Search

NeRF is a deep learning model aimed at modeling three-dimensional implicit spaces, and it holds significant value in the representation and rendering of 3D scenes. However, due to the complex training process, substantial computational resources, and time requirements, the usability and practicality of the NeRF algorithm are somewhat limited. Addressing the pain points of NeRF optimization has become a hot topic in the field of computer vision. This paper aimed to provide a comprehensive review of the optimization and application of NeRF. Firstly, it delved into the basic principles of NeRF and outlined the current optimization status from the perspectives of rendering quality, computational complexity, and pose. Secondly, it enumerated the application scenarios of NeRF to provide references for future, more efficient and practical algorithmic optimizations. Finally, it summarized the strengths and limitations of NeRF and proposed potential future directions tailored to harness the tremendous potential of NeRF in 3D rendering, scene synthesis, and beyond. [ABSTRACT FROM AUTHOR]

Aiming at the problem that feature extraction is inaccurate and the reconstruction image is not natural enough in blind super-resolution reconstruction, this paper proposed an image blind super-resolution reconstruction based on degradation aware and sequence residuals. This paper proposed a mini-residual group combined degeneration aware and sequence residuals as the backbone network. Then the method constructed a symmetrical enhanced multi-scale residual block. In the image reconstruction part, this paper used the bottleneck attention module and the sub-pixel convolutional module to emphasize the multi-dimensional elements of the image. Finally, the method made a global residual connection. Compared with the current representative algorithm DASR, experiments show that the PSNR and SSIM of the proposed algorithm are improved 0.145dB and 0.0014 on Set14×2, and the PSNR of the proposed algorithm is improved 1.898dB and 0.252dB on Set14×3/4, respectively. The proposed algorithm achieves better performance than several current image super-resolution algorithms on five standard test sets. [ABSTRACT FROM AUTHOR]

Aiming at the problem of insufficient feature extraction ability of deep clustering algorithm on multivariate time series data( MTS), This paper proposes a new deep clustering structure model (MDTC. In order to extract the key features of MTS and realize dimensionality reduction, one-dimensional convolution learns the attribute and temporal dimension feature representation of MTS and the autoencoder structure composed of network layers such as recurrent neural network; To improve the model’s ability to represent temporal features, this paper proposes MCBAM temporal attention module, which is used to enhance the representation features of different time periods in the MTS sequence. This paper conducts experiments on nine publicly available UEA multivariate time series datasets, compared with other autoencoders, the autoencoder structure of the model improves by 2%-9% on 7 data sets; Compared with other attention modules, the MCBAM module of the model improves by 0.3%-2% on the six datasets. Experiments show the effectiveness of the MDTC model structure and MCBAM module, and the model has excellent performance compared with other clustering algorithms. [ABSTRACT FROM AUTHOR]

In order to address the shortcomings of the facial landmarks detection models, which cannot model the relations between long-distance landmarks, this paper proposed a parallel multi-branch architecture combining with convolution and Transformer for facial landmarks tasks, called MCTN, it utilized the dynamic attention mechanism to model the long-distance relations between facial landmarks. The multi-branch parallel structure designing allowed MCTN to include shared weights, global information fusion and other merits. What’s more, this paper proposed the novel Transformer structure, Deformer, which could make the MCTN focused attention weights faster on sparse and meaningful locations and solved the problem of slow convergence of Transformer. MCTN reached 4.33%,3.12% and 3.15% normalized average error respectively on the WFLW,300W and COFW datasets, the results show that MCTN utilizes Transformer with CNN multi-branch parallel structure and Deformer structure to dramatically outperform other facial landmarks localization algorithms based on convolution network. [ABSTRACT FROM AUTHOR]

In recent years, various human action recognition algorithms have achieved excellent recognition performance based on a large number of labeled samples. However, in practical applications, acquiring training samples and their corresponding labels is time-consuming and laborious, which limits the actual implementation of the algorithm. This paper summarized the deep learning algorithms for action recognition under weak supervision and few-shot learning. Firstly, in the case of weak supervision, it classified and summarized the semi-supervised action recognition methods and unsupervised domain adaptation video action recognition methods separately. Then, it reviewed video action recognition algorithms based on few-shot learning in detail. Further, it summarized the relevant human behavior datasets and analyzed and compared the performance of various relevant video action recognition algorithms on these datasets. Finally, the paper summarized the full text and discusses the future development trend of human action recognition. [ABSTRACT FROM AUTHOR]

At present, the research on combining deep learning with Visual SLAM(Simultaneous Localization And Mapping) to construct indoor 3 D pointcloud semantic map is in full swing. In order to solve the problems that traditional Visual SLAM networks have low accuracy and poor speed and lack semantic information, this paper proposed a novel RGB-D semantic segmentation network. The network uses the depth information which less affected by the light in indoor scenes to improve the accuracy of segmentation, and meanwhile designs the lightweight multi-scale residual module(MRAM) and Atrous Spatial Pyramid Pooling(ASPP) module to lightweight the segmentation network and improve the segmentation accuracy. Firstly, ORB-SLAM2 network screens the input image sequences to obtain keyframes. Then, the keyframes go into the proposed semantic segmentation network to get the 2 D semantic label, and then map the 2 D semantic information to 3 D pointcloud space. Finally, the method uses the Bayesian algorithm to update the 3 D map to obtain the globally consistent 3 D pointcloud semantic map. The experiments adopt NYUv2 dataset to verify the performance of semantic segmentation network, and adopt TUM dataset construct pointcloud semantic map. The results show that the performance and speed of the semantic segmentation network in this paper are better than the existing models, and the combination of semantic segmentation network with visual SLAM can meet the requirements of constructing 3 D dense semantic pointcloud map accurately and quickly. [ABSTRACT FROM AUTHOR]

The purpose of image stitching is to obtain a high-definition, seamless panoramic image. Existing methods rely on the accuracy of feature matching, which will misalign images and produce errors such as artifacts and distortions.This paper proposed a new unsupervised real scene image stitching network that can adapt to real scene stitching in the presence of moving targets, ensuring no loss of accuracy in the panorama. It included two networks of alignment and reconstruction, excluding the negative influence of moving targets and misleading regions on the transformation matrix through content branching, and optimizing image details by constraining the reconstruction process through edge branching to achieve high-definition and artifact-free stitching effects. The experimental results show that the method’s RMSE, PSNR, and SSIM reached 1.81, 26.56, and 0.85, respectively. The objective evaluation indexes are better than other classical algorithms overall, and the user research results also indicate that the method obtains higher definition of panoramic images. The method effectively accomplishes unsupervised image stitching in real scenes and can be generalized to stitching tasks in other scenes. [ABSTRACT FROM AUTHOR]

Recent years, the motion deblurring algorithm based on deep learning has been widely concerned, while single defocus image deblurring is rarely studied. In order to specifically solve the defocus blur problem of single image, this paper proposed a defocus deblurring algorithm based on deep recurrent neural network. Firstly, the algorithm used two cascaded residual networks to estimate the defocus map and image deblurring, respectively. After that, to ensure that the depth features of defocus map and clear images could better propagate across stages and interact within stages, the algorithm introduced LSTM ( long short-term memory) as a recurrent layer in the residual network. Finally, the whole residual network underwent several iterations and reused the network parameters during the iterative stages. To train the network, this paper produced a synthetic defocus blur image dataset, where each defocus blurred image contained a corresponding clear image and defocus map. The experimental results show that, compared with existing defocus deblurring methods, the proposed algorithm has significant advantages in both the subjective and objective image quality evaluation, and can produce sharper edges and clear details in the restoration results. On the real defocus blur dual-pixel image dataset DPD, the proposed algorithm improves the peak signal-to-noise ratio ( PSNR) and structural similarity( SSIM ) by 0. 77 dB and 5. 6%, respectively, compared with DPDNet-Single. Therefore, the proposed method can effectively deal with defocus blur in real scenes. [ABSTRACT FROM AUTHOR]

In dynamic gesture recognition methods based on deep learning, aiming at the problems of large network scale, simple dimension of extracted spatiotemporal features, and insufficient extraction ability of effective features, this paper proposed a deep network framework. Firstly, this paper applied a novel spatiotemporal convolution module based on multiscale information fusion in the time domain to improve the 3D residual network structure, greatly reduced the size of the network and obtained rich spatiotemporal receptive field characteristics. Then it introduced a spatiotemporal feature channel attention mechanism with global information synchronization, and used a few parameters to construct the global dependency between feature maps, and the module could obtain the key features of dynamic gestures more efficiently. The experimental results on the self-built gesture dataset SHC and the public gesture dataset SKIG show that the proposed gesture recognition method has fewer parameters and more powerful multiscale spatiotemporal feature extraction ability, and gains a higher recognition rate than the current mainstream algorithms. [ABSTRACT FROM AUTHOR]

To solve the problem that existing botnet detections targeted a single phase of the botnet lifecycle, this paper proposed an online botnet detection method based on ensemble learning. Firstly, this paper fine-grained labeled the traffic of multiple phases of botnet lifecycle to generate a botnet dataset. Secondly, this paper combined multiple feature selection algorithms to generate a significant feature set containing 23 features and a less significant feature set containing 28 features. It integrated multiple deep learning models based on stacking ensemble learning and provided different input feature sets for different primary class ifiers to obtain a botnet online detection model. Finally, this paper deployed the botnet online detection model to detect multiple botnets online at the network entrance. Experiment shows that the proposed botnet online detection method based on ensemble learning in this paper can effectively detect multiple stages of botnet traffic, and the malicious traffic detection rate can reach 96 . 47% . [ABSTRACT FROM AUTHOR]

The most existing deep text clustering methods only use traditional autoencoder to learn representation for clustering, and neglect the problems with over-reliance on raw data quality and loss of key semantic information during feature mapping. This paper proposed a deep document clustering method via key semantic information complementation (DCKSC) model. The DCKSC model firstly enriched the original text data by extracting keyword data. Secondly, this model designed a key semantic information complement module which used data enhancement representation to improve the traditional autoencoder, and compensated for the key semantic information lost in the mapping process. Finally, the algorithm synthesized the clustering loss and the reconstruction loss of the keyword semantic autoencoder, optimized the cluster label assignment and learned the presentation characteristics suitable for clustering. Experimental results show that DCKSC is superior to many mainstream deep document clustering algorithms. [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]

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]

Aiming at the limitation that the existing chemical process fault diagnosis methods based on deep learning usually need complete labeled data to build a fault diagnosis model, this paper proposed a semi-supervised fault diagnosis method for chemical process based on temporal ensembling-dual student model. Firstly, based on the dual student model, the method guided the mutual training through the classification constraint, the stability constraint and the consistency constraint, which effectively alleviated the error accumulation. Then it used temporal ensembling to integrate the prediction of multiple previous network evaluations as consistent regularization objects to alleviate the prediction noise and reduce the training time of the model, so as to improve the classification performance and realize fault diagnosis. Finally, this paper verified the validity and feasibility of the proposed method by the Tennessee-Eastman chemical process benchmark data. Compared with supervised methods such as BNLSTM, DCNN and MCLSTM, it proves that TE-DS algorithm is superior to fault diagnosis. [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]

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]

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]

People have widely used air quality prediction models composed of traditional machine learning methods. However, such models still have shortage on data validity, especially the validity of spatial-temporal related data selection. In response to the input data validity of deep learning networks, this paper proposed a prediction model based on spatial-temporal similarity LSTM to select more effective data at the time and space level. STS-LSTM contained three modules, pre-order, middle-order and post-order module. The pre-order module was the time-space similar selection input module, which proposed the GCWDTW algorithm. This paper used it to select data with higher temporal and spatial similarity. The in-order module used LSTM as a deep. learning network for training. The post-order module selected different output groups for integration according to the characteristies of the target station. The STS-LSTM overall model improves the air quality prediction error by about 8% compared with the existing algorithm, and the data selected by the validity improves the accuracy of the model by up to 21%. The experimental results show that this model has achieved significant results in the effective data selection, and the data input and output method as a part of the applied deep learning network can effectively improve the final effect of the deep learning network. [ABSTRACT FROM AUTHOR]

With the development of big data, computational power and deep learning, the object detection algorithm based on deep learning becomes the mainstream algorithm in this field, and its performance is far superior to the traditional algorithms. In order to review the development of algorithms, track the latest research results, and promote the research in the field of object detection, this paper summarized the representative object detection algorithms from two dimensions: two-stage /one-stage and anchor-based anchor-free, and realized the rectangular box or approximate rectangular box annotation under these two different classification standards. This paper discussed the process, characteristic, evolution and performance of the algorithms, and made the classification and analysis on the important improved versions. Finally, this paper summarized the advantages and disadvantages, limitations and applicable scenarios the algorithms, and looked forward to the development trend in the field of object detection, and put forward several important research directions in the future. [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]

Loop closure detection is important for visual simultaneous localization and mapping (VSLAM) systems to reduce cumulative errors and perform re-localization. In order to shorten the loop closure detection online runtime while meeting the accuracy recall rate requirement, the paper proposed a fast loop closure detection algorithm using broad autoencoder (FLCD-BA). The algorithm improved broad learning architecture to learn feature representations autonomously from the input data in an unsupervised manner, and then accomplished loop closure detection tasks. Differing from the traditional deep learning methods, the network used a pseudo-inverse ridge regression algorithm to solve the weight matrix and achieved fast reconfiguration of the network by incremental learning without retraining the entire network. The proposed algorithm experimented on three public datasets without using GPU devices, and the training time of the network greatly reduced compared to bag-of-words models as well as deep learning methods. The experimental results show that the algorithm has high accuracy and recall in detecting loop closure, and the average running time per frame in the test is only 21 ms, which provides a new algorithm for loop closure detection in visual SLAM systems. [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]

This paper proposed a cross-domain mapping algorithm of service function chain based on deep reinforcement learning in view of the influence of SFC mapping on transmission delay and resource cost in the partial information isolation. Firstly, this paper constructed a centralized choreography architecture, which the upper controller utilized the full mesh aggregation technology to construct the abstract topology and reduced the complexity of mapping between domains. Secondly, this paper modeled the SFC request partition problem as Markov decision process, so that virtual network function could evenly distribute in each domain. Finally, this paper constructed the deep reinforcement learning network when taking the inter-domain transmission delay and mapping resource cost as reward function,and completed the inter-domain mapping by training. If the intra-domain mapping fails, used the feedback mechanism to improve the acceptance rate of SFC requests. Simulation results show that the proposed algorithm can effectively reduce the transmission delay and resource cost. Meanwhile,it can improve the request acceptance rate . [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]

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]

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]

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]

Aiming at the high dimensionality of the empirical learning sample and the low robustness of the strategy gradient model in the actor-critic algorithm, this paper constructed the attention mechanism network and acted as a proxy based on the information cooperation advantages of the multi-agent systems, introducing a multi-layer parallel attention mechanism. By adding the network model and the soft function to the actor-critic algorithm, this paper proposed a soft actor-critic algorithm based on multi-layer parallel attention mechanism to solve the problem of robot path planning, enhance the actors' strategy gradient robustness and reduce regression error of the critics, and achieved the fast convergence of robot path planning. The experimental results show that this method can effectively overcome the local optimization problem of robot path planning, and has the advantages of fast computation speed and stable convergence. [ABSTRACT FROM AUTHOR]

In order to understand the development of outlier detection technique detailly, this paper overviewed the outlier detection techniques in recent years. Firstly, it introduced and summarized the definition of outliers, the causes of outlier and classification of the outlier mining algorithms. Next, it overviewed outlier detection methods based on neighbor, based on distributed framework and based on deep learning. Especially, it discussed the most representative methods in outlier detection, and pointed out the merits and drawbacks. In the end, this paper concluded and discussed the future direction of outlier detection techniques. [ABSTRACT FROM AUTHOR]

Based on video action recognition, this paper firstly reviewed the traditional action recognition algorithms based on RGB, including traditional algorithms and deep learning algorithms. Because of the influence of background lighting, RGB-videobased action recognition is low accuracy, but it has rich color appearance information. Then this paper analyzed and summarized action recognition algorithms based on RGB-D, which was divided into depth sequence, bone and multi-feature fusion. RGB-D video has multiple modes and can provide more information for action recognition, which performs better than RGB video but also brings new challenges. Finally, this paper prospected the common data sets and the possible future development direction. [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]

Aiming at the knowledge overload in the process of online learning and the problems of data sparsity and cold start in the traditional recommendation algorithm, this paper proposed an improved learning resource recommendation algorithm based on MLP. The algorithm used the advantage of MLP in nonlinear data processing, converted the prediction mode of vector multiplication of learner characteristics and learning resource characteristics into the input mode of MLP, and improved the DN-CBR neural network recommendation model. In order to verify the effectiveness of the model, this paper built a dataset with the online learning platform data of iCourse as the sample. Compared with DN-CBR model, the improved model improves the normalized cumulative loss gain and hit rate by 1. 2 % and 3 % respectively on the dataset, which effectively improves the recommendation performance of the model. [ABSTRACT FROM AUTHOR]

Vehicle detection and identification in urban roads is of great significance for improving traffic safety and developing intelligent transportation. The traditional detection method relies on the features of manual extraction, which has been difficult to apply the complex and variable traffic scenarios, and has the defects of low recognition accuracy and high time complexity. The deep learning model can automatically extract effective features, and the generalization ability is strong, but it is difficult to classify similar vehicles more closely. To this end, this paper proposed a small vehicle target detection algorithm based on residual network. The algorithm changed the connection form of the traditional convolutional neural network to a residual connection mode based on local connection and weight sharing. At the same time, this paper changed the number of network structure control parameters, fused the features of different levels of the picture, applied the pooling layer of the region of interest to normalize the front layer features, and finally obtained the confidence and correction parameters of the target frame through the classification layer and the regression layer. Experiments show that the improved model can enhance the learning ability of the network under the premise of ensuring time efficiency, improve the average accuracy value, and obtain good detection results on the detection of similar small vehicles. [ABSTRACT FROM AUTHOR]

Aiming at the problem of autonomous localization and environmental reconstruction, SLAM based on visual sensor has become a hot research topic at this stage. In order to deeply analyze the current situation of visual SLAM, this paper summarized the related algorithms and results. Firstly, it briefly summarized the concept, characteristics and research significance of visual SLAM. Then, it analyzed the visual odometry algorithm in depth, and described the classical visual odometry algorithms in detail, which included feature-based method, optical flow-based method and direct method, and introduced the landmark achievements of classical visual SLAM algorithm. Secondly, this paper introduced the research progress visual SLAM based on deep learning according to supervised learning and unsupervised learning, and summarized the algorithms. In addition, it analyzed the integration of visual SLAM and inertial navigation. Finally, it proposed the future development trend of visual SLAM. [ABSTRACT FROM AUTHOR]

When modeling users' preferences, current researches of group recommendation usually ignored the mutual influence between group preference and individual preference and the problem of modeling initialization. To address these issues, this paper proposed a new group recommendation model called ranking based hybrid deep tensor factorization model, namely R-HDTF model. First of all, this paper developed a hybrid deep learning-based initialization method, which utilized deep denoising autoencoder to pretrain the initial values of the parameters for the R-HDTF model. Then, it proposed a pairwise tensor factorization model to capture the correlation among group, individual and item. Finally, it used the Bayesian personalized ranking( BPR) metric to optimize the loss objective function of tensor factorization and learn the parameters of the proposed model. Experimental results on real data sets show that the performance of the proposed algorithm outperforms traditional group recommendation algorithm. [ABSTRACT FROM AUTHOR]

In order to give a comprehensive understanding of SLAM, this paper first gave an overview of the progress of visual SLAM community has made over the last 30 years in this survey. Then it presented the non-linearity of the mathematical model and computational complexity in visual SLAM algorithms. This paper mostly focused on the latest achievements and approached improving the accuracy of pose estimation, building a globally consistency representation of the environment and promoting computation efficiency. It also surveyed the failure modes of current visual SLAM algorithms for large scale, full life cycle implementation and the different ways to address that. Finally, it discussed the potential connections between deep learning architectures and visual SLAM state estimations. [ABSTRACT FROM AUTHOR]

In order to sort out the development of deep learning methods in the field of human action recognition, this paper summarized the most representative models and algorithms in this field in recent years. Firstly, it described in detail the latest achievements, advantages and disadvantages and network structure of deep learning methods in video pre-processing stage based on the task flow of human action recognition. Then, it introduced two kinds of datasets related to human action recognition. Finally, it discussed and prospected the future research direction of human action recognition. [ABSTRACT FROM AUTHOR]

When the deep reinforcement learning algorithm is trained in a complex dynamic environment, it is difficult for the agent to obtain useful information due to the partial observability of the environment, which leads to typical problems such as failure to learn good strategies and slow algorithm convergence speed. This paper proposed an improved DDPG algorithm based on LSTM and asymmetric actor-critic network. This method introduced the LSTM structure into actor-critic network to learn the hidden states in partially observable Markov through memory reasoning. At the same time, when the actor network only used RGB images as partially observable inputs, the critic network used the complete state of the simulation environment to train, which formed an asymmetric network and speeded up the training convergence. The simulation experiment of manipulator grasping in ROS shows that the proposed algorithm has higher success rate and faster convergence speed compared with DDPG, PPO and LSTM-DDPG. [ABSTRACT FROM AUTHOR]

The purpose is to deal with the problems of excessive pruning of important convolutional layers caused by equalscale pruning, retain many redundant parameters and large loss of accuracy. This paper integrated sensitivity analysis on the basis of FPGM pruning strategy for network pruning. The algorithm used precision feedback to analyze the importance of each convolutional layer, control the single-layer pruning ratio, analyze the impact of different pruning ratios in each layer on accuracy loss, and obtained the sensitivity of each convolutional layer. It could be combined with FPGM to analyze the importance of the convolution kernel and cut the unimportant convolution kernel according to the pruning ratio of the sensitivity to complete the neural network pruning. The experimental results show that the accuracy of this method only drops by l. 56% and 0. 11 % when the pruning rate on MobileNet-v 1 and ResNet50 is 50%. This method has a higher pruning rate and lower calculation amount on ResNet50 under the same accuracy loss. [ABSTRACT FROM AUTHOR]

Aiming at the learning of contextual features in 3 D model semantic segmentation, this paper proposed a 3 D model semantic segmentation algorithm based on context-reinforced octree network, named CR-O-CNN. The octree-based convolutional neural network combined the context reinforcement network to model Markov decision process of context feature learning, and used asynchronous advantage actor-critic to optimize the process. By learning deep context features, the segmentation results of the 3 D model were improved. The experimental results on the public data set ShapeNet show that the proposed algorithm can improve the performance of semantic segmentation of 3 D models. [ABSTRACT FROM AUTHOR]

Aiming at the problems of complex background, variety of change types, missing detection and rough boundary recognition in high-resolution remote sensing image of the same region, this paper proposed a high-resolution remote sensing image building change detection algorithm based on Siam-UNet++network. The algorithm used UNet++as the backbone extraction network. In the encoder phase, it applied the Siam-diff structure to extract the change features of the two sequential images, and employed the attention mechanism after the up sampling and lateral jump path connection in the decoding stage to highlight the building change features and inhibit the network learning from other types of features. Meanwhile, it used the MSOF strategy to weight and fuse feature information of different semantic levels, which improved the accuracy of building change detection. Finally, it adopted a sliding window method to predict large-scale remote sensing images, reducing the hole pattern generated by the change result map during the splicing process. The experimental results demonstrate that proposed algorithm shows better performance than other models. [ABSTRACT FROM AUTHOR]

Network representation learning aims to transform the nodes in the network into a low-dimensional vector space while maintaining the inherent properties of the network. Most of the existing methods are aimed at normal networks, ignoring the particularity of attribute bipartite networks and the highly non-linear characteristics of the network. To solve the above problem, this paper proposed a deep attributed bipartite network embedding method incorporating with multilevel structure information. Specifically, the algorithm introduced an extended weight matrix to fuse the explicit and implicit structure of the bipartite network with attribute information. Then, it utilized a deep auto-encoder model to capture the highly non-linear characteristics of the network. To maintain the global network structure, a deep auto-encoder reconstructed the second-order proximity. Meanwhile, the deep auto-encoder used the first-order proximity of the nodes as supervisory information to maintain the local network structure. Finally, the algorithm performed joint optimization to get the final representation vectors of nodes. The model was executed on the four datasets of Yelp, Douban Book, Douban Movie and MovieLens. Compared with the latest benchmark method, the average values of F1@10, MAP@10,MRR@10 and NDGG@10 of this model have improved by 4.29%、5.63%、6.26%、4.21%. [ABSTRACT FROM AUTHOR]

In order to solve the problem that the recommendation model cannot mine the diversity of user interest and capture the order information between the sequence of user behavior, and the interaction occurs at the element level rather than between the feature vectors, etc., based on multiple attention mechanism and location information, this paper proposed the x DMAL FM. Firstly, it extracted the feature depth from different subspaces by using the multi-head attention mechanism, and then location information could capture the sequential relationship between user behavior sequences. Finally, it used three public datasets to conduct comparative experiments and the AUC index to evaluate the results. The experimental results show that the proposed algorithm has better recommendation performance than the xDeepFM model and show the effectiveness and feasibility of the proposed algorithm. [ABSTRACT FROM AUTHOR]

In recent years, as deep learning has achieved good results in many fields, deep learning has also begun to be applied to recommendation systems, such as NFM models and DeepFM models that use deep learning technology to capture high-level feature interactions. However, considering the changes in the external environment and internal perception, the user' s interest should also change dynamically over time, and the combination based on the original features may not necessarily learn effective feature interaction. This paper attempted to build a new model FG_DRFwFm, which could learn the interaction of low-level and high-level features of multiple feature domains and dealt with long-term changes in user interest. It constructed the training features by constructing new features based on the original features and splicing them together, which could better learn effective feature interaction. Finally, the proposed model compared the recommendation effect with multiple advanced CTR algorithms on the MovieLens data set. The experimental results show that the proposed model achieves better results. [ABSTRACT FROM AUTHOR]

Considering federated learning under mobile edge computing, where a global server connects a large number of mobile devices through the network to jointly train a deep neural network model. The data distribution shift caused by global class imbalance and device local class imbalance leads to the performance degradation of the standard federated averaging ( FedAvg) algorithm. This paper proposed a device selection algorithm based on the combinatorial multi-armed bandit ( CMAB) as an online learning algorithm framework, and designed a class estimation scheme to form a nonlinear reward function. Based on class estimation scheme and CMAB, in each round of communication, the global server selected the device subset with class imbalance that could be best complementary with test performance deviation across classes of global model from last communication round. Therefore, the current aggregated global model could achieve more balance and better test performance per class, and also faster convergence and more stable training dynamics. Extensive numerical results demonstrate the influence of different parameters on FedAvg under class imbalance, and verify the effectiveness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

In order to improve the information processing ability of the model in complex scenes, this paper proposed a dynamic selection mechanism based on attention, which selectively allocated weights according to the current information, effectively fused the feature outputs of deformation convolution and ordinary convolution, and adaptively balanced deformable convolution and standard convolution, so as to improve its representation ability. In addition, the learning ability of the model was further enhanced by means of iteration without additional parameters. It used seven different kinds of noises from Noise-X92 in TIMIT corpus, and carried out experiments in various SNR environments. The results show that the proposed algorithm outperforms other recent deep learning algorithms in terms of intelligibility and speech quality, regardless of SNR and whether noise appears in the training data set. [ABSTRACT FROM AUTHOR]