Search

For image denoising, this paper proposed CEANet which had a dual-channel dilated convolution with attention mechanism to solve the problem of information loss caused by deep neural network. Reserving block merged output feature maps of each layer to make up the loss of detail information during convolution. Dilated convolution achieved better balance between denoising performance and efficiency,extracting more features with less parameters and enhancing the representation capability of the model for noisy images. The sparse module of dilated convolution expanded the receptive field to extract significant structural information and edge features and recover details of complicated noisy images. The feature enhancement module based on attention mechanism further guided network for image denoising by fusing global features with local features. The experimental results show that CEANet achieves high peak signal-to-noise ratio and structure similarity mean value at Gaussian white noise level of 25 and 50, which can capture image detail information more efficiently and has better performance in edge retention and noise suppression. Through the above comparative experiments proved the effectiveness of the algorithm framework. [ABSTRACT FROM AUTHOR]

Expert recommendation is one of the research hotspots in the online Q&A community. However, the majority of the currently used algorithms concentrate on matching user's static interest and question information, ignoring the efficient capture of user' s dynamic interest representation information, which results in a lack of recommendation accuracy. In order to address the aforementioned issues, this paper proposed an expert recommendation algorithm for the Q&A community that incorporated multi-head self-attention. Firstly, this algorithm built out question encoders of convolutional neural networks and attention mechanisms to process target question and user' s historically answered questions, in order to extract the corresponding question representations. Secondly, it treated the sequence of user's historically answered questions as a time series and used the multi-head self-attention mechanism to learn the dynamic interest representations hidden in the sequence, and combined with the user' s static interest representations to obtain the user' s comprehensive interest representations. Finally, it calculated the similarity between the target question representation and the comprehensive user representation to generate recommendation results. Based on the real data from the Zhihu Q&A community, the experimental results show that the performance of this algorithm is significantly better than the current popular expert recommendation algorithm. [ABSTRACT FROM AUTHOR]

High-quality learning low-dimensional representation of nodes in the graph is a current research hotspot. The existing shallow model methods cannot capture the nonlinear relationship of the graph structure, and the graph convolution model in the graph neural network technology will cause an over-smoothing problem. At the same time, how to determine the role of different hop number relationships in graph representation learning is also a problem that needs to be solved in the research. To solve the above problems, this paper proposes a deep learning model based on T（T＞1） feedforward neural networks. The framework uses deep learning models to extract the nonlinear relationship of the graph structure, and T sub-models effectively capture the local and global（higher-order） relationship information of the graph, and they give different roles in the final vector representation to take advantage of different hop relations. Experimental results on vertex classification and link prediction tasks show that the framework is competitive with existing methods, the benchmark algorithm can be improved by about 20%. [ABSTRACT FROM AUTHOR]

Using the average method and the voting method as a combination strategy can't make full use of the effective information of the base classifiers in ensemble learning, and the weights of base classifiers set with the volatility are imprecise and inappropriate. The above problems will reduce the effect of ensemble learning. In order to further improve the performance of ensemble learning, this paper proposed an ensemble learning method, which used evidence reasoning (ER) rules as a combination strategy and used diversity empowerment method set up the weights of the base classifiers. Firstly, the model used multiple deep learning models as the base classifiers and the ER rules as the combination strategy to construct the basic structure of ensemble learning. Then, it calculated the differences of each base classifier with respect to other base classifiers by the diversity measure method. Finally, it used the results of the differences normalization of the base classifiers as the weights of the base classifiers. Through the classification experiments of multiple image datasets, the experimental results show that the proposed method is more accurate and stable than other methods, which proves that this method can make full use of the effective information of the base classifiers, and the diversity weighting method is more accurate. [ABSTRACT FROM AUTHOR]

As a key problem and hub link between problem discovery and problem solving, the current research on root cause analysis mainly includes two types of methods: data-driven and causality-driven. In view of the advantages of data-driven methods in narrowing the range of root causes, at present, root cause research mainly focusses on datadriven methods such as association rule mining, heuristic search, machine learning and deep learning. There are few root cause analysis from the perspective of causal knowledge, nor has it been based on method dimension. The inductive analysis of the root cause is carried out, and there is a lack of relevant research results. Therefore, this paper sorts out and summarizes the main results of root cause analysis in recent years, analyses the differences and advantages of root cause analysis under different method dimensions, and proposes a root cause analysis method that integrates causal knowledge, and combines asymmetric Shapley value with causal chain diagram to improve the accuracy of root cause analysis. Finally, the existing some research difficulties and development trends put forward scientific and meaningful future research directions. [ABSTRACT FROM AUTHOR]

Machine reading comprehension is one of the research hotspots in the field of natural language processing, it is of great significance to improve the reading ability and intelligence level of the machine. In order to follow up the research progress in related fields, this paper reviewed it. Firstly, this paper introduced the development process and main tasks of machine reading comprehension. Secondly, it focused on the current work of multi-choice machine reading comprehension based on deep learning methods, and described the related work from four aspects: semantic matching, pre-training model, semantic reasoning and external knowledge. Next, it summarized the related datasets and evaluat ion metrics . Finally, this paper looked forward to the future development trend of multi-choice machine reading comprehension. [ABSTRACT FROM AUTHOR]

Multi-modal medical image segmentation is one of the research hotspots in the field of medical image analysis. Effectively using the complementary information of different modal images to provide more information about the focus area and its surrounding area from multiple levels can improve the accuracy of clinical diagnosis. In order to analyze the research status and development direction of deep learning in the field of multi-modal medical image segmentation, this paper sorted and studied the segmentation methods in this field in recent years. Based on the analysis of their characteristics and existing problems, this paper prospected the future research direction, which could help relevant researchers comprehensively and quickly understand the research status, existing problems and future research direction in this field. [ABSTRACT FROM AUTHOR]

The study heartbeat model based on Van der Pol equation is beneficial to heartbeat control and offering therapy guidance of cardiac diseaes such as arrhythmia. To cope with the issue that the timescale of the solutions produced by Van der Pol equation is different from those of real living beings, this paper introduced a timescale parameter into the Van der Pol equation. To solve the problem of numerical simulation of rhythm model, this paper proposed a deep neural network algorithm. To avoid spurious solutions caused by existing neural network algorithms, this paper proposed a new sampling strategy to construct training data sets. To further improve the accuracy, this paper introduced an adaptive sampling means into the proposed sampling strategy. This paper conducted numerical experiments and compared numerical solutions given by Runge-Kutta method with results of the proposed method. The results show that the maximum mean error of the proposed method is below 0. 3 %. Furthermore, this paper employed the deep neural network method to simulate the action potential of the cardiac pacemaker cell. The results show that the proposed method can simulate the action potential fairly well. [ABSTRACT FROM AUTHOR]

In order to improve the search ability of AGV in complex unknown environment, this paper proposed an improved DDPG. It constructed the empirical playback matrix and double-layer network structure to improve the convergence speed of the algorithm ε-greedy in the green search strategy, to solve the local optimization problem of AGV in selecting the optimal action. To solve the problem of slow training speed of deep neural network, it applied priority sampling to depth deterministic strategy gradient algorithm. In order to solve the problem of high complexity of ordinary priority sampling, this paper proposed a small batch priority sampling method to train the network. In order to verify the effectiveness of the method, it used the grid method to model and compare the simulation experiments in different complex environments. It compared the loss function, iteration times and return value of different algorithms. The experimental results show that compared with the original algorithm, the improved algorithm reduces the loss function, reduces the number of iterations and increases the return value, which verifies the effectiveness of the algorithm. At the same time, it provides a new idea for AGV to complete the planning task more safely and quickly in complex environment. [ABSTRACT FROM AUTHOR]

With the rapid development of computer vision, human action recognition has shown its wide application prospects and research value in many fields such as video surveillance, video retrieval, and human-computer interaction. Human action recognition involves the understanding of image content, and the progress of practical applications is slow due to the complexity and diversity of human postures and the occlusion factors of the background. This paper comprehensively reviewed the development of human action recognition, and deeply explored the research methods in this field, including traditional manual feature extraction methods and deep learning-based methods, as well as the recently popular graph convolutional network（GCN）-based method. And this paper systematically summarized these methods according to the data types they used. In addition, for different data types, it introduced some popular action recognition datasets, compared and analyzed the performance of various methods on these datasets. Finally, this paper summarized the review, and prospected the future research direction of human action recognition. [ABSTRACT FROM AUTHOR]

The image rain removal algorithm analyzes and processes rain images to remove rain streaks and restore clean background scenes, which helps to improve the recognition accuracy of computer vision task, so that it becomes a hot spot in current research. In order to systematically understand the current research status and development trends in this field. Firstly, this paper introduced some typical synthetic rain models. Secondly, it analyzed typical image rain removal algorithm models and methods from two aspects, such as model-driven and data-driven. Then it compared the algorithm evaluation metrics and public rain datasets respectively. Finally, this paper prospected the future development trend of single image rain removal algorithms. [ABSTRACT FROM AUTHOR]

Traditional manually designed feature descriptors are prone to cause a large number of mismatches in the face of multi temporal remote sensing images with large geometric and radiation differences and obvious changes in ground features. This paper developed a convolutional neural network matching algorithm with double screening and proposed double constraints to extract the deep semantic feature map of the image through CNN, it selected the key points that satisfied both the priority maximum principle and the precise extreme value principle from the feature map, and extracted 512-dimension descriptors from the corresponding positions. In the feature matching stage, the strategy of combining the rough to fine reverse matching constraints and RANSAC constraints ensured that the false matching points were eliminated effectively, and retained a certain number of correct matching points, which improved the matching accuracy. The experimental results show that the number of matches is moderate, the correct matching rate is improved compared with other algorithms selected in the experiment, and the image registration error is reduced by about 2 pixels. The running time is obviously improved, matching effect is good, with certain adaptability and robustness. [ABSTRACT FROM AUTHOR]

Single-view 3D reconstruction based on deep learning is a research hot spot at present. In order to discover more high-frequency details, SDF-SRN algorithm introduces positional encoding, but neural network is easy to overfit without accurate supervision, and reconstructs uneven surface. To solve the problem, this paper proposed the network model based on sparse feature. The model enabled the network that preferred to overfitting to predict high-frequency residual by residual learning. The feature extraction network extracted sparse features and the global features. Then one hypernetwork took the sparse features as input and generated prediction shallow head. This shallow head predicted low-frequency part of signed distance function. Another hypernetwork took global features as input and generated another shallow head. This shallow head predicted high-frequency residual. It fused two predictions of shallow heads into final signed distance function. Spectrum analysis shows that the design purpose of network is achieved. Compared with other smooth surface reconstruction schemes, the network can achieve smoother surface reconstruction with enough details. It overcomes the overfitting of SDF-SRN. The qualitative and quantitative comparison with other advanced single-view reconstruction approaches show the superiority of the proposed approach. [ABSTRACT FROM AUTHOR]

To solve the insufficient mining problem of semantic correlation information within a single modality in the unsupervised cross-modal retrieval task, this paper proposed an unsupervised cross-modal hash retrieval (UCMHR) method based on GCN. It obtained the features of the two modalities through the image and text encoders, respectively, input the features into the GCN to exploit the single intra-modal semantic information. Then it calculated the loss by comparing with the deep semantic correlation similarity matrix, so the generated binary codes were continuously reconstructed and optimized until the robust hashing expression corresponding to the samples was generated. The experimental results show that the cross-modal retrieval accuracy of this method on multiple datasets improves significantly, compared with the classical shallow methods and deep-learning methods. It is proved that the semantic information within the modality can be further mined through the graph convolutional network, the proposed model has higher accuracy and robustness. [ABSTRACT FROM AUTHOR]

Rain streaks and fog brought by rain can degrade the quality of images taken outdoors. In order to remove the in-fluence of rain and fog on images, this paper proposed an image derain method based on rain and fog separation processing and multi-scale convolutional neural network. Firstly, it extracted the rain lines and image details to the high frequency layer using guided filtering, while separated the fog and background information to the low frequency layer. Then it constructed a multi-scale convolutional neural network to remove the rain lines in the high frequency layer, and incorporated multiple dense connection modules into the network to improve the accuracy of feature extraction. Secondly, it constructed a lightweight defogging network with multi-layer feature fusion to remove the fog in the low frequency layer, and used the parameter integration structure to avoid estimation of multiple atmospheric scattering model parameters resulting in sub-optimal solutions. Finally, it combined the processed high and low frequency results to restore a clear image. Tested on several synthetic rain and fog datasets as well as on real natural scene images, the qualitative and quantitative results show that the proposed method removes rain and fog while retaining color information well, and improves the image structure similarity by 0. 02 to 0. 08 and the image peak signal-to-noise ratio by 0. 2 to 3. 5 dB compared to recent algorithms. [ABSTRACT FROM AUTHOR]

To tackle the problem that existing pan-sharpening networks cannot preserve spatial information and spectral information simultaneously, this paper proposed a pan-sharpening network guided by wavelet coefficients, which consisted of fusion network and guidance network. The fusion network extracted the multi-level features of PAN and MS images respectively, and performed feature selection and fusion at the same level. The fused features guided the extraction of features at the next level. The guidance network learned the mapping relationship between the wavelet coefficients of the input LRMS/PAN images and HRMS image, and provided extra supervision for the output of the fusion network. Experimental results show that the proposed network can recover as much spatial information as possible while preserving the spectral information of MS images. Comparison experiments on simulated datasets and real datasets also show that the fusion effect of the proposed method is better than other traditional methods and deep learning methods, which has certain value in practice. [ABSTRACT FROM AUTHOR]

In view of the problems that select cross entropy as a loss function in a graph convolution network may lead to the over-training and the weak generalization ability of the model in a small sample data sets, this paper proposed a graph convolution network based on structural error. Using the improved support vector machine (SVM) as the classifier of the graph convolution network could reduce the risk of over-fitting of the model. Based on the generalization error theory of SVM,improving the loss function of SVM,the proposed method maximized the interval of different samples and limited the interval of similar samples, improved the generalization ability of the model. Firstly, it calculated the average distance from the feature vector to the center point in the feature space, used it to approximately replace the radius of the sphere, and then the new loss function would guide model learning. Experiments on the NTU RGB+D60 and NTU RGB+D120 datasets in the field of behavior recognition based on skeleton prove that compared with the traditional graph convolution network model, the proposed method can obviously improve the recognition accuracy and has better generalization performance. [ABSTRACT FROM AUTHOR]

In order to improve the safety of pedestrian interaction in complex traffic scenes, this paper proposes a pedestrian trajectory prediction algorithm SAN-GAN (Social Angle Norm-GAN) based on Social-GAN network (Social-Generative Adversarial Network). The algorithm first takes the pedestrian’s historical location information and head information as input, obtains the hidden feature information of the pedestrian through the trajectory generator LSTM network (Long Short Term Memory Networks), captures the dynamic changes of the pedestrian’s visual field based on the pedestrian visual field module, builds a fan-shaped visual field for all pedestrians and filters the valid information, thus driving the neural network model to predict future trajectory changes of pedestrians. By comparing SAN-GAN with LSTM, Social-LSTM (Social-Long Short Term Memory Networks), Social-GAN and other trajectory prediction algorithms, The results show that the SAN-GAN algorithm reduces the ADE by an average of 65.8%, 51.2% and 10.7%, and the FDE by an average of 73.6%, 60.9% and 10.4%, respectively, in predicting the pedestrian trajectory for 3.2 s. The SAN-GAN is effective in predicting the future trajectory of pedestrians interacting in complex traffic environments compared to other algorithms. [ABSTRACT FROM AUTHOR]

As a deep learning method for extracting video spatio-temporal features, pseudo-3 D residual net（P3 D ResNet） uses the objective function of SVM to drive the learning of deep network. In this way, this method inherits the insufficiency of SVM, which only considers the interval between different categories, and ignores the distribution information of similar samples. Aiming at this problem, this paper proposed an improved method called P3 D ResNet based on minimum intra-class variance. This method not only embodied the principle of large interval, but also used the distribution information of sample data. Firstly, the method used the feature vector extracted by P3 D ResNet to calculate the intra-class divergence matrix. Then it used the matrix to construct a new objective function. Finally, it drove the learning of P3 D ResNet by the newly constructed objective function. This paper applied the method to the field of behavior recognition. Experimental results on multiple datasets show that compared with the traditional P3 D ResNet, the proposed method achieves higher recognition accuracy and shows better generalization performance. [ABSTRACT FROM AUTHOR]

The recommendation algorithm based on graph neural network can extract the association relationship between users and goods. Traditional methods can’t extract this relationship. At present, most of these algorithms ignore the general prefe-rences in the review data of users and products. In order to solve this problem, this paper proposed a new method. This me-thod used the graph neural network to extract association relations, and the advantage of deep learning to extract the general preferences, and carried out feature fusion to improve the recommendation effect. This paper conducted comparative experiments and ablation experiments on four sets of public data sets to verify the effectiveness of the proposed method. The evaluation indexes include the recall rate and normalized discounted cumulative gain. Experiments show that this method is more effective than the existing algorithms. The feature fusion of the two networks can improve the recommendation effect. [ABSTRACT FROM AUTHOR]

Aiming at the problem of fine-grained visual categorization, this paper proposed an effective algorithm to achieve end-to-end fine-grained visual categorization. The ECA module in ECA-Net was a channel attention mechanism with significant performance advantages. It model-fused with the classic network ResNet-50 to form the ResEca. Then, it used the object-level image positioning module and the part-level image generation module to generate object-level and part-level images. Those images combined with original images could be as the input of the new constructed network Tb-ResEca-Net. This paper trained the 95. 1% and 95. 3% respectively on the test set of the corresponding dataset. The experimental results show that this method has higher classification accuracy and stronger robustness compares with other traditional fine-grained classification methods, which is an effective fine-grained image classification method. [ABSTRACT FROM AUTHOR]

The success of open source software promoted the vigorous development of the software industry, and a large number of code resources have created conditions for code search. How to find the required code through code search technology has become an important issue. In order to better promote the follow-up research, firstly this paper introduced and explained the concept and research trend of code search. Secondly, it reviewed the research of code search using different technologies, including information retrieval, query and code description enhancement, program feature classification, and deep learning, and summarized the differences. Next, it introduced the application of code search technology in many fields, including program synthesis, code recommendation and completion, and code style improvement. Finally, this paper analyzed the main problems of code search in order to provide some references and suggestions for the future development of this direction. [ABSTRACT FROM AUTHOR]

Single object tracking( SOT) is a technique to analyze the motion status and provide localization of the single target by using target appearance and context information in video. It has promising applications in intelligent surveillance, intelligent interaction, navigation and guidance, etc. However, problems such as occlusion, background interference and appearance variation led to slow progress in practical applications. With the rapid development of deep learning in recent years, the study of using deep learning techniques to optimize SOT algorithm has become one of the hot spots in computer vision. Around the SOT algorithm based on deep learning, this paper respectively provided outline and analysis of each of the six aspects of correlation filter, Siamese networks, meta-learning, attention, recurrent neural networks and generative adversarial networks according to the core algorithms, after analyzing the basic principles of SOT. In addition, this paper summarized the current state of research and proposed the development trend and optimization ideas of the algorithms. [ABSTRACT FROM AUTHOR]

In the current software development environment, a large amount of low-quality and meaningless code knowledge hinders developers from code reuse, which greatly reduces the efficiency of software empolder. In order to quickly and accurately recommend high-quality code knowledge for developers, this paper proposed a code snippets recommendation method CSRSB based on SBERT model. Firstly, the method obtained massive high-quality data to build a code corpus. It also generated sentence vectors with rich semantics for the natural language description corresponding to the code snippets and the natural language query input by the user based on the deep learning model SBERT. Then, it implemented code snippets recommendations by comparing the dot product similarity. The effectiveness of the method was verified by comparing the three commonly used recommendation evaluation metrics, Hit Ratio, Mean Reciprocal Rank and Mean Average Precision, with the methods in existing related research. The experimental results show that CSRSB can effectively improve the accuracy of code snippets recommendation and can also achieve fast recommendations. [ABSTRACT FROM AUTHOR]

Most of the existing methods only connect multi-modal features, without considering the complex connection between modes. To overcome these limitations, this paper proposes an end-to-end model named factorized bilinear pooling for multi-modal fusion fake news detection. First, the algorithm effectively fuses the text and visual features captured by multi-modal feature extractor utilizing factorized bilinear pooling method, and then cooperates with fake news detector to classify posts as fake or not. The role of event classifier is to remove the event-specific features. Experimental results based on two multimedia datasets, Twitter and Weibo, demonstrate the effectiveness of the proposed algorithm. Experimental results show that the proposed algorithm can effectively fuse multi-modal data, narrow the heterogeneity difference between modes, so as to improve the accuracy of fake news detection. [ABSTRACT FROM AUTHOR]

Underwater imaging is affected by light scattering and absorption, water impurities, artificial light source and other factors, which leads to poor imaging quality. The enhancement and restoration of underwater images are of great significance to enhance the machine vision in underwater environment. In order to help researchers quickly grasp the research framework and tools in the field of underwater image processing, this paper reviewed the underwater image enhancement and restoration methods. First, this paper introduced the degradation types of underwater images. Then, it reviewed the classical methods and the latest progress of underwater image enhancement and recovery, and presented a brief overview of underwater image evaluation system and datasets. Finally, it prospected the research direction on underwater image enhancement and restoration. [ABSTRACT FROM AUTHOR]

In order to protect personal information in images, this paper proposed an adversarial image perturbations algorithm to combat deep neural network, which could mine and discover personal image knowledge. It transformed the problem of adversarial example generation into a multi-objective optimization problem with constraints. Considering the classification confidence of the neural network, the location of the perturbed pixels and the chromatic aberration, this paper obtained the adversarial examples iteratively by using the differential evolution algorithm. On MNIST and CIF AR-10 dataset, based on deep neural network LeN et and ResN et, the algorithm generated the experiment of adversarial examples. This paper compared and analyzed the success rate, number of perturbation pixels, optimization effects and spatial characteristics of the adversarial examples. The results show that the proposed algorithm still can effectively combat the deep neural network in the case of few disturbed pixels ( the average number of perturbation pixels is 5) . The algorithm significantly optimizes the location and chromatic aberration of the perturbed pixels, so as to protect personal information without destroying the original image. This study is helpful to balance the relationship between information technology dividend sharing and personal information security, and provides technical support for the research of adversarial examples generation and classification spatial features in deep neural networks. [ABSTRACT FROM AUTHOR]

Deep matrix factorization adopts deep nonlinear mapping to break through the bottleneck of bilinear relationship affecting the performance of the recommendation system in matrix factorization. However, it doesn't take into account users' preference for unrated items, and its recommendation performance isn't advantageous for large-scale data with high sparsity. This paper proposed a recommendation algorithm for fusing matrix completion and deep matrix factorization. First, it filled the unknown elements in the original scoring matrix by the matrix completion model. Then, based on the completed matrix, it constructed the latent vectors of users and items by deep learning model. Finally, this paper tested the proposed model on the MovieLens and SUSHI datasets. Experimental results show that the proposed algorithm significantly improves the performance of the recommendation system compared to deep matrix factorization. [ABSTRACT FROM AUTHOR]

When the scale of data is large, the deep learning model will encounter the problem of time-consuming weight adjustment and easy to fall into the local optimal solution. In order to solve these problems, broad learning system comes into being. The broad learning system not only has the advantages of simple structure, fast training speed and high accuracy, but also has the advantage of incremental learning. This paper firstly introduced the background and development of broad learning system, then described the basic theory and implementation method of broad learning system, and compared its similarities and differences with deep network. Then this paper introduced the improvement of broad learning system on image classification, numerical regression, EEG signal processing, and analyzed the advantages and disadvantages of these algorithms. Finally, it summarized the shortcomings of existing broad learning algorithms, and prospected the future research direction. [ABSTRACT FROM AUTHOR]

This paper presented an image dehazing method based on deep learning to solve the problem that the remote sensing images had reduced image sharpness due to haze. Firstly, this algorithm distorted the original atmospheric scattering model to get an end-to-end defrosting model. Then, it unified several unknown parameters to one parameter and estimated the unknown parameters by using multiscale convolution neural network. Finally, it brought the parameter estimates into the defrosting model to get a haze-free image. For no reference image dataset, this paper used the existing dataset to preliminary train the network, then added the self-built dataset to secondary train the network. The experimental results show that, compared with the related defrosting algorithms, the proposed algorithm improves the visual effect and objective index to some extent, and effectively improves the clarity of remote sensing images in haze weather conditions. [ABSTRACT FROM AUTHOR]

In order to improve the training speed and certain classification accuracy of CNN in the image classification, this paper started from BN, adjusted the affine transform of BN by adding new parameters, and proposed an improved BN, called BNalpha. Except fo r the neural networks with some specific structures, compared with the original BN, BNalpha could improve the training speed and certain classification accuracy of general neural networks without increasing the computational complexity. By analyzing and comparing the parameters of BN affine transform, this paper tried to explain the operation mechanism of BN partially, and conducted contrast experiment which covering different periods during training to illustrate that BNalpha was superior to the original BN. Based on the CIFAR-10 and CIFAR-100 datasets, by using various types of CNN structures, it compared and analyzed BNalpha and BN, and the experimental results verify that BNalpha can further improve the training speed and certain classification accuracy. [ABSTRACT FROM AUTHOR]

In order to improve the long-term prediction accuracy of PM2. 5, this paper proposed a TSMN (time series memory network) prediction model based on deep learning by taking air pollutants and meteorological factors as the influencing factors. The model consisted of two components. The local memory component used external memory to improve the long-range memory capacity of the model, and cooperated with the neighborhood component that modeled the multi-site spatial relationship to complete long-term prediction of PM2. 5 from the perspective of time and space. This paper compared the TSMN model with multiple models by using different evaluation indicators. Comparing the TSMN model with the better-performing CNN-1.STM model, the RMSE and MAE of this model goes down 5. 2% and 5. 7% respectively,and the R2 goes up 7. 5% . The experimental results show that the TSMN model can effectively improve the long-term prediction accuracy of PM2. 5 concentration. [ABSTRACT FROM AUTHOR]

The community detection method can mine hidden cluster structure in the network, which is of great significance for the analysis of the structure and function of complex network. In recent years, with the explosive growth of network data and the diversity of network evolution, a large number of methods and frameworks for community detection that can handle different scenarios have emerged. In order to deeply understand the research status and development trend, this paper reviewed the community detection methods. This paper firstly classified these algorithms, introduced each kind of algorithm in detail and made analysis and comparison, and then introduced some commonly used evaluation indicators and expounded the application scenarios. Finally, this paper looked forward to the future research directions of this field. [ABSTRACT FROM AUTHOR]

This paper constructed a new TerraSAR-X dataset named GDUT-Nansha and then proposed a new lightweight semantic segmentation algorithm using synthetic aperture radar images（ SAR）. It is difficult to apply traditional deep learning models to SAR datasets with small volume due to the tremendous amount of parameters. A revision scheme is, therefore, put forward to deal with such problem. This paper accomplished an improved lightweight convolutional neural network model named revised weighted loss ENet（ RWL-ENet） for SAR images. The current study introduced a weighted loss function to solve the problem of imbalance of training datasets. Compared with other classical convolution neural network models, the efficiency and robustness of the new dataset were validated. Meanwhile, RWL-ENet model attained 0. 884,0. 804, and 0. 645 in terms of three quantitative metrics, including pixel accuracy（ PA）, mean pixel accuracy（ m PA）, and mean intersection over union（ m IoU）. In addition, the parameters of this new proposed model are much less than other classic network models. [ABSTRACT FROM AUTHOR]

Aiming at the traditional model parallel methods for accelerating convolution neural network (CNN) tend to have low utilization, this paper proposed PipeCNN, which accelerated CNN with software pipeline. Firstly, this paper studied the forward propagation and back propagation, and then explored data correlation during training. Secondly, it parallelized CNN with the support of software pipeline, and then analyzed two feasible gradient updating methods in PipeCNN. Finally, it used circular queue to realize communication between two layers and then proposed a task allocation algorithm to divide CNN into working parts. Experiments show that the method can obtain good speedup and utilization while ensuring the accuracy of the model. It shows that software pipeline can effectively solve the problem of low utilization in model parallel, and accelerate the training of CNN. [ABSTRACT FROM AUTHOR]

As an important part of software, code comments play an important role in software maintenance, software re use . Automatic code comments generation technology aims to reduce the workload of manual comment, thus improving the efficiency of software development. Existing comments automatic generation methods can be categorized into rule-based, text summarybased, data-based, topic model-based, deep learning-based and other levels . This paper summarized the concept of automatic code comments generation, compared and summarized the various types of code comment automatic generation methods, sorted out and reviewed the research progress of code comment automatic generation in recent years. Finally, this paper analyzed the challenges of code comments automatic generation and look ed forward to the future research in this area. [ABSTRACT FROM AUTHOR]

To deal with challenges of limited and small-size defects in product quality inspection, this paper proposed a method for surface-defect-detection of small-size with few training samples (Smooth-DETR). This method utilized DETR-based encoder-decoder to predict the classification and location of defects, which reduced the parameters and complexity. DETR has a strong global feature learning capability, which could obtain rich texture features of product surfaces with few samples, so that it is easy to detect defects that break the continuity of texture. The combination of Smooth-L1 loss and GIoU loss improves the regression accuracy on small-size defect samples. Experimental results show that the proposed method performs better than the existing state-of-the-art methods. Moreover, the average detection precision of the proposed method for 11 different classes of surface defects is higher than 98% with few training samples. [ABSTRACT FROM AUTHOR]

Aiming at the poor classification effect caused by complex background, large intra-class difference and high interclass similarity in remote sensing scene images, this paper proposed an attentional mechanism and residual contraction unit algorithm based on supervised contrast learning. Firstly, the algorithm improved the effective channel attention mechanism (ECA), and optimized the extraction of image features to be recognized. Then, the algorithm proposed a cooperative residual shrinkage unit algorithm, which is used to filter and eliminate redundant information of images. In addition, supervised contrast learning algorithm was used to enhance the generalization ability of the algorithm. Finally, experiments were carried out with remote sensing image data set and compared with the latest algorithms such as enhanced attention algorithm and scale attention mechanism algorithm. Experimental results show that the proposed algorithm improves the classification accuracy by 1.75% and 2.5% in AID Data Set with 20% training ratio. [ABSTRACT FROM AUTHOR]

In view of the shortcomings of traditional salient target detection methods in detecting multiple salient targets at different scales. This paper presents a salient object detection algorithm with deep multiplexing of multi-scale features. The network model consists of vertically stacked bidirectional dense feature aggregation modules and horizontally stacked multiresolution semantic complementary modules. First, the bidirectional dense feature aggregation module extracts semantic features of different resolutions based on the ResNet backbone network, and then performs adaptive fusion on the top-down and bottom-up paths in turn to obtain multi-scale representation features at different levels; The multi-resolution semantic complementation module fuses the multi-scale features of two adjacent levels to eliminate the mutual crosstalk between features at different levels and enhance the consistency of prediction results. The experimental results on 5 benchmark datasets show that the method can achieve the highest Fmax, Sm, MAE of 0.939, 0.921, 0.028, and the detection rate can reach 74.6 fps, which has better detection performance compared with other comparison algorithms. [ABSTRACT FROM AUTHOR]

The traditional research on educational knowledge graph is mostly text-oriented and ignores the interpretation function of multimodal resources to educational knowledge and its rich characteristic representation. In order to better promote the follow-up research work, this paper reviews the educational knowledge graph from the perspective of multi-modal resources. Firstly, it introduces the concept and classification of knowledge graph. Secondly, it introduces the connotation of the educational knowledge graph, summarizes the definition, classification and construction framework of educational knowledge graph; Thirdly, combined with deep learning represented by neural network, it introduces the construction technology of educational knowledge graph. Finally, it summarizes the specific application of the educational knowledge graph, points out the problems existing in current research and future research directions. [ABSTRACT FROM AUTHOR]

Salient object detection (SOD ) aims at detecting the significant parts in the images automatically and efficiently, which plays an important role in computer vision tasks such as object detection and recognition, key points location, visual tracking, semantic segmentation and so on. This paper focused on a comprehensive review of salient object detection, which covered the closely related fields, models, datasets, applications and future directions. It introduced the relationship between salient object detection and closely fields at first. Then, it analyzed salient object detection algorithms in terms of flowcharts, ideas, innovations, performance as well as applicability. Thirdly, it introduced the public datasets which improving continuously with the development of the saliency detection models. Finally, it discussed a prospect of future researches and several real application scenes of salient object detection. [ABSTRACT FROM AUTHOR]

in order to get better performance of 3 D model retrieval and classification,this paper proposed the characterization of 3 D models by multi-modal information fusion,which based on deep-learning model.The method considered the correlation of different modalities in the training step for extracting a more robust feature vector,which benefitted from the proposed correlation loss function.In addition,it applied fusion features to 3 D model retrieval and classification.This paper evaluated the proposed method on the ModelNet40 dataset for 3 D models classification task and retrieval.The comparison between the experimental results and the existing methods proves the superiority of this method,which provides a new idea for the field of 3 D model retrieval and classification. [ABSTRACT FROM AUTHOR]

Traditional image inpainting algorithms cannot accurately capture high-level semantics when regions involve complex non-repetitive structures, such as faces. In the past three years, the method based on deep learning has been applied to image inpainting, and the structural similarity of the repair results had increased by more than 10% compared with the traditional methods. This paper firstly expounded the research and development process of facial completion technologies, mainly introduced the face repair algorithm based on deep learning, which was divided into unsupervised and supervised categories. In each category, it focused on the various facial completion algorithm ideas that had emerged in recent years. Then it summarized the six mainstream types of image datasets. Two evaluation indexes were summarized in this paper. Finally, it discussed the future research direction of facial completion technique. [ABSTRACT FROM AUTHOR]

In distributed video coding ( DVC ), generating high-quality side information and improving decoding performance in various sports scenes is a crucial research area. This paper proposed a deep learning optical flow interpolation ( OFI ) side information generation algorithm. The encoder used interval overlapped distributed arithmetic codes( DAC) to encode the video. The decoder extracted the decoded key frames and inputted them into the optical flow interpolation network for side information generation. The network used a multi-layer optical flow module to generate optical flow, and used the optical flow to warp key frames to generate a preliminary side information estimation, and then underwent a fusion process to eliminate occlusion to produce more refined results. Finally, the side information assisted the decoding tree to complete the decoding. The experimental results show that comparing with the existing method, the PSNR of this method increases up to 2. 25 dB, which happens mainly in the linear motion scenes. At the same time, the SSIM increases 0. 001 5 - 0. 064 8 in both linear and non-linear scenes. The decoded video rate-distortion curve shows consistent results. It proves that the algorithm can improve the estimation of linear motion side information, and it also has excellent robustness on the structure of non-linear motion side information. [ABSTRACT FROM AUTHOR]

Due to the low randomness of character distribution and high randomness of word combination in word-based DGA domain names, the traditional detection methods are difficult to identify them. The method based on deep learning such as LSTM can capture domain's sequence features, but it lacks the word combination features and has low detection accuracy. In order to solve above problems, this paper proposed a new DGA domain name detection method based on fusion embedding layer. In domain embedding stage, it carried out a fusion vector representation based on characters and word segmentation technology . Then, it constructed a hybrid deep learning model based on CNN and BiGRU. The experimental results show that the proposed model has increased by 3 . 1 % and 4. 3% respectively in accuracy compared with the models based on CNN or LSTM alone. When dealing with the matsnu, suppobox and ngioweb DGAs, the proposed model is more effective. [ABSTRACT FROM AUTHOR]

With the rapid development of deep learning and 3 D sensing technology, point cloud classification has been widely used in intelligent classification and other fields. In order to better promote the research and application of point cloud classification technology, this paper combed, analyzed and summarized the research progress of related methods systematically by using pipeline architecture. Firstly, according to the different point cloud data processing methods, it analyzed and summarized the existing point cloud classification methods into indirect point cloud based methods and direct point cloud based methods. Then, it introduced the representative methods and the latest research, compared and analyzed the core ideas, advantages and disadvantages, scope of application, application scenarios and experimental results of the main methods. Finally, it prospected the future development and research direction of point cloud classification from four aspects. The results show that 2D-3D feature fusion of indirect and direct point cloud methods is an important development direction in the future. [ABSTRACT FROM AUTHOR]

In order to solve the problem of mismatch in cross-domain medical image analysis, this paper proposed an UAL-DAF. Specifically, the framework used the ATM and the STM that combined conditional generative adversarial networks to reduce the differences in the appearance and semantic levels of cross-domain medical images, respectively. Finally, in the challenging medical image segmentation, the results are significantly better than existing methods. Therefore, the framework can extract the appearance and semantic level information of domain adaptation knowledge, and realize the collaborative integration of domain knowledge. [ABSTRACT FROM AUTHOR]

At present, super-resolution method based on CNN can obtain excellent results in the evaluation metric of peak signal- to-noise ratio and the structural similarity index, but the visual perceptual quality of super- resolution image is poor, and the details of the facial features are lost. In order to solve these problem, this paper designed a new deep neural network to predict the super-resolution wavelet coefficients to get clear super-resolution face images . Firstly, it used the prior knowledge of face images to manually give the facial features more attention. Then it introduced linear low-rank convolution in the network, and finally used the idea of long-distance dependence to supplement the details of the super-resolution images. The experimental results show that the method in this paper has achieved competitive results in the evaluation metric of peak signal-to-noise ratio and structural similarity index, and the visual perceptual quality of its super-resolution face images are excellent. [ABSTRACT FROM AUTHOR]

To solve the problems that the objects with different semantic classes are identified as co-salient objects in current co-saliency detection methods, this paper proposed a CNN and semantic correction-based co-saliency detection method (CSCCD). The proposed method first adopted the guided super pixel filter to process the super pixels obtained by SLIC and the saliency results generated by DSS, which showed clear object boundaries. Then it utilized Mask R-CNN to extract semantic features. It proposed the definitions of image semantic feature and semantic consistency. It also defined the image group semantic correction to solve the problem that detected the objects with different pose belonging to a semantic class as different semantic classes. With the concept, this paper defined image group semantic correlation class, solving semantic correlation problem of multiple images. It generated the final co-saliency detection results by fusing the saliency detection regions with the image group semantic consistent regions. The experimental results on public benchmark datasets show that this algorithm can effectively highlight the whole and outline of the object, and its comprehensive performance in objective quantification is obviously improved. [ABSTRACT FROM AUTHOR]

In order to solve the problem that the existing super-resolution algorithm based on deep learning didn't make full use of the feature information of each level, resulting in low reconstruction accuracy and large parameter quantity, this paper proposed a double dense connection structure named densely channel attention skip connection network. In the inner structure of the network, it improved the original dense cascade block to generate a channel separable dense cascade block. The outer structure adopted a densely residual connection and attention mechanism to fuse the features extracted by the dense block to achieve the goal that less convolution layer and higher precision effect. This paper tested the network models on several benchmark datasets . The results show the proposed model has higher accuracy and fewer parameters than the other models. [ABSTRACT FROM AUTHOR]