Search

One of the primary goals of the airborne vehicle detection system is to reduce the risks of incident collisions and to relieve traffic jam caused by the increasing number of vehicles. Different from the stationary systems, which are usually fixed on buildings, the airborne systems in unmanned aircrafts or satellites take the advantages of wider view angle and higher mobility. However, detecting vehicles in airborne videos is a challenging task because of the scene complexity and platform movement. The direct application of the traditional image processing techniques to the problem may result in low detection rate or cannot meet the requirements of real-time applications. To address these problems, a new and efficient method composed by two stages, attention focus extraction and vehicle classification is proposed in this paper. Our work makes two key contributions. The first is the introduction of a new attention focus extraction algorithm, which can quickly detect the candidate vehicle regions to make the algorithm focus on much smaller regions for faster computation. The second contribution is a simple and efficient classification process, which is built using the AdaBoost learning algorithm. The classification process, which is a hierarchical structure, is designed to obtain a lower false alarm rate by looking for vehicles in the candidate regions. Experimental results demonstrate that, compared with other representative algorithms, our method can obtain better performance in terms of higher detection rate and lower false positive rate, while meeting the needs of real-time application. [ABSTRACT FROM AUTHOR]

The neighbor-embedding (NE) algorithm for single-image super-resolution (SR) reconstruction assumes that the feature spaces of low-resolution (LR) and high-resolution (HR) patches are locally isometric. However, this is not true for SR because of one-to-many mappings between LR and HR patches. To overcome or at least to reduce the problem for NE-based SR reconstruction, we apply a joint learning technique to train two projection matrices simultaneously and to map the original LR and HR feature spaces onto a unified feature subspace. Subsequently, the k-nearest neighbor selection of the input LR image patches is conducted in the unified feature subspace to estimate the reconstruction weights. To handle a large number of samples, joint learning locally exploits a coupled constraint by linking the LR–HR counterparts together with the K-nearest grouping patch pairs. In order to refine further the initial SR estimate, we impose a global reconstruction constraint on the SR outcome based on the maximum a posteriori framework. Preliminary experiments suggest that the proposed algorithm outperforms NE-related baselines. [ABSTRACT FROM AUTHOR]

The biologically inspired model (BIM) proposed by Serre presents a promising solution to object categorization. It emulates the process of object recognition in primates' visual cortex by constructing a set of scale- and position-tolerant features whose properties are similar to those of the cells along the ventral stream of visual cortex. However, BIM has potential to be further improved in two aspects: mismatch by dense input and randomly feature selection due to the feedforward framework. To solve or alleviate these limitations, we develop an enhanced BIM (EBIM) in terms of the following two aspects: 1) removing uninformative inputs by imposing sparsity constraints, 2) apply a feedback loop to middle level feature selection. Each aspect is motivated by relevant psychophysical research findings. To show the effectiveness of the EBIM, we apply it to object categorization and conduct empirical studies on four computer vision data sets. Experimental results demonstrate that the EBIM outperforms the BIM and is comparable to state-of-the-art approaches in terms of accuracy. Moreover, the new system is about 20 times faster than the BIM. [ABSTRACT FROM AUTHOR]

Visual surveillance from low-altitude airborne platforms plays a key role in urban traffic surveillance. Moving vehicle detection and motion analysis are very important for such a system. However, illumination variance, scene complexity, and platform motion make the tasks very challenging. In addition, the used algorithms have to be computationally efficient in order to be used on a real-time platform. To deal with these problems, a new framework for vehicle detection and motion analysis from low-altitude airborne videos is proposed. Our paper has two major contributions. First, to speed up feature extraction and to retain additional global features in different scales for higher classification accuracy, a boosting light and pyramid sampling histogram of oriented gradients feature extraction method is proposed. Second, to efficiently correlate vehicles across different frames for vehicle motion trajectories computation, a spatio-temporal appearance-related similarity measure is proposed. Compared to other representative existing methods, our experimental results showed that the proposed method is able to achieve better performance with higher detection rate, lower false positive rate, and faster detection speed. [ABSTRACT FROM AUTHOR]

Abstract: In this paper, a rapid adaptive pedestrian detection method based on cascade classifier with ternary pattern is proposed. The proposed method achieves its goal by employing the following three new strategies: (1) A method for adjusting the key parameters of the trained cascade classifier dynamically for detecting pedestrians in unseen scenes using only a small amount of labeled data from the new scenes. (2) An efficient optimization method is proposed, based on the cross entropy method and a priori knowledge of the scenes, to solve the classifier parameter optimization problem. (3) In order to further speed up pedestrian detection in unseen scenes, each strong classifier in the cascade employs a ternary detection pattern. In our experiments, two significantly different datasets, AHHF and NICTA, were used as the training set and testing set, respectively. The experimental results showed that the proposed method can quickly adapt a previously trained detector for pedestrian detection in various scenes compared with other existing methods. [Copyright &y& Elsevier]

Considering that the Human Visual System (HVS) has different perceptual characteristics for different morphological components, a novel image quality metric is proposed by incorporating Morphological Component Analysis (MCA) and HVS, which is capable of assessing the image with different kinds of distortion. Firstly, reference and distorted images are decomposed into linearly combined texture and cartoon components by MCA respectively. Then these components are turned into perceptual features by Just Noticeable Difference (JND) which integrates masking features, luminance adaptation and Contrast Sensitive Function (CSF). Finally, the discrimination between reference and distorted images perceptual features is quantified using a pooling strategy before the final image quality is obtained. Experimental results demonstrate that the performance of the proposed prevails over some existing methods on LIVE database II. [ABSTRACT FROM AUTHOR]

Abstract: Mammographic mass segmentation plays an important role in computer-aided diagnosis systems. It is very challenging because masses are always of low contrast with ambiguous margins, connected with the normal tissues, and of various scales and complex shapes. To effectively detect true boundaries of mass regions, we propose a feature embedded vector-valued contour-based level set method with relaxed shape constraint. In particular, we initially use the contour-based level set method to obtain the initial boundaries on the smoothed mammogram as the shape constraint. To prevent the contour leaking and meanwhile preserve the radiative characteristics of specific malignant masses, afterward, we relax the obtained shape constraint by analyzing possible valid regions around the initial boundaries. The relaxed shape constraint is then used to design a novel stopping function for subsequent vector-valued level set method. Since texture maps, gradient maps, and the original intensity map can reflect different characteristics of the mammogram, we integrate them together to obtain more accurate segmentation by incorporating the new stopping function into the newly proposed feature embedded vector-valued contour-based level set method. The experimental results suggest that the proposed feature embedded vector-valued contour-based level set method with relaxed shape constraint can effectively find ambiguous margins of the mass regions. Comparing against existing active contours methods, the new scheme is more effective and robust in detecting complex masses. [Copyright &y& Elsevier]

Histogram-based lossless data embedding (LDE) has been recognized as an effective and efficient way for copyright protection of multimedia. Recently, a LDE method using the statistical quantity histogram has achieved good performance, which utilizes the similarity of the arithmetic average of difference histogram (AADH) to reduce the diversity of images and ensure the stable performance of LDE. However, this method is strongly dependent on some assumptions, which limits its applications in practice. In addition, the capacities of the images with the flat AADH, e.g., texture images, are a little bit low. For this purpose, we develop a novel framework for LDE by incorporating the merits from the generalized statistical quantity histogram (GSQH) and the histogram-based embedding. Algorithmically, we design the GSQH driven LDE framework carefully so that it: 1) utilizes the similarity and sparsity of GSQH to construct an efficient embedding carrier, leading to a general and stable framework; 2) is widely adaptable for different kinds of images, due to the usage of the divide-and-conquer strategy; 3) is scalable for different capacity requirements and avoids the capacity problems caused by the flat histogram distribution; 4) is conditionally robust against JPEG compression under a suitable scale factor; and 5) is secure for copyright protection because of the safe storage and transmission of side information. Thorough experiments over three kinds of images demonstrate the effectiveness of the proposed framework. [ABSTRACT FROM AUTHOR]

We consider the problem of enriching the travelogue associated with a small number (even one) of images with more web images. Images associated with the travelogue always consist of the content and the style of textual information. Relying on this assumption, in this paper, we present a framework of travelogue enriching, exploiting both textual and visual information generated by different users. The framework aims to select the most relevant images from automatically collected candidate image set to enrich the given travelogue, and form a comprehensive overview of the scenic spot. To do these, we propose to build two-layer probabilistic models, i.e. a text-layer model and image-layer models, on offline collected travelogues and images. Each topic (e.g. Sea, Mountain, Historical Sites) in the text-layer model is followed by an image-layer model with sub-topics learnt (e.g. the topic of sea is with the sub-topic like beach, tree, sunrise and sunset). Based on the model, we develop strategies to enrich travelogues in the following steps: (1) remove noisy names of scenic spots from travelogues; (2) generate queries to automatically gather candidate image set; (3) select images to enrich the travelogue; and (4) choose images to portray the visual content of a scenic spot. Experimental results on Chinese travelogues demonstrate the potential of the proposed approach on tasks of travelogue enrichment and the corresponding scenic spot illustration. [ABSTRACT FROM AUTHOR]

This paper presents a new image segmentation method that applies an edge-based level set method in a relay fashion. The proposed method segments an image in a series of nested subregions that are automatically created by shrinking the stabilized curves in their previous subregions. The final result is obtained by combining all boundaries detected in these subregions. The proposed method has the following three advantages: 1) It can be automatically executed without human–computer interactions; 2) it applies the edge-based level set method with relay fashion to detect all boundaries; and 3) it automatically obtains a full segmentation without specifying the number of relays in advance. The comparison experiments illustrate that the proposed method performs better than the representative level set methods, and it can obtain similar or better results compared with other popular segmentation algorithms. [ABSTRACT FROM AUTHOR]

The Gaussian process latent variable model (GP-LVM) has been identified to be an effective probabilistic approach for dimensionality reduction because it can obtain a low-dimensional manifold of a data set in an unsupervised fashion. Consequently, the GP-LVM is insufficient for supervised learning tasks (e.g., classification and regression) because it ignores the class label information for dimensionality reduction. In this paper, a supervised GP-LVM is developed for supervised learning tasks, and the maximum a posteriori algorithm is introduced to estimate positions of all samples in the latent variable space. We present experimental evidences suggesting that the supervised GP-LVM is able to use the class label information effectively, and thus, it outperforms the GP-LVM and the discriminative extension of the GP-LVM consistently. The comparison with some supervised classification methods, such as Gaussian process classification and support vector machines, is also given to illustrate the advantage of the proposed method. [ABSTRACT FROM AUTHOR]

Inspired by human visual cognition mechanism, this paper first presents a scene classification method based on an improved standard model feature. Compared with state-of-the-art efforts in scene classification, the newly proposed method is more robust, more selective , and of lower complexity. These advantages are demonstrated by two sets of experiments on both our own database and standard public ones. Furthermore, occlusion and disorder problems in scene classification in video surveillance are also first studied in this paper. [ABSTRACT FROM AUTHOR]

Abstract: The broadcast soccer video is usually recorded by one main camera, which is constantly gazing somewhere of playfield where a highlight event is happening. So the camera parameters and their variety have close relationship with semantic information of soccer video, and much interest has been caught in camera calibration for soccer video. The previous calibration methods either deal with goal scene, or have strict calibration conditions and high complexity. So, it does not properly handle the non-goal scene such as midfield or center-forward scene. In this paper, based on a new soccer field model, a field symbol extraction algorithm is proposed to extract the calibration information. Then a two-stage calibration approach is developed which can calibrate camera not only for goal scene but also for non-goal scene. The preliminary experimental results demonstrate its robustness and accuracy. [Copyright &y& Elsevier]

Eye detection plays an important role in many practical applications. This paper presents a novel two-step scheme for eye detection. The first step models an eye by a newly defined visual-context pattern (VCP), and the second step applies semisupervised boosting for precise detection. VCP describes both the space and appearance relations between an eye region (region of eye) and a reference region (region of reference). The context feature of a VCP is extracted by using the integral image. Aiming to reduce the human labeling efforts, we apply semisupervised boosting, which integrates the context feature and the Haar-like features for precise eye detection. Experimental results on several standard face data sets demonstrate that the proposed approach is effective, robust, and efficient. We finally show that this approach is ready for practical applications. [ABSTRACT FROM AUTHOR]

Abstract: Face recognition by sketches in photos remains a challenging task. Unlike the existing sketch–photo recognition methods, which convert a photo into sketch and then perform the sketch–photo recognition through sketch–sketch recognition, this paper devotes to synthesizing a photo from the sketch and transforming the sketch–photo recognition to photo–photo recognition to achieve better performance in mixture pattern recognition. The contribution of this paper mainly focuses on two aspects: (1) in view of that there are no many research findings of sketch–photo recognition based on the pseudo-photo synthesis and the existing methods require a large set of training samples, which is nearly impossible to achieve for the high cost of sketch acquisition, we make use of embedded hidden Markov model (EHMM), which can learn the nonlinearity of sketch–photo pair with less training samples, to produce pseudo-photos in terms of sketches; and (2) photos and sketches are divided into patches and pseudo-photo is generated by combining pseudo-photo patches, which makes pseudo-photo more recognizable. Experimental results demonstrate that the newly proposed method is effective to identify face sketches in photo set. [Copyright &y& Elsevier]

Abstract: This paper proposes a simple scene segmentation method based on incremental principal component analysis (IPCA). Instead of segmenting moving objects in a conventional frame by frame manner, the newly proposed method segments a scene into unchanged background zone (UBZ) and moving object zone (MOZ). As a result, moving objects normally appear in MOZs rather than UBZs, and therefore, detection and behaviours analysis can be performed in MOZs. In visual communication, UBZs do not need to be encoded and transmitted. Moreover, if an object is in UBZs, it can be linked to abnormal events. Experimental results demonstrate the contribution of the proposed method. [Copyright &y& Elsevier]

Abstract: With the popularity of cameras and rapid development of computer vision technology, vision-based HCI is attracting extensive interests. In this paper, we present a system for controlling avatars by natural body movement via a single web-camera. A pose database and a set of color markers are utilized to make ill-posed vision problem tractable for real game applications. Based on the proposed algorithms for indexing pose samples and estimating human pose, we build a prototype system that is responsive, easy to manipulate and runs automatically in real time. User study shows that the system is user-friendly and provides immersive experiences. [Copyright &y& Elsevier]

• This paper considers four directions of multi-label learning. • The hierarchical constraint guarantees the hierarchical label connections. • The low-rank constrains guarantees the low-rank property of multi-label projection. • MDML outperforms competitors in effectiveness and efficiency. In multi-label learning, the key problem is to capture the relationships between multiple labels, including proximities and unconformities. In this paper, we consider the relationships among multiple labels from multi-directions, including utilizing discriminative classifier, proposing a general hierarchical constraint and proximity correlation, meanwhile combining low-rank constraint, to infer a novel Multi-Directional Multi-Label learning (MDML) model. To optimize the problems involved in to the proposed models, we develop an iterative algorithms based on the alternating direction method of multipliers (ADMM) algorithm. In the simulations, the experimental results on 4 popular benchmark datasets demonstrate the superiorities of MDML model. [ABSTRACT FROM AUTHOR]

Abstract: This paper presents a novel algorithm for computing graph edit distance (GED) in image categorization. This algorithm is purely structural, i.e., it needs only connectivity structure of the graph and does not draw on node or edge attributes. There are two major contributions: (1) Introducing edge direction histogram (EDH) to characterize shape features of images. It is shown that GED can be employed as distance of EDHs. This algorithm is completely independent on cost function which is difficult to be defined exactly. (2) Computing distance of EDHs with earth mover distance (EMD) which takes neighborhood bins into account so as to compute distance of EDHs correctly. A set of experiments demonstrate that the newly presented algorithm is available for classifying and clustering images and is immune to the planar rotation of images. Compared with GED from spectral seriation, our algorithm can capture the structure change of graphs better and consume 12.79% time used by the former one. The average classification rate is 5% and average clustering rate is 25% higher than the spectral seriation method. [Copyright &y& Elsevier]

The rail transit has difficulties in meeting daily travel needs of passengers owing to a large population and accelerating urbanization. Analyzing urban travel behaviors with big data helps the design in infrastructures and the optimized personnel allocation. Furthermore, travel behaviors are characterized by dynamic at different time and locations, displaying the rule of urban traffic operation. This paper utilizes smart card data in two cities with different geographical features to analyze the temporal–spatial characteristics of urban travel behaviors. More specifically, by creating travel networks based on the pick-up and drop-off stations and the passenger population among these stations, an interesting observation is that the community structure of travel networks owns a metabolic trend and a stable feature simultaneously. The finding shows that the traffic system can be managed in several parts. Moreover, similar mobility patterns exist in some stations, which can be organized and controlled in the same way. Finally, travel behaviors are related to the urban layout and structure, so the distribution of urban areas can be understood better. Experiments provide enlightening insights for policy makers to comprehend the urban travel behaviors, thus improving the rail transit service plans and scheduling strategies. [ABSTRACT FROM AUTHOR]

• We introduce third parties and disputants on interdependent network. • Disputants play prisoner's dilemma game and bring third parties extra payoffs. • Third parties intervene disputants play snowdrift dilemma game or not. • Conflicts in disputants are relieved though non-interventions exist in third party layer. Interventions from third parties, such as governmental agencies or organizations, play an important role in mitigating conflicts in modern human societies. The goal thereby is to pacify disputants, although this is subject to failure on account of self-interest from all involved. To study how relationships between disputants and third parties evolve, we propose an interdependent network model, where one layer is occupied by disputants and the other layer is occupied by third parties. Disputants play a prisoner's dilemma game, where defection is the dominant strategy, whereas third parties play a snowdrift game, where cooperation and defection coexist more commonly. Moreover, third parties have the ability to mediate a conflict on the other layer by enforcing a snowdrift game onto disputants, for which they can receive a fee. We show that third party interventions improve the evolution of cooperation between disputants, and also, that the improvement of cooperation in turn promotes interventions. Nonetheless, non-intervention does not go extinct, which enables defectors to survive, thus creating a feedback loop between the two networks layers. The evolutionary dynamics is characterized by fascinating spatial pattern formation, which we explore by means of Monte Carlo simulations and via replicator equations. [ABSTRACT FROM AUTHOR]

Image quality is a key characteristic in image processing,10,11 image retrieval,12,13 and biometrics.14 In this paper, a novel reduced-reference image quality assessment method is proposed based on wavelet transform. By simulating the human visual system, we take the variance of the visual sensitive coefficients into account to measure a distorted image. The computational complexity of the proposed method is much lower compared with some existing methods. Experimental results demonstrate its advantages in terms of correlation coefficient, outlier ratio, transmitted information, and CPU cost. Moreover, it is also illustrated that the proposed method has a good accordance with human subjective perception. [ABSTRACT FROM AUTHOR]

Abstract: Facial sketch synthesis (FSS) is crucial in sketch-based face recognition. This paper proposes an automatic FSS algorithm with local strategy based on embedded hidden Markov model (E-HMM) and selective ensemble (SE). By using E-HMM to model the nonlinear relationship between a photo–sketch patch pair, a series of pseudo-sketch patches, generated based on several learned models for a given photo patch, are integrated with SE strategy to synthesize a finer face pseudo-sketch patch. Finally, the intact pseudo-sketch can be generated by combining all synthesized patches. Experimental results illustrate that the proposed FSS algorithm works well. [Copyright &y& Elsevier]

• We derive a more discriminative LDA which generates the whitening transformation, and it can minimize the scatter within same samples while keeping the scatter of total samples unchanged simultaneously. • Proposed model adaptively selects k neighbors for each data point by imposing L0-norm constraint on similarity matrix. Thus, the graph constructed in our method is k-connected which is more sensitive to local structure of data than full-connected graph in above methods. • Proposed model learns the similarity matrix and the transformation matrix simultaneously such that the kNN graph is dynamically updated. In such way, the neighborships of each sample can be found in the optimal subspace rather than in original space. Additionally, we impose a maximum entropy regularization on similarity matrix so that the trivial solution can be avoided naturally. • An efficient iterative optimization algorithm is presented to solve proposed problem with L0-norm constraint, and a strict proof of convergence is provided as well. Experiments conducted on synthetic and several real-world data sets demonstrate the superiority of proposed DMEG compared to related state-of-the-art methods on classification task. In recent years, Linear Discriminant Analysis (LDA) has seen huge adoption in data mining applications. Due to its globality, it is incompetent to handle multimodal data. Besides, most of LDA's variants learn the projection matrix based on the pre-defined similarity matrix, which is easily affected by noisy and irrelevant features. To address above two issues, a novel local structured feature learning with Dynamic Maximum Entropy Graph (DMEG) method is developed which firstly develops a more discriminative LDA with whitening constraint that can minimize the within-class scatter while keeping the total samples scatter unchanged simultaneously. Second, for exploring the local structure of data, the ℓ 0 -norm constraint is imposed on similarity matrix to ensure the k connectivity on graph. More importantly, proposed model learns the similarity and projection matrix simultaneously to ensure that the neighborships can be found in the optimal subspace where the noise have been removed already. Moreover, a maximum entropy regularization is employed to reinforce the discriminability of graph and avoid the trivial solution. Last but not least, an efficient iterative optimization algorithm is provided to optimize proposed model with a NP-hard constraint. Extensive experiments conducted on synthetic and several real-world data sets demonstrate the efficiency in classification task and robustness to noise of proposed method. [ABSTRACT FROM AUTHOR]

• A GA training pipeline to select key input channels of DenseNet automatically. • A 'Weight inheritance' strategy to improve efficiency whilst maintaining accuracy. • To reduce up to 30% parameters yet achieving a similar accuracy as the DenseNet. • Validated robustness/scalability on several image recognition/classification datasets. Convolutional neural networks (CNNs) have been successfully applied in many computer vision applications [1] , especially in image classification tasks, where most of the structures have been designed manually. With the aid of skip connection and dense connection, the depths of the models are becoming "deeper" and the filters of layers are getting "wider" in order to tackle the challenge of large-scale datasets. However, large-scale models in convolutional layers become inefficient due to the redundant channels from input feature maps. In this paper, we aim to automatically optimize the topology of the DenseNet, in which unnecessary convolutional kernels are reduced. To achieve this, we present a training pipeline that generates the network structure using a genetic algorithm. We first propose two encoding methods that can represent the structure of the model using a fixed-length binary string. A three-step based evolutionary process consisting of selection, crossover, and mutation is proposed to optimize the structure. We also present a pretrained weight inheritance method which can largely reduce the total time consumption of the genetic process. Experimental results have demonstrated that our proposed model can achieve comparable accuracy to the state-of-the-art models, across a wide range of image recognition and classification datasets, whilst significantly reducing the number of parameters. [ABSTRACT FROM AUTHOR]

Bipartite spectral graph partition (BSGP) is a school of the most well-known algorithms designed for the bipartite graph partition problem. It is also a fundamental mathematical model widely used in the tasks of co-clustering and fast spectral clustering. In BSGP, the key is to find the minimal normalized cuts (Ncuts) of bipartite graph. However, the convolutional BSGP algorithms usually need to use the singular value decomposition (SVD) to find the minimal Ncuts, which is computational prohibitive. Under this circumstance, the application range of those methods would be limited when the volume of the dataset is huge or the dimension of features is high. To overcome this problem, this paper proposes a novel weighted bilateral k -means (WBKM) algorithm and applies it for co-clustering and fast spectral clustering. Specifically, WBKM is a relaxation of the problem of finding the minimal Ncuts of bipartite graph, so it can be seen as a new solution for the minimal-Ncuts problem in bipartite graph. Different from the conventional relaxation ways, WBKM relaxes the minimal-Ncuts problem to a Non-negative decomposition problem which can be solved by an efficient iterative method. Therefore, the running speed of the proposed method is much faster. Besides, as our model can directly output the clustering results without any help of post-procedures, its solution tends to be more close to the ideal solution of the minimal-Ncuts problem than that of the conventional BSGP algorithms. To demonstrate the effectiveness and efficiency of the proposed method, extensive experiments on various types of datasets are conducted. Compared with other state-of-the-art methods, the proposed WBKM not only has faster computational speed, but also achieves more promising clustering results. [ABSTRACT FROM AUTHOR]

• This paper proposes a novel stacked Squeeze-and-Excitation Recurrent Residual Network (SER2-Net) for visual-semantic matching. • This paper develops an effective and efficient cross-modal representation learning module, which is capable of generating semantically complementary multi-level features for both modalities. • This paper presents a novel objective function for aligning cross-modal data, which is able to capture the interdependency among multiple semantic levels to alleviate the distribution inconsistency between visual and textual modality. • Extensive experiments on two benchmark datasets demonstrate the superiority of our proposed model compared to the state-of-the-art approaches. In recent years, visual-textual matching has been widely studied in the intersection of computer vision and natural language processing communities. A feasible scheme for learning discriminative representations is leveraging hierarchical features to align both modalities at multiple semantic levels. However, most existing approaches rely on pre-trained object detectors or semantic parsers to generate multi-level representations, whose performance is overly dependent on the extra supervision and thereby leads to its vulnerability. In this paper, we introduce a Stacked Squeeze-and-Excitation Recurrent Residual Network (SER2-Net) for visual-textual matching. Firstly, an efficient multi-level representation module is presented to produce a series of semantically discriminative features without the aid of extra supervision, which is built by stacking the squeeze-and-excitation recurrent residual (SER2) learning components. Specifically, SER2 incorporates the residual learning and inverse recurrent connection into the squeeze-and-excitation learning block, which allows for utilizing complementary current information and residual information to improve the modality-specific representation ability. Besides, to capture the implicit correlations contained among multi-level features, we propose a novel objective namely Cross-modal Semantic Discrepancy (CMSD) loss, which is characterized by exploiting the interdependency among different semantic levels to narrow the cross-modal distribution discrepancy. Extensive experiments on two benchmark datasets validate the superiority of our model, which compares favorably with the state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

• In this paper, we establish a two-layered multiplex network model which combines SIR epidemic process and vaccination decision-making. • We discover that imitating behavior would restrain the increase of herd immunity, • The model is verified by Monte Carlo simulations and mean-field equa- tions, respectively. • A suitable quantity of conformity motivated individual could be beneficial to save the social costs. When confronting the epidemics or pandemics, there often exists an interplay between epidemic incidence and the vaccination strategies of individuals. Recently, the characteristics of human behaviors, such as imitating nature or bandwagon effect, have been proven critical to the final herd immunity. In this paper, by establishing a two-layered multiplex network model which combines SIR epidemic process, vaccination decision-making and imitating human nature, we discover that imitating behavior would restrain the increase of herd immunity, which is verified by Monte Carlo simulations and mean-field equations, respectively. Interestingly, a suitable quantity of conformity motivated individual, counter-intuitively, could be beneficial to save the social costs. At the same time, we analytically determine the precise conditions for the minimum total social costs. The current results can help to understand the behavior of social group in depth and then explore public attitudes concerning the vaccine, which usually has a tremendous impact on social vaccine take-up within the population. [ABSTRACT FROM AUTHOR]

Ultrafast non-diffractive Bessel laser beams provide strong light confinement and show robust advantages for fabricating high-aspect-ratio nanoscale structures inside transparent materials. They take the form of nanoscale voids with typical diameters well below the wavelength and aspect ratio of more than 1000. Delivering 3D morphologies of such nanoscale voids is an important issue to evaluate the result for fabrication. However, the characterization of such laser-induced structures is a difficult task. Here, an accurate and time-saving tomography-like methodology is proposed and adopted for reconstructing the morphology of high-aspect-ratio nano-holes. The technique allows an accurate assertion of laser parameters and position on nano-structured features. The reconstructed configuration reveals that nanoholes morphologies have a close relationship with energy distribution in the focal region. It suggests that the configuration of micro-explosion can be controlled by laser energy deposition in the process of laser-matter interaction down to the nanoscale. [ABSTRACT FROM AUTHOR]

• A novel segmentation method for breast ultrasound is proposed. • Breast lesion is segmented by semantic classification of superpixels. • A K-NN based reclassification is adopted to refine the segmentation. • Experimental results show the advantages of the proposed method. Breast cancer is a great threat to females. Ultrasound imaging has been applied extensively in diagnosis of breast cancer. Due to the poor image quality, segmentation of breast ultrasound (BUS) image remains a very challenging task. Besides, BUS image segmentation is a crucial step for further analysis. In this paper, we proposed a novel method to segment the breast tumor via semantic classification and merging patches. The proposed method firstly selects two diagonal points to crop a region of interest (ROI) on the original image. Then, histogram equalization, bilateral filter and pyramid mean shift filter are adopted to enhance the image. The cropped image is divided into many superpixels using simple linear iterative clustering (SLIC). Furthermore, some features are extracted from the superpixels and a bag-of-words model can be created. The initial classification can be obtained by a back propagation neural network (BPNN). To refine preliminary result, k-nearest neighbor (KNN) is used for reclassification and the final result is achieved. To verify the proposed method, we collected a BUS dataset containing 320 cases. The segmentation results of our method have been compared with the corresponding results obtained by five existing approaches. The experimental results show that our method achieved competitive results compared to conventional methods in terms of TP and FP, and produced good approximations to the hand-labelled tumor contours with comprehensive consideration of all metrics (the F1-score = 89.87% ± 4.05%, and the average radial error = 9.95% ± 4.42%). Image, graphical abstract [ABSTRACT FROM AUTHOR]

• The original SAE is expanded to suit with the multiplicative noise in SAR change detection. • The features extracted by SFAE are more discriminative than the original stacked autoencoder due to that Fisher discriminant criterion is incorporated into SFAE. • Experiments on the simulated and real SAR datasets reveal that the proposed SFAE algorithm is effective on multitemporal single/multi-polarization SAR change detection. Specifically, the proposed SFAE method is obviously superior to the real-time methods on detection accuracy and the non-realtime methods on computational complexity. Stacked autoencoder is effective in image denoising and classification when it is used for synthetic aperture radar (SAR) change detection. However, the resulting features may not be discriminative enough for in some sense. To alleviate this problem, in this paper we propose a stacked Fisher autoencoder (SFAE) for SAR change detection. Specifically, in the framework of SFAE, unsupervised layer-wise feature learning and supervised fine-tuning are jointly performed when training the network. The trained network can be used to detect the changes in both of the single and multi-polarization SAR datasets in real-time. The proposed SFAE has two advantages. The first one is to expand the stacked autoencoder to suit the environment with the multiplicative noise in SAR change detection. The second is that the features extracted by SFAE are more discriminative than the original stacked autoencoder due to that Fisher discriminant criterion is incorporated into SFAE. The results on the simulated and real SAR datasets indicate that the proposed SFAE algorithm has a significant advantage on multitemporal single/multi-polarization SAR (SAR/PolSAR) change detection. [ABSTRACT FROM AUTHOR]

As a local invariant feature of videos, the spatiotemporal interest point (STIP) has been widely used in computer vision and pattern recognition. However, existing STIP detectors are generally extended from detection algorithms constructed for local invariant features of two-dimensional images, which does not explicitly exploit the motion information inherent in the temporal domain of videos, thus weakening the performance of existing STIP detectors in a video context. To remedy this, we aim to develop an STIP detector that uniformly captures appearance and motion information for video, thus yielding substantial performance improvement. Specifically, under the framework of geometric algebra, we first develop a spatiotemporal unified model of appearance and motion-variation information (UMAMV), and then a UMAMV-based scale space of the spatiotemporal domain is proposed to synthetically analyze appearance information and motion information in a video. Based on this model, we propose an STIP feature of UMAMV-SIFT that embraces both appearance and motion variation information of the videos. Three datasets with different sizes are utilized to evaluate the proposed model and the STIP detector. We present experimental results to show that the UMAMV-SIFT achieves state-of-the-art performance and is particularly effective when dataset is small. [ABSTRACT FROM AUTHOR]

We focus on spatially-extended networks during their transition from short-range connectivities to a scale-free structure expressed by heavy-tailed degree-distribution. In particular, a model is introduced for the generation of such graphs, which combines spatial growth and preferential attachment. In this model the transition to heterogeneous structures is always accompanied by a change in the graph’s degree-degree correlation properties: while high assortativity levels characterize the dominance of short distance couplings, long-range connectivity structures are associated with small amounts of disassortativity. Our results allow to infer that a disassortative mixing is essential for establishing long-range links. We discuss also how our findings are consistent with recent experimental studies of 2-dimensional neuronal cultures. [ABSTRACT FROM AUTHOR]

The article discusses various reports published within the issue including the two schemes for Bidirectional Texture Function (BTF) data and a statistical method for choosing image patches for object detection and classification.

The work presented here solves the multi-sensor centralized fusion problem in the linear Gaussian model without the measurement noise variance. We generalize the variational Bayesian approximation based adaptive Kalman filter (VB_AKF) from the single sensor filtering to a multi-sensor fusion system, and propose two new centralized fusion algorithms, i.e., VB_AKF-based augmented centralized fusion algorithm and VB_AKF-based sequential centralized fusion algorithm, to deal with the case that the measurement noise variance is unknown. The simulation results show the effectiveness of the proposed algorithms. [ABSTRACT FROM AUTHOR]