Search

Closed-circuit television (CCTV) videos provide important data for intelligent control systems; however, sensitive information such as human faces and vehicle license plates must be de-identified by a de-identification framework before such videos are used. Previous research has mainly focused on enhancing the performance of de-identification methods, and only a few are devoted to detecting sensitive information. To address this issue, this study proposes an artificial intelligence-based sensitive information de-identification framework. The framework detects objects and utilizes their structural information to estimate the relative position of sensitive data, followed by the de-identification process. To enhance the recall of the detection module, this study analyzes difficult-to-detect faces and license plates in CCTV videos and proposes relative position estimation methods. These methods minimize the possibility of sensitive information leakage while reducing the number of locations of sensitive information that need to be annotated. When evaluated using actual urban CCTV videos, the recall of the framework was 84.63%, which is 33.01% higher than that of the conventional algorithm. [ABSTRACT FROM AUTHOR]

Camera-based indoor localization is a fundamental aspect of indoor navigation, virtual reality, and location-based services. Deep learning methods have exhibited remarkable performance with low storage requirements and high efficiency. However, existing methods mainly derive features implicitly for pose regression without considering explicit structure information from images. This paper proposes that incorporating such information can improve the localization performance of learning-based approaches. We extract structure information from RGB images in the form of depth maps and edge maps and design two modules for depth-weighted and edge-weighted feature fusion. These modules are integrated into the pose regression network to enhance pose prediction. Furthermore, we employ a self-attention module for high-level feature extraction to augment the network capacity. Extensive experiments are conducted on the publicly available 7Scenes and 12Scenes datasets, and the results demonstrate that the proposed method achieves high localization performance, with an average positional error of 0. 19 m and 0. 16 m , respectively. The code for this work is available at https://github.com/lqing900205/structureLoc. [ABSTRACT FROM AUTHOR]

• The structure and transport properties of molten Na 2 CO 3 -K 2 CO 3 salts are studied by machine learning molecular dynamics. • Deep potential models are trained on first-principles data and can accurately describe interatomic interactions. • The DP model achieves DFT-level precision, reproducing structural results from FPMD simulations. • Detailed structural information on the radial and angle distributions of ions is introduced. • The DP model is a more accurate predictor of properties than the empirical potential models. Molten Na 2 CO 3 -K 2 CO 3 binary salts have shown promise as electrolytes for fuel cell technology. Extensive investigations of the local structure and transport properties of these melts have been conducted via experiments and molecular dynamics (MD) simulations. With advancing machine learning capabilities, deep learning strategies are being widely incorporated into MD to generate highly accurate machine learning (ML) potentials. In this work, first-principle-derived Deep Potential is applied to study Na 2 CO 3 -K 2 CO 3 melts at specified temperatures. A deep neural network acts to fit the first-principle data and produce the model. This model enables large-scale MD simulations with accuracy comparable to density functional theory (DFT). The local structure is analyzed. Temperature and concentration impacts on ion arrangements are observed. The concentration effect has little influence on the melt structure, but the radial and angular distributions between the ions are strongly affected by temperature. Density, viscosity, and diffusion values predicted by the DP model agree closely with experimental measurements. In comparison to conventional empirical potentials, the DP model demonstrates DFT-level accuracy for structural analysis and experimental-level property predictions. This study provides detailed insights into the microstructure and transport properties of Na 2 CO 3 -K 2 CO 3 melts via the power of the DP model, showcasing their ability to advance understanding of complex molten salt systems. Meanwhile, a molten salt database is initially constructed using machine learning strategies. [ABSTRACT FROM AUTHOR]

Graph-based unsupervised feature selection methods have successfully processed high-dimensional data since they can effectively preserve data structure information. However, most existing methods are facing two challenges: (1) it is unreliable to exploit the intrinsic spatial structure from raw data because of the existence of redundant information and noise; (2) they only consider the first-order similar information but ignore the high-order similar information (i. e., samples with similar neighborhood network structure should be similar to each other). This study proposes an unsupervised feature selection with high-order similarity learning (HSL) to tackle the above problems. The projection matrix, first-order similar information, and high-order similar information are simultaneously learned in a unified framework, such that the intrinsic structure information can be exploited in the clean data that come from a latent low-dimensional embedding subspace. Specifically, we project raw data into a low-dimensional embedding subspace to effectively eliminate redundant information and noise. Moreover, we simultaneously consider the first-order similarity and the high-order similarity in the low-dimensional embedding space so that a better graph Laplacian matrix can be learned to fully preserve the intrinsic structure information of raw data and simultaneously utilize the label information. Furthermore, we design an effective optimization algorithm to tackle the proposed HSL. Comprehensive experiments on real-world datasets verify the superiority and effectiveness of HSL. [ABSTRACT FROM AUTHOR]

Detecting fine-grained changes among a set of images taken at different times is a challenging problem, which is important for the applications such as high-value scene monitoring and structural inspection. Existing methods use a geometry registration and lighting compensation pipeline to alleviate the ingredients that affect change detection. However, lighting compensation may introduce a lot of artifacts, e.g., inaccurate local lighting conditions and fine-grained change disappearance. The distortion introduced by general registration methods also makes the process of lighting correction more challenging. To solve these problems, in this paper, we propose a new phase-based change detection method, called as pb-FGCD, which first aligns two observation of different times and then extract structure information to handle lighting difference. Benefiting from the proposed weighted amplitude filter and iterative alignment strategy, we could obtain a better registration performance. The structure information extracts the lighting irrelevant components of an image and is more sensitive to structure changes compared with the lighting compensation based method, which is vital for detecting the changes with low intensity difference. Furthermore, we contribute a new change detection dataset, which contains 100 groups of the real-world data of the ancient Mogao murals and the Terra-Cotta. It is the first fine-grained change detection dataset focusing on the ancient mural. Our approach significantly improves the accuracy by more than 190% higher F1-measure than the state-of-the-art methods. • A novel fine-grained change detection framework. • A novel phase-based fine-grained registration method. • Finding structural information effective for fine-grained change detection. • Building a real-world dataset for fine-grained change detection. • Increasing the F1-measure by more than 190% over those state-of-the-art methods. [ABSTRACT FROM AUTHOR]

[Display omitted] • Introduce capsule network for multi-focus image fusion. • Utilize structure information to help locate focus regions. • Design structure-guided flow module to integrate structure features. Existing deep learning based methods have shown their advantages in multi-focus image fusion task. However, most methods still suffer from inaccurate focus region detection. In this paper, we employ the property of part-whole relationships embedded by the Capsule Network (CapsNet) to solve the problem. Specifically, we introduce CapsNet in multi-focus image fusion task, and design a structure-guided flow module, which fully utilizes structure information to help locate focus regions. CapsNet is introduced to extract structure features by supervising gradient information of the image. Compared with traditional convolutional neural networks (CNNs), CapsNet takes into account the correlation of features from different positions, such that it encodes more compact features. Once structure features are obtained, a flow alignment module is introduced to learn flow field between structure and image features, and propagate effectively structure features to image features to make confident focus region detection. Experimental results show the proposed method achieves robust fusion performance on three publicly available multi-focus datasets, and outperforms or is comparable to the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Graph neural networks (GNNs) are the dominant paradigm for modeling and handling graph structural data by learning universal node representation. The traditional way of training GNNs depends on a great many labeled data, which is time-consuming and money-consuming. In some special scenes, it is even unavailable and impracticable. Self-supervised representation learning, which can generate labels by graph structural data itself, is a potential approach to tackle this problem. And turning to research self-supervised learning problems for heterogeneous graphs is more challenging than dealing with homogeneous graphs, there are fewer studies about it as well. In this paper, we propose a SE lf-supervised learning method for heterogeneous graph via S tructure I nformation based on M etapath (SESIM). Firstly, the pseudo-labels are constructed to train pretext tasks, using data itself and avoiding time-consuming manual labeling. Afterward, we use traditional graph neural networks to aggregate node features, obtaining the node embeddings. And then, the primary task and pretext tasks are designed by these node embeddings. The pretext tasks, i.e., jump numbers prediction between nodes in each metapath, can improve the representation ability of the primary task. Moreover, predicting jump numbers in each metapath can effectively utilize graph structural information, which is the essential property of nodes. Therefore, SESIM deepens the understanding of models for graph structure. At last, we train the primary task and pretext tasks jointly and balance the contributions of pretext tasks for the primary task. The key advantage of our proposed model is that we research self-supervised learning for the heterogeneous graph to address the time-consuming and money-consuming problem of obtaining labels. And we design a novel pretext task, i.e., jump numbers prediction in each metapath, via graph structural information based on the metapath. Empirical results validate the performance of the SESIM method and demonstrate that this method can improve the representation ability of traditional neural networks on link prediction tasks and node classification tasks. • The self-supervised information is generated by jump number prediction in each metapath which bases on the graph structure. • We apply self-supervised learning based on metapath on heterogeneous graphs. • The experimental results show that the pretext tasks can improve the performance of primary task and representation power of GNNs. [ABSTRACT FROM AUTHOR]

• The local structure and properties of LaCl 3 melt are studied using machine learning potential. • The machine learning potential enables higher efficiency and similar accuracy relative to DFT. • The machine learning potential can yield precise descriptions of local structure and properties. It has been known for many years that mixtures of lanthanum chloride (LaCl 3) with alkali chlorides in spent nuclear fuel show severe departures from ideality. To go deep into this non-ideality, the local structure of molten LaCl 3 was investigated by experiments and classic molecular dynamics simulations. However, there appears to be some controversy concerning conclusions of these research methodology such as coordination numbers of the first coordination shell. In this work, interatomic potential driven by machine learning is developed based on data sets generated by ab initio calculations in order to research the local structure and property of molten LaCl 3 at 1200 K, 1300 K, 1400 K and 1500 K. The machine learning potential enables higher efficiency and similar accuracy relative to DFT and yields precise descriptions of microstructures and properties. Microstructural evolution with target temperatures is analyzed through partial radial distribution functions, coordination numbers, angular distribution functions and total neutron structural factors. We observe short- and intermediate-range order and the latter disappears at high temperature. The sevenfold and eightfold coordinated structures are dominant in LaCl 3 melt and the network structure is composed of corner-sharing, edge-sharing and face-sharing configurations. Evolution of properties including density and self-diffusion coefficient over the entire operating temperature range are documented. This work exhibits a thorough understanding of the local structure and property of LaCl 3 melt and reveals the accuracy of machine learning potential on molten trivalent metal chlorides for first time. [ABSTRACT FROM AUTHOR]

Abstract: Raman-based technologies have proved to be excellent tools for on-site and in-vivo analysis, due to the non-invasive nature of their detection, their capability of providing structure information, their high tolerance to aqueous samples, the ultra-sensitivity of surface-enhanced Raman scattering (SERS) and resonance Raman scattering (RRS), the high spatial resolution of tip-enhanced Raman scattering (TERS), and the ultrashort spectra-acquisition time for coherent anti-Stokes Raman scattering (CARS) and stimulated Raman scattering (SRS). In this review, we highlight the recent success of Raman-based technologies in various applications, including: [(1)] on-site surface analysis and chemical-reaction monitoring; [(2)] on-site identification of cultural objects, archeological studies and planetary science; [(3)] in-vivo analysis of cells and microorganisms; [(4)] in-vivo diagnosis inside human and animal bodies; [(5)] in-vivo fast Raman imaging and mapping; [(6)] the study of SERS processes; and, [(7)] assessment of nanomaterial safety. [Copyright &y& Elsevier]

The purpose of multiple kernel learning (MKL) is to learn an appropriate kernel from a set of predefined base kernels. Most of the MKL methods follow the basic idea of support vector machine (SVM) to learn the optimal weights of base kernels and build the used classifier. However, SVM is a local method and ignores the structure information of the data in that its solution is exclusively determined by the so-called support vectors. In the paper, we propose an improved SVM-based MKL method called minimum class variance multiple kernel learning (MCVMKL). The key characteristic of MCVMKL is that it exploits the ellipsoidal structure of the data during learning the optimal weights and building the classifier. Besides, its formulation is invariant to scalings of the weights of base kernels. We develop two optimization strategies to handle the optimization model of MCVMKL. Further, we derive a rough upper bound for the objective function of MCVMKL and propose a variant called trace-constrained multiple kernel learning (TCMKL) by using the trace of the within-class scatter matrix. TCMKL enlarges the margin between different classes and simultaneously shrinks the region covering the data as much as possible. Moreover, it can automatically tune the regularization parameter and so saves the training time due to avoiding using the time-consuming cross-validation technique to select an appropriate regularization parameter. Finally, the comprehensive experiments are conducted and the results demonstrate that the proposed methods are effective and can achieve better performance over the competing methods. • We propose an improved MKL method, which exploits the ellipsoidal structure of the data. • We develop two optimization strategies to handle the optimization model of the proposed method. • We discuss a variant that can automatically tune the regularization parameter. • We conduct the comprehensive experiments to evaluate the effectiveness of the proposed methods. [ABSTRACT FROM AUTHOR]

• The structure parameter is applied to quantify the shape of the target. • Long-term and short-term observations-based Bayesian infers the target shape. • The structure-based method achieves excellent target tracking capability. The tracking of infrared small target may be unstable due to the interference of background clutter and imaging noise. Moreover, the changing target appearance could degrade the tracking robustness. How to estimate the target spatial-temporal structure is the key to enhance the tracking stability for appearance changing small target under heavy clutter. This paper proposes a robust target tracking algorithm based on sparse representation and Bayesian inference that can estimate and predict the target spatial-temporal structure. Firstly, the small target signal is sparsely decomposed on the generalized Gaussian target over-complete dictionary (GGTOD). In this way the spatial structure information of small target is extracted from the noised and clutter contaminated infrared image. Then, according to the long term observations the long term temporal-spatial structure distribution of the target is established. Meanwhile the short term target temporal-spatial structure distribution is built according to the short term observations. Finally, the long term structure distribution and the short term structure distribution are combined by Bayesian inference to estimate and predict the target temporal-spatial structure in the next frame. By estimating the temporal change of target spatial structure, the proposed method achieves outstanding adaptability to the changing small target and robustness to clutter disturbance. Experiments on various infrared sequences show that the proposed method not only can estimate and predict the temporal-spatial structure of small target accurately but also can track the appearance changing small target stably under the inference of heavy clutter and noise. [ABSTRACT FROM AUTHOR]