Search

Copyright of Application Research of Computers / Jisuanji Yingyong Yanjiu is the property of Application Research of Computers Edition and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The federated learning framework that uses autoencoder model to detect malicious model updates is an excellent defense framework for poisoning attacks. However, the existing autoencoder-based models face several challenges such as training difficulties and limited anomaly detection capability. In view of the above problems, this paper proposed an algorithm for detecting malicious model updates of federated learning based on β-VAE: the central server stabilized the training dataset by suppressing random attributes of the training samples, and used the dataset to train β-VAE anomaly detection model in real time. The model computed the anomaly score of task model updates uploaded by the clients, and then to detect and exclude malicious model updates based on the dynamic threshold of anomaly score. This paper evaluated the performance of the proposed algorithm on three federated learning tasks. Specifically, these tasks include classification on the MNIST dataset using the logistic regression (LR) model, classification on the FEMNIST dataset using the convolutional neural network (CNN) model, and character prediction on the Shakespeare dataset using the recurrent neural network (RNN) model. The experimental results show that, the task model under this algorithm achieves higher accuracy compared to other defense algorithms. This indicates that in Non-IID scenarios, the algorithm exhibits strong robustness against poisoning attacks in federated learning. [ABSTRACT FROM AUTHOR]

Implementing fast and accurate hand detection on embedded devices mainly face two challenges. Firstly, it is difficult for complex deep learning networks to achieve real-time hand detection. Secondly, the complexity of the scene leads to a decrease in the accuracy of hand detection algorithms based on RGB color images. Unlike mainstream RGB image based detection technologies, this paper adopted a lightweight hand detection algorithm based on ToF infrared images to attain precise and swift hand detection within the infrared images. Firstly, this paper gathered 22 419 static infrared images using this self-engineered equipment, thereby establishing an infrared dataset tailored for hand detection. Subsequently, it enhanced a general object detection algorithm to create a lightweight hand detection network known as Retina Hand, using two different lightweight networks, MobileNetV1 and Shuffle NetV2, as the backbone network of the model. Furthermore, this paper proposed an attention-enhanced feature pyramid structure called Attention-FPN. This structure integrated attention mechanisms to enhance the detection process. Ultimately, this paper conducted comparative experiments on the infrared dataset against conventional methods to validate the effectiveness of the method. [ABSTRACT FROM AUTHOR]

HD maps can provide accurate road information and rich semantic information, so that the automatic driving system can guide the vehicle to drive correctly. HD maps usually rely on manual labeling. The existing automatic labeling methods have low recognition accuracy in autonomous driving scenarios, resulting in low efficiency of HD map labeling. In order to solve this problem, this paper proposed a new semantic segmentation method for automatic labeling of HD maps called MapFormer. This paper proposed a multi-level feature fusion module, which enabled the model to aggregate different levels of detail and semantic information. Additionally, it proposed a novel boundary-decoupled joint decoder to improve the model's ability to handle intercategory boundaries. Experiments on the bird's-eye view dataset show that the proposed model not only achieves excellent performance in segmentation accuracy, but also has a clearer handling of category boundaries. The mIoU of MapFormer is 55.82%, which is higher than the SegFormer of 1.03%. The proposed method can improve the HD map labeling efficiency and labeling automation rate. [ABSTRACT FROM AUTHOR]

To address the problem of insufficient recommendation performance in session recommendation, this paper proposed a disentangled graph neural network model (GDST-GNN) using global graph diffusion and spatio-temporal awareness. Specifically, the model firstly constructed a global collaborative graph based on all sessions from a global perspective, and then employed graph diffusion as the message propagation paradigm for global representation learning of items to capture global information be- yond the current session. For the representation learning of the current session, this paper designed a disentangled spatio-temporal gated network modeling the complex transition pattern and temporal dependency pattern of items in the session, and then fused the learned global and local representations factor by factor. In addition, this paper employed a self-supervised task to achieve performance enhancement of the model. Finally, it generated session representations through attention networks to achieve accurate recommendation of items. Extensive experiments on four real-world datasets validate the effectiveness of the proposed model. [ABSTRACT FROM AUTHOR]

Copyright of Application Research of Computers / Jisuanji Yingyong Yanjiu is the property of Application Research of Computers Edition and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The estimation of multiple matching models between wide baseline or large angle images is a quite challenging task in image processing. The existing algorithms can be used to estimate multiple matching models and their inliers between images well, but their results are prone to matching pairs mis-classification issues. In order to accurately estimate the multiple matching models and allocate matching pairs, this paper proposed an image multi-matching model estimation algorithm based on the aggregation of matching points of the same model (AMPSM). Firstly, for improve the proportion of correct matching pairs, it filtered out incorrect matching pairs based on the distribution characteristics of correct matching points in the neighboring region. Furthermore, based on the different matching model degrees to which the matching pairs belong, searched for the suspected intersection matching pairs of multiple models, that was interference matching pairs. Meantime, for reducing the impact of interference matching pairs on the accuracy of matching classification, they were removed. Afterwards, for improve the clustering degree of matching points with the co-model, the position was dynamically moved based on the distance between the points within the same model and the center of gravity of the point set during the sampling process. Finally, classifying clustered matching points by Mean Shift to obtain a multi matching model. And the proposed method was compared with classical framework based algorithms RANSAC, PROSAC, MAGSAC++, GMS, AdaLAM, PEARL, MTC, Sequential RANSAC, and deep learning based algorithms SuperGlue, OANet, CLCNet, CONSAC, etc. Results indicate over 30% increase in the inlier rate, 8.39% reduction in the mis-classification rate of multi model estimation. It is concluded that the new algorithm has significant advantages in incorrect matches filtering and multi-model estimation. [ABSTRACT FROM AUTHOR]

Current researches on NDP flooding behavior detection mainly focus on detecting RA flooding and NS flooding behaviors, and there is insufficient flooding detection for other messages of the NDP protocol. Moreover, traditional threshold rule detection methods suffer from poor dynamics and low accuracy, while most of the Al-based detection methods can only perform binary classification detection, and there are still challenges in performing multi-classification detection. In short, there is a lack of corresponding research in multi-classification flooding detection of all messages of NDP protocol. Therefore, this paper proposed a multi-classification detection framework for NDP protocol flooding behaviors, and proposed a flooding behavior detection method for NDP protocol based on time interval characteristics. The framework constructed the first multiclassification dataset for NDP flooding detection through the processes of traffic collection and data processing, it compared and used 5 machine learning and 5 deep learning algorithms to train the detection model. The experimental results show that the detection accuracy of the XGBOOST algorithm in machine learning can reach 99.18%, and the detection accuracy of the Transformer algorithm in deep learning can reach 98.45%. Compared with the existing detection methods, the accuracy is higher. Meanwhile, the detection framework can detect 9 types of flooding behaviors for all 5 types of messages of NDP protocol and classify the flooding behaviors into multiple types. [ABSTRACT FROM AUTHOR]

Nowadays due to the dependence of fault diagnosis method based on deep learning on well-labeled training dataset, which will lead to the problem that deep neural network can easily overfit those noisy labels and affect the generalization of network under the condition of label noise. In order to achieve accurate recognition of equipment operating conditions in the network trained with label noise, this paper proposed a fault diagnosis method via contrastive learning and neighborhood sample analysis. Firstly, the method used contrastive learning to pre-train the model, which could reduce the embedding distance of similar samples in the feature space and achieved improving the ability of optimizing the feature representation ability of the network. Then, the method utilized the feature similarity to find each sample's closest neighbors to estimate the reliability of training labels which could separate all training samples into a clean or noisy subset and implemented label correction on noisy subset. After that, it established a more reliable training subset. Lastly, the proposed method made use of label reweighting and consistency regularization to enhance robustness of network. In particular, two networks got trained simultaneously where each network used the dataset division from the other network during the training process, which could mitigate confirmation bias caused by single network model training framework. The experimental results on public dataset demonstrate that proposed method can verify and correct the noisy labels impressively well and maintain great fault diagnosis performance under the condition of high-level noisy labels. [ABSTRACT FROM AUTHOR]

Deep semi-supervised clustering aims to achieve better clustering results using a small amount of supervised information. However, the amount of supervised information is often limited due to the expensive labelling cost. Therefore, with limited supervised information, it becomes crucial to select the most valuable supervisory information for clustering. To address the above problem, this paper proposed a deep active semi-supervised clustering model (DASCM) which designed an active learning method that was able to select marginal texts containing rich information and further generated high-value supervised information containing edge texts. The model used this supervised information to guide the clustering, thus improving the clustering performance. The experimental results on five real text datasets show that the clustering performance of DASCM is significantly improved. This result verifies that supervised information generated using active learning methods that cover marginal text is effective in improving clustering. [ABSTRACT FROM AUTHOR]

To address the challenge of constructing spatial and temporal dependencies in existing traffic flow prediction methods, this paper proposed a new method called spatial temporal position attention graph neural network (ST-PAGNN), which utilized spatiotemporal location attention. Firstly, the graph neural network contained a location attention mechanism, which could better capture the spatial dependence of traffic nodes in the urban road network. Then, it used a gated recurrent neural network with trend adaptive transformer (Trendformer) to capture the local and global information of the traffic flow sequence in the time dimension. Finally, it used the improved grid search optimization method to optimize the introduced para-meters of the model, obtaining the global optimal solution with high time efficiency. The experimental results show that in the dataset PEMS-BAY, the evaluation indexes RMSE, MAE and MAPE of the ST-PAGNN method are 1.37, 2.57, 2.67%, 1.55, 3.64, 3.37%, 1.97, 4. 37 and 4.43%, respectively, when the prediction step size is 15 min, 30 min and 60 min, respectively. In the dataset METR-LA, when the prediction step size is 15 min, 30 min and 60 min, the evaluation indexes RMSE, MAE and MAPE of the ST-PAGNN method are 2. 73, 5. 16, 7.13%, 2.99, 5.97, 7.86%, 3.53, 7. 16 and 9.96%, respectively. The results show that the proposed ST-PAGNN method is higher than the existing models in the evaluation indexes under different granularities, which illustrates the effectiveness and superiority of ST-PAGNN in solving traffic prediction problems. [ABSTRACT FROM AUTHOR]

Currently, human sleep staging methods based on electroencephalogram (EEG) signals show a trend towards single-channel and deep network models, however, single-channel information acquisition makes EEG lose the positional information of brain regions, and the features characterizing sleep stages in EEG tend to be sparse and thus difficult to extract, at the same time, the common problems of deep networks-the artificial setting of the model and its training hyperparameters make the training process blind and inefficient, and these problems lead to the low accuracy of automatic sleep staging methods. Therefore, this paper proposed to use the inter-layer feature reuse function of DenseNet to explore the sleep state information hidden in EEG signals, and improved the DenseNet model for the low-frequency characteristics of single-channel EEG signals in the frequency domain and the long-range dependence of single-channel EEG signals in the time domain, so as to achieve the fast and accurate sleep staging of the human body. In order to further improve the performance of DenseNet, it used a deep deterministic policy gradient (DDPG) algorithm to optimize and automatically adjust the key hyperparameters of DenseNet using the reinforcement learning idea during the network learning and training process. The experimental results show that the staging accuracy of the algorithm model on the Sleep-EDFx dataset reaches 89.23%, and the overall performance is better than other advanced staging algorithms in recent years, demonstrating good application prospects. [ABSTRACT FROM AUTHOR]

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]

Camera pose estimation plays a crucial role in tasks such as autonomous driving and robotics, elucidating the direction and position of the camera in relation to a given scene through the estimation of its positional coordinates and angular deviations around the three coordinate axes. To facilitate the understanding of researchers in the realm of camera pose estimation, this paper comprehensively reviewed the current research status and latest progress in this field will. Firstly, it introduced the fundamental principles, evaluation indicators, and pertinent datasets associated with camera pose estimation. Subsequently, the review elaborated and summarized the two-stage model structure method and single-channel model structure method from the two key technologies of scene relationship construction and camera pose calculation. It conducted classification and analysis based on the diverse core algorithms and scene information employed, with performance comparisons drawn from indoor and outdoor public datasets. Lastly, it expounded the current challenges in the field and future development trends. [ABSTRACT FROM AUTHOR]

Copyright of Application Research of Computers / Jisuanji Yingyong Yanjiu is the property of Application Research of Computers Edition and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In order to solve the problem that class-imbalance data of clinical medical tables tend to have an impact on the model and that the performance of deep learning framework is difficult to match that of traditional machine learning methods when processing scale data tasks, this paper proposed a layer by layer Transformer (LLT) network model based on cascaded under-sampling. LLT deleted the most types of data layer by layer by cascade under-sampling method to achieve the balance of data categories and reduced the impact of class-imbalance data on the classifier. Moreover, LLT used attention mechanism to carry out correlation evaluation on the features of the input data to achieve feature selection, refined the feature extraction abi-lity and improved the model performance. This paper used RA (rheumatoid arthritis) data as test samples. Experimental results show that, on the premise of not changing the sample distribution, the recognition rate of a few categories is increased by 6.1% by the proposed cascade under-sampling method, which is 1.4% and 10.4% higher than that of the commonly used NEARMISS and ADASYN respectively. The accuracy of the RA tabular data and the F1-score index of LLT reach 72.6% and 71.5%, the AUC value is 0.89, the mAP value is 0.79, and the performance exceeds the current mainstream tabular data classification models such as RF, XGBoost and GBDT. This paper also visualized the model process and analyzed the characteristics affecting RA. It has a good guiding significance for the clinical diagnosis of RA. [ABSTRACT FROM AUTHOR]

For the problem of image degradation caused by raindrops attached to the lens or glass surface, this paper proposed a multi-stage progressive image raindrop removal method which divides the raindrop removal process into multiple stages to easily implement. First, the multi-scale fused encoder-decoder network at each stage designed to learn raindrop features. The constructed multi-scale dilated convolutions with gated recurrent units refined the internally transferred spatial features. In addition, the no dimensionality reduction channel attention module extracted channel information under specific spatial features. Finally, this paper adopted cross-stage feature fusion mechanism to strengthen the information exchange between the parts of each stage. Adding horizontal connections between the encoder-decoder networks in each stage to realize the horizontal transfer of feature information. And adding a supervised attention module to enhance the information transmission between different stages. The raindrop removal is progressively achieved. Experiments show that the proposed method can effectively remove raindrops. [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]

The level of face recognition technology continues to improve, and has achieved an ideal recognition rate in identity authentication, human-computer interaction and other industrial applications, and the market scale keeps growing. However, the occlusion problem in real scenes has not been completely solved. How to restrain or eliminate the negative impact of occlusion on key facial feature, is one of the hot spots in the field of face recognition. Aiming at the problem of lack of face structure information caused by occlusion, this paper reviews the occluded face recognition datasets and the occluded face recognition methods. Firstly, this paper introduces and analyzes some important new occluded face recognition datasets; Secondly, this paper summarizes the traditional learning methods and deep learning based methods to solve occlusion problems, and emphasizes the deep learning based robustness feature extraction and occluded facial information recovery. Finally, this paper summarizes and analyzes the advantages and disadvantages of relevant methods, points out the problems and challenges of occluded face recognition, and prospects the future research directions. [ABSTRACT FROM AUTHOR]

Copyright of Application Research of Computers / Jisuanji Yingyong Yanjiu is the property of Application Research of Computers Edition and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Application Research of Computers / Jisuanji Yingyong Yanjiu is the property of Application Research of Computers Edition and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Image stitching is an important branch in computer vision and computer graphics, and has a wide range of applications in 3D imaging and other aspects. Compared with the traditional image stitching framework based on feature point detection, the image stitching framework based on deep learning has stronger scene generalization performance. Although there are many research results on image stitching based on deep learning, there is still a lack of comprehensive analysis and summary of the corresponding research. In order to facilitate the subsequent work in this field, this paper sorted out the representative results in this field in the past 10 years. Based on the comparison between traditional stitching methods and deep learning-based image stitching methods, it collated and analysed the learning strategy and model architecture design, classical model review, and dataset from the three sub-problems of homography estimation, image stitching, and image rectangling in the research field of image stitching. It summarized some features of deep learning-based image stitching research methods and summarized the current research status in the field, and prospected the future research prospects. [ABSTRACT FROM AUTHOR]

Predictive business process monitoring(PBPM) represents a vital research field within BPM that aims to accurately predict future behavioral events. At present, deep learning methods are widely used in PBPM research. However, most of these methods consider only a single event-control flow perspective and do not fuse the attribute-data flow perspective for process prediction. To address this issue, this paper proposed a method called the fusion multi-perspective(FMP) framework based on a two-layer BERT neural network. Firstly, the first layer of BERT was used to learn attribute-data flow information. Subsequently, the second layer of BERT learnt event-behavior control flow information. Finally, the FMP framework combined data flow and control flow to achieve multi-perspective process prediction. Experimental results on real event logs demonstrate that, compared to other research methods, the FPM framework yields higher accuracy in predicting the next event activity. This validates that the FPM framework, which merges multi-perspective views of processes, enables a more comprehensive and in-depth analysis of complex process behaviors while enhancing predictive performance. [ABSTRACT FROM AUTHOR]

Knowledge distillation algorithms have a great effect on the streamlining of deep neural networks. The current feature-based knowledge distillation algorithms either focus on a single part for improvement and ignore other beneficial parts, or provides effective guidance for the part that a small model should focus on, which makes the distillation effect insufficient. In order to make full use of the beneficial information of the large model and process it to improve the knowledge conversion rate of the small model, this paper proposed a new distillation algorithm. Firstly, it used the conditional probability distribution to fit the feature spatial distribution of the large model's middle layer, and then extracted the spatial attention maps that tended to be similar after fitting together with other beneficial information. Finally, it used the small convolutional layer, narrowed the gap between models, transmitted the transformed information to the small model to achieve distillation. Experimental results show that the algorithm has the applicability of multiple teacher-student combinations and the generality of multiple data sets, and compared with the current more advanced distillation algorithms, the performance is improved by about 1.19% and the time is shortened by 0.16 h. It has important engineering significance and wide application prospects for large networks' optimization and the application of deep learning on low-resource devices. [ABSTRACT FROM AUTHOR]

Video distortion mainly comes from the degradation of video quality caused by spatial and temporal distortion. Aiming at these two kinds of video quality degradation, this paper proposed a full-reference video quality assessment method STPFVQA combining spatio-temporal features and visual perception. Firstly, the method extracted spatial perceptual features from reference video and distorted video using ResNet50 convolutional network. Secondly, the method feeded the extracted spatial perceptual features into transformer’s encoder and decoder to construct the serialization relationship of the video, and at the same time to explore the effect of distortion on the video serialization relationship by comparing the reference video and distorted video Then, the method sent the output of the transformer to the prediction header to form a frame-level score Finally, in order to simulate the hysteresis of human visual system perception, this paper obtained the video quality score from the short-term, long-term and global memory effects. To verify the feasibility of the method, this paper conducted experiments on four datasets, respectively LIVE,IVC-IC,CSIQ,and IVPL. The experimental results show that the proposed method is more consistent with the perception of the human visual system. Compared with the state-of-the-art serial dependence model（SDM） on the IVC-IC and CSIQ datasets, the SROCC is 2.6% and 3.1% higher, the KROCC is 6.1% and 7.9% higher, and the PLCC is 2.3% and 5.5% higher. [ABSTRACT FROM AUTHOR]

COVID-19 is spreading rapidly around the world. In order to diagnose it quickly and accurately and thus block the chain of epidemic transmission, the study proposed a deep learning-based classification network DLDA-A-DenseNet. Firstly, DenseNet-201 combined deep layer dense aggregation to aggregate feature information at different stages to enhance its ability to identify and localize lesions. Secondly, this paper proposed efficient multi-scale long-range attention to refine the aggregated features. Moreover, this paper used a balanced sampling training strategy to eliminate the bias for the class imbalance problem of CT image dataset. Testing on the China consortium of chest CT image investigation dataset, the method improved 2.24%,3.09%,2.09%,2.60% and 3.48% in accuracy, recall, precision, F1 score and Kappa coefficient compared with DenseNet-201,and achieved an optimal accuracy of 99.50% on COVID-CISet image dataset. The results show that the proposed COVID-19 CT image classification method can fully extract the lesion features of CT slices compared with other methods, and has higher classification accuracy and good generalizability. [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]

Long-tail characteristic of data has always been a great challenge in solving computer vision problems. To solve the difficulties brought to instance segmentation, image re-sampling, a simple and efficient method has always been used. However, there may be many classes in one image, it’s hard to balance different classes on the data level. This paper proposed a object-centric post-processable memory bank method. Firstly, it introduced a memory bank model and set up an object-based storage policy to address the number imbalance of categories. Then, in order to increase the predicted score for tail classes and common classes, it used a post-processing calibration to adjust the confidence score of each class. This paper verified the effectiveness of the proposed method by experiments on LVIS dataset. The accuracy can be improved by 2.2% compared to EQL method. [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]

Collaborative intrusion detection system (CIDS) can detect distributed cooperative attacks and deal with large-scale network intrusion. It has the advantages that traditional intrusion detection systems do not have. How to improve the detection performance while achieving decentralization is an important research topic. Through reviewing the research achievements of CIDS in recent years, this paper expounded the research progress and problems in detection methods, data aggregation, privacy protection and trust management, analyzed the challenges faced in decentralization, discussed the future development direction of CIDS based on blockchain technology. Finally this paper looked forward to the application prospects of CIDS in cloud computing, the Internet of Things and other emerging fields. [ABSTRACT FROM AUTHOR]

Although high-quality and high-resolution depth maps can significantly improve the performance of computer vision tasks in various natural scenes, the limitations of depth camera hardware make the depth maps captured by consumer-level depth cameras have problems such as low resolution, poor quality, invalid holes, etc. Depth super-resolution reconstruction (DSR) is a kind of technology that can effectively improve the resolution and quality of depth maps, and DSR has become a research hot-spot in the field of computer vision. Firstly, this paper introduced the definition of DSR and the research progress of DSR algorithm at home and abroad in recent years, and then mainly stated and analyzed deep learning DSR reconstruction algorithms. Next, it introduced the depth image quality evaluation criteria. Finally, this paper prospected the application fields of DSR and the challenges as well as the opportunities in the future. [ABSTRACT FROM AUTHOR]

The layout of document images is complex and distribution of object sizes is uneven, currently, most of detection methods ignore multimodal information and global dependencies. Therefore, this paper proposed a multi modal document object detection method based on vision and text. Firstly, this method explored the fusion strategy of multimodal features. In order to utilize textual features, it converted text sequence information of the image into two-dimensional representation. After the initial fusion of text features and visual features, it input the fused features to backbone network to extract multiscale features, and repeatedly integrated textual features during the extraction process, so as to realize deep fusion of multimodal features. Next, to ensure the detection accuracy of small and large objects, this paper designed a pyramid network. The lateral connection could concatenate feature maps of the same spatial size from the bottom-up pathway and the top-down pathway in channel, so as to achieve the propagation between high-level semantic information and low-level feature information. The experimental results on large public dataset PubLayNet show that the detection accuracy of this method reaches 95. 86%,and it has a higher accuracy than other methods. This method not only realizes the deep fusion of multi modal features, but also enriches the fused multimodal feature information, and it has good detection performance. [ABSTRACT FROM AUTHOR]

As a new research hotspot in deep learning, intermediate deep feature compression has gotten a great deal of attention and has been applied to edge-cloud intelligent collaboration. This paper summarized the current state of research on the intermediate deep feature compression and analyzed the problems in the current methods. Firstly, it introduced three kinds of intermediate deep feature compression from aspects of image/video coding framework, channel bit allocation and network units. Then it did the comparisons of the data set performance between the three intermediate deep feature compression. Finally, this paper discussed the existing challenges and solutions in intermediate deep feature compression and looked forward to the feature trends of intermediate deep feature compression. [ABSTRACT FROM AUTHOR]

Copyright of Application Research of Computers / Jisuanji Yingyong Yanjiu is the property of Application Research of Computers Edition and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Local feature information plays an important role in image segmentation, however, the referring image segmentation task is dependent on the text expression, so it is impossible to extract local feature information directly from the original reference image. In order to solve this problem, this paper proposes a specific noun-guided local feature extraction deep neural network model（NgLFNet). The NgLFNet model can automatically mine the local feature information of the object to be segmented according to the key nouns in the input text expression. Specifically, the model first obtains key nouns in text through sentence analysis; secondly, extracting corresponding features through text and image encoders, and using the key nouns to obtain local features of high-interest regions through the multihead attention mechanism; then the multi-modal features are gradually fused to learn; Finally, the decoding and correction module uses the obtained local features to perform more detailed corrections on the prediction mask to obtain the final result. The method in this paper is compared with a variety of mainstream referring segmentation methods and the experimental results show that the proposed method improves the accuracy of text-based instance segmentation task. [ABSTRACT FROM AUTHOR]

Object surface defect detection technology is an important subject in the field of industrial quality inspection, which is of great significance to industrial production. This paper mainly summarized the surface defect detection techniques based on machine vision in recent years. Firstly, it listed several application scenarios of defect detection in the industry. Secondly, from the perspective of feature extraction and classification algorithms, it expounded on traditional machine vision methods. Then, this paper focused on the classical neural network structure and the latest development of defect detection algorithms and introduced two commonly used optimization methods of the defect detection algorithm. Finally, it analyzed three major challenges in the field of defect detection; real-time problems, small sample problems and small target problems. The purpose was to provide useful references and context for the research of industrial surface defect detection. [ABSTRACT FROM AUTHOR]

Generative adversarial network (GAN), as an emerging generative model, has been gradually developed and applied in the fields of image generation, 3D reconstruction, cross-modal conversion, etc. It effectively solves the problem of inefficiency of conventional convolutional neural networks in image-generating tasks and fills the shortage of deep learning in the field of image generation. In order to help subsequent researchers quickly and comprehensively understand GAN, this paper sorted out the improved model of GAN based on the literature in recent years. It firstly introduced the basic principles of GAN from two perspectives of network structure and objective function, then elaborated and summarized various derivative models of GAN from two major perspectives of improvement and application types. Secondly it summarized and analyzed the quality and diversity of generated images from the perspectives of subjective qualitative, objective quantitative and task-specific evaluation. Finally, this paper discussed some core issues and latest research progress of GAN series models in recent years and analyzed the future development trend. [ABSTRACT FROM AUTHOR]

In recent years, the deep learning network model based on UNet and GAN (generative adversarial network) has shown unique advantages in the field of image restoration. But, there are still artifacts, blurring, degradation of texture details, difficult to repair large-area damage, and the repaired holes are incompatible with the background image. In order to solve the problems that the current existing models are not friendly to the repair of large-area damaged images and the degraded images after repair, this paper improved the Shift-UNet model by studying the existing methods. On the basis of U-Net and GAN, this paper added an improved attention mechanism Attention-UNet between each layer of encoder and decoder and integrated it into the Shift-UNet to form Attention-Shift-UNet. And through research, it changed the activation function of the original down-sampling part from Leaky＿ ReLU to SiLU. The improved model not only achieved good results on the 64×64 central cover, but also realized the random cover, and the cover area increased from 20 % to 80 %. The experimental results show that the repair effect of the proposed model is better, especially for the repair of large-area damaged images. After testing on CelebA, Paris Architecture and Paris Stree View datasets, the evaluation indexes have been significantly improved, and SSIM has increased from 0.944 5 to 0.947 1. PSNR is increased from 27.992 7 to 28.553 6. L2 loss is decreased from 0.001 7 to 0.001 5. [ABSTRACT FROM AUTHOR]

Aspect and opinion pair extraction aims to extract aspect and opinion items and match relations from a given sentence. However, related studies typically extract aspects and opinions independently without identifying the relationships. To identify the relationships of aspect and opinion item, this paper proposed a knowledge-augmented multi-task learning model for aspect and opinion pair extraction. First, it used the pre-trained language model to generate word vectors with semantic information for the text. In order to achieve the effect of knowledge enhancement, it used the masked attention mechanism to integrate the semantic information of the knowledge graph into the word vectors, and used the sequence labeling method based on the distance-based attention and conditional random fields to extract aspects and opinions. Finally, it matched the extracted aspects and opinions to predict the corresponding relationship. In order to strengthen the connection between the aspect and opinion extraction module and the matching module, the model adopted a shared coding layer to achieve joint training. In addition, in the training process, the matching module used the real labels as input, and used the result of the extraction module as input in the testing process. Finally, to demonstrate the effectiveness of the model, this paper used three general domain datasets for comparative experiments. The model achieves F, values of 66. 99%, 75. 17% and 67. 30% in aspect and opinion matching tasks respectively, and outperforms other comparative models. [ABSTRACT FROM AUTHOR]

The radar echo extrapolation method is widely used in rainfall forecasting. Addressing the issue of insufficient prediction accuracy in radar echoes, this paper proposed a deep learning model DIPredRNN based on recurrent neural networks. This model combined long-term temporal and channel information by introducing a dual attention mechanism of space and channel, improved the long-term dependence of time memory. By introducing an interactive framework of hidden states and inputs, it retained more features and improved the short-term dependence of temporal memory. This model was experimentally compared with classical models and many advanced models on the HKO-7 and Sichuan datasets. The model achieved the best results in comparing multiple indicators such as extrapolated images, MSE, SSIM, CSI-30~50 dbz. The experiment proves that the proposed DIPredRNN network improves the radar echo prediction performance and has advanced performance. [ABSTRACT FROM AUTHOR]

The majority of current machine learning and deep learning solutions for ECG-based emotion recognition utilize fully-supervised learning methods. Several limitations of this approach are that large human-annotated datasets and computing resources are required. Furthermore, the feature representations learned by fully supervised methods tend to be task-specific with limited generalization capability. In response to these issues, this paper proposed an approach based on contrastive lear-ning for ECG-based emotion recognition, which consisted of two steps, such as pre-training and fine-tuning. The goal of pre-training was to learn representations from unlabeled EGG data through contrastive learning. Specifically, it designed two simple and efficient ECG signal augmentation methods, and used these two views to learn robust temporal representations in the time contrastive module, followed by learning discriminative feature representations in the context contrastive module. Fine-tuning used labelled data to learn emotion recognition. Experiments show that the proposed method has reached the maximum accuracy on three public ECG-based emotion recognition datasets. Additionally, the proposed method shows high efficiency under the semi-supervised settings. [ABSTRACT FROM AUTHOR]

As a popular research direction in the field of artificial intelligence, Facial Expression Recognition (FER) is the most direct and effective way for computers to access human emotions. It occupies a key technical position in human-computer interaction, intelligent medical care, fatigue driving, and other R＆D topics. In order to meet the application requirements of high recognition rate, the structure of FER deep learning network becomes more and more complex, occupying a large amount of computing resources and storage space, which seriously affects the real-time requirements of the algorithm. This paper focuses on the problem of how to guarantee the accuracy of the model while effectively improving its computational speed. Firstly, it introduces the important datasets for expression recognition using lightweight networks; Secondly, it analyzes the classical lightweight network models used for facial expression recognition; Thirdly, it describes the principles, characteristics, and applicable scenarios of the main network lightweighting methods; Finally, it summarizes the problems and challenges of lightweight networks in facial expression recognition research and looks forward to the future research direction. [ABSTRACT FROM AUTHOR]

The current research on the application of artificial intelligence techniques to the field of system architecture is promising, especially the research on applying deep learning to data prefetching in multicore architectures has become a research hotspot at home and abroad. This work studied the cache prefetching task based on deep learning and defined the deep learning cache prefetch model formally. Based on the introduction of current common multi-core cache architectures and prefetching techniques, this paper comprehensively analyzed the design ideas of existing typical cache prefetchers based on deep learning. The application of deep learning neural network in the field of multicore cache prefetching mainly adopts machine learning methods such as deep neural network, recurrent neural network, long and short-term memory network and attention mechanism. A comprehensive comparative analysis of existing deep learning-based data prefetching hierarchical neural models reveals that deep learning-based multicore cache prefetching techniques still have certain computational cost, model optimization, and practicality. In the future, there is still much room for research exploration and development prospect in adaptive prefetching models and the practicality of neural network prefetching models. [ABSTRACT FROM AUTHOR]

To address the problem of poor recommendation accuracy in the session recommendation model, this paper proposed a capsule-based graph convolutional disentanglement for session-aware recommendation (CGCD) method.Specifically, it used disentangled learning technique to transition item embedding into factor embedding based on multiple sub-channels. Then, it used a capsule dynamic fusion strategy to aggregate different factors to obtain a new item embedding.In addition, it used a multi-head attention mechanism to assign weights to each item in the session. Finally, it aggregated the item embedding with other items in the current session according to the assigned weights, and then generated an accurate session representation to achieve item recommendation. Experiments on two publicly available real datasets show that the proposed model can improve the Pre@10, Pre@20, MRR@10 and MRR@20 by 5.17%, 2.99%, 6.56% and 2.94% on average of the recommended performance, which verifies the effectiveness and efficiency of the method in this paper. [ABSTRACT FROM AUTHOR]

As a kind of 3 D environment data, point cloud has gotten a great deal of attention and has been applied to many scenarios because of its high accuracy. In recent years, deep learning has entered the field of point cloud, enabling the rapid development of point cloud data processing. Based on the deep learning point cloud three-dimensional target detection task, this paper firstly analyzed the characteristics of point cloud data and listed the point cloud data sets which was commonly used in daily tasks. Then this paper classified the process of single mode 3 D object detection and multimode 3 D object detection and did the comparison of the data sets performance between single-mode and multimode states. Finally, this paper summarized and prospected the development trend of current point cloud 3 D target detection research. [ABSTRACT FROM AUTHOR]

In order to mitigate mode collapse when generative adversarial networks (GANs) synthesis images, this paper proposed maximizing middle modes and minor modes in generative adversarial networks (MMMGANs). First of all, MMMGANs defined the mode of the generated images with the identical label as the middle mode and the minor mode. The middle mode and the minor mode separately represented the collection of similar modes and the possible mode changes after learning the middle modes. Secondly, based on the above definition, this paper proposed maximizing middle modes and minor modes loss. Finally, on the premise that the distribution of generated images was possibly close to the real image, MMMGANs improved more than 90% of evaluation metrics and then enhanced diversity of generated images. Extensive experimental results show that the proposed maximizing middle modes and minor modes loss effectively alleviates mode collapse in two or more different types of tasks. [ABSTRACT FROM AUTHOR]

Bone age assessment is a common method to detect endocrine and growth abnormalities in children. But in deep learning methods, low-quality hand X-ray images reduce the final evaluation accuracy. To solve this problem, this paper proposed an alignment network that increases the area of interest in hand X-ray images. This network uses the Swin Transformer structure as the backbone network to learn image hand similarity and obtain affine coefficients and does not require large-scale hand annotation during the training process. In the bone age assessment network, for the improvement of efficient channel attention and spatial attention mechanism. This paper proposed dual-pool efficient channel attention and asymmetric convolution spatial attention method and combines these two methods in the form of dual attention and Xception network proposes DA-Xception. This paper tested the RSNA dataset, which achieved a mean absolute error of 5.37 months for this bone age assessment method. Compared with other deep learning methods, this method can fully extract features and optimize the evaluation results. [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]

Point of interest recommendation is one of the research hotspots in location-based social networks. Firstly, this paper analyzes the references about point-of-interest recommendation research from Web of Science, then it analyzes the factors that influence point-of-interest recommendation. Furthermore, based on the analysis of traditional methods of point-of-interest recommendation, this paper mainly analyzes the methods of point-of-interest recommendation based on deep learning from two aspects: modeling of user historical check-in information and extraction of user social generated information. Finally, it looks forward to future research directions that may improve the performance of point-of-interest recommendation. [ABSTRACT FROM AUTHOR]