaningful background information and suppressing uninformative one; second, for the target area inside the bounding box, it helps to focus on the reliable area and repress the rapidly changing area; third, the target-and-surrounding soft mask is adaptively adjusted based on the variations of the target and its surrounding during the tracking process. By jointly modeling the filter and the adaptive soft mask, our ATSM tracker achieves an efficient integration of meaningful information of both foreground and background and performs favorably against state-of-the-art algorithms on seven well-known benchmarks. [ABSTRACT FROM AUTHOR]

$k$ k -means method using Lloyd heuristic is a traditional clustering method which has played a key role in multiple downstream tasks of machine learning because of its simplicity. However, Lloyd heuristic always finds a bad local minimum, i.e., the bad local minimum makes objective function value not small enough, which limits the performance of $k$ k -means. In this paper, we use coordinate descent (CD) method to solve the problem. First, we show that the $k$ k -means minimization problem can be reformulated as a trace maximization problem, then a simple and efficient coordinate descent scheme is proposed to solve the maximization problem. Two interesting findings through theory are that Lloyd cannot decrease the objective function value of $k$ k -means produced by our CD further, and our proposed method CD to solve $k$ k -means problem can avoid produce empty clusters. In addition, according to the computational complexity analysis, it is verified CD has the same time complexity with original $k$ k -means method. Extensive experiments including statistical hypothesis testing, on several real-world datasets with varying number of clusters, varying number of samples and varying number of dimensions show that CD performs better compared to Lloyd, i.e., lower objective value, better local minimum and fewer iterations. And CD is more robust to initialization than Lloyd whether the initialization strategy is random or initialization of $k$ k -means++. [ABSTRACT FROM AUTHOR]

Exploiting the inner-shot and inter-shot dependencies is essential for key-shot based video summarization. Current approaches mainly devote to modeling the video as a frame sequence by recurrent neural networks. However, one potential limitation of the sequence models is that they focus on capturing local neighborhood dependencies while the high-order dependencies in long distance are not fully exploited. In general, the frames in each shot record a certain activity and vary smoothly over time, but the multi-hop relationships occur frequently among shots. In this case, both the local and global dependencies are important for understanding the video content. Motivated by this point, we propose a reconstructive sequence-graph network (RSGN) to encode the frames and shots as sequence and graph hierarchically, where the frame-level dependencies are encoded by long short-term memory (LSTM), and the shot-level dependencies are captured by the graph convolutional network (GCN). Then, the videos are summarized by exploiting both the local and global dependencies among shots. Besides, a reconstructor is developed to reward the summary generator, so that the generator can be optimized in an unsupervised manner, which can avert the lack of annotated data in video summarization. Furthermore, under the guidance of reconstruction loss, the predicted summary can better preserve the main video content and shot-level dependencies. Practically, the experimental results on three popular datasets (i.e., SumMe, TVsum and VTW) have demonstrated the superiority of our proposed approach to the summarization task. [ABSTRACT FROM AUTHOR]

Recent research has revealed that COVID-19 pneumonia is often accompanied by pulmonary edema. Pulmonary edema is a manifestation of acute lung injury (ALI), and may progress to hypoxemia and potentially acute respiratory distress syndrome (ARDS), which have higher mortality. Precise classification of the degree of pulmonary edema in patients is of great significance in choosing a treatment plan and improving the chance of survival. Here we propose a deep learning neural network named Non-local Channel Attention ResNet to analyze the lung ultrasound images and automatically score the degree of pulmonary edema of patients with COVID-19 pneumonia. The proposed method was designed by combining the ResNet with the non-local module and the channel attention mechanism. The non-local module was used to extract the information on characteristics of A-lines and B-lines, on the basis of which the degree of pulmonary edema could be defined. The channel attention mechanism was used to assign weights to decisive channels. The data set contains 2220 lung ultrasound images provided by Huoshenshan Hospital, Wuhan, China, of which 2062 effective images with accurate scores assigned by two experienced clinicians were used in the experiment. The experimental results indicated that our method achieved high accuracy in classifying the degree of pulmonary edema in patients with COVID-19 pneumonia by comparison with previous deep learning methods, indicating its potential to monitor patients with COVID-19 pneumonia. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel energy optimization framework to accurately estimate surface normal and reflectance of an object from an input image sequence. Input images are captured from a fixed viewpoint under varying lighting conditions. In the proposed approach we combine photometric stereo and Retinex constraints into our energy function. To formulate inter-image constraints, shading information is added to the Lambertian model to account for shadows. For intra-image constraints, we moderate the strength of shading smoothness according to shadow mask and normal variations. By minimizing this energy function we are able to recover accurate surface normals and reflectance. Experimental results show that our approach yields more realistic normal map and accurate albedo map than the state-of-the-art uncalibrated photometric stereo algorithms. As for intrinsic image decomposition, results on the real and synthetic scenes show that the proposed approach outperforms previous ones. [ABSTRACT FROM PUBLISHER]

• A novel segmentation-to-classification framework is proposed for breast US diagnosis. • The segmentation network is trained to obtain the segmentation enhanced images, and the features of the segmentation enhanced images and original images are extracted in parallel for classification. • An attention-based method is proposed for feature aggregation of two parallel networks to enhance features useful for classification in a data-driven manner. • Experimental results show the advantages of the proposed method. Breast cancer is one of the most common forms of cancer among women worldwide. The development of computer-aided diagnosis (CAD) technology based on ultrasound imaging to promote the diagnosis of breast lesions has attracted the attention of researchers and deep learning is a popular and effective method. However, most of the deep learning based CAD methods neglect the relationship between two vision tasks tumor region segmentation and classification. In this paper, taking into account some prior knowledges of medicine, we propose a novel segmentation-to-classification scheme by adding the segmentation-based attention (SBA) information to the deep convolution network (DCNN) for breast tumors classification. A segmentation network is trained to generate tumor segmentation enhancement images. Then two parallel networks extract features for the original images and segmentation enhanced images and one channel attention based feature aggregation network is to automatically integrate the features extracted from two feature networks to improve the performance of recognizing malignant tumors in the breast ultrasound images. To validate our method, experiments have been conducted on breast ultrasound datasets. The classification results of our method have been compared with those obtained by eleven existing approaches. The experimental results show that the proposed method achieves the highest Accuracy (90.78%), Sensitivity (91.18%), Specificity (90.44%), F1-score (91.46%), and AUC (0.9549). [ABSTRACT FROM AUTHOR]