Most Read articles

    Published in last 1 year |  In last 2 years |  In last 3 years |  All

    Published in last 1 year
    Please wait a minute...
    For Selected: Toggle Thumbnails
    Review of Deep Learning Applied to Time Series Prediction
    LIANG Hongtao, LIU Shuo, DU Junwei, HU Qiang, YU Xu
    Journal of Frontiers of Computer Science and Technology    2023, 17 (6): 1285-1300.   DOI: 10.3778/j.issn.1673-9418.2211108
    The time series is generally a set of random variables that are observed and collected at a certain frequency in the course of something??s development. The task of time series forecasting is to extract the core patterns from a large amount of data and to make accurate estimates of future data based on known factors. Due to the access of a large number of IoT data collection devices, the explosive growth of multidimensional data and the increasingly demanding requirements for prediction accuracy, it is difficult for classical parametric models and traditional machine learning algorithms to meet high efficiency and high accuracy requirements of prediction tasks. In recent years, deep learning algorithms represented by convolutional neural networks, recurrent neural networks and Trans-former models have achieved fruitful results in time series forecasting tasks. To further promote the development of time series prediction technology, common characteristics of time series data, evaluation indexes of datasets and models are reviewed, and the characteristics, advantages and limitations of each prediction algorithm are experimentally compared and analyzed with time and algorithm architecture as the main research line. Several time series prediction methods based on Transformer model are highlighted and compared. Finally, according to the problems and challenges of deep learning applied to time series prediction tasks, this paper provides an outlook on the future research trends in this direction.
    Reference | Related Articles | Metrics
    Survey of Camouflaged Object Detection Based on Deep Learning
    SHI Caijuan, REN Bijuan, WANG Ziwen, YAN Jinwei, SHI Ze
    Journal of Frontiers of Computer Science and Technology    2022, 16 (12): 2734-2751.   DOI: 10.3778/j.issn.1673-9418.2206078

    Camouflaged object detection (COD) based on deep learning is an emerging visual detection task, which aims to detect the camouflaged objects “perfectly” embedded in the surrounding environment. However, most exiting work primarily focuses on building different COD models with little summary work for the existing methods. Therefore, this paper summarizes the existing COD methods based on deep learning and discusses the future development of COD. Firstly, 23 existing COD models based on deep learning are introduced and analyzed according to five detection mechanisms: coarse-to-fine strategy, multi-task learning strategy, confidence-aware learning strategy, multi-source information fusion strategy and transformer-based strategy. The advantages and disadvantages of each strategy are analyzed in depth. And then, 4 widely used datasets and 4 evaluation metrics for COD are introduced. In addition, the performance of the existing COD models based on deep learning is compared on four datasets, including quantitative comparison, visual comparison, efficiency analysis, and the detection effects on camouflaged objects of different types. Furthermore, the practical applications of COD in medicine, industry, agriculture, military, art, etc. are mentioned. Finally, the deficiencies and challenges of existing methods in complex scenes, multi-scale objects, real-time performance, practical application requirements, and COD in other multimodalities are pointed out, and the potential directions of COD are discussed.

    Table and Figures | Reference | Related Articles | Metrics
    Survey of Few-Shot Object Detection
    LIU Chunlei, CHEN Tian‘en, WANG Cong, JIANG Shuwen, CHEN Dong
    Journal of Frontiers of Computer Science and Technology    2023, 17 (1): 53-73.   DOI: 10.3778/j.issn.1673-9418.2206020
    Object detection as a hot field in computer vision, usually requires a large number of labeled images for model training, which will cost a lot of manpower and material resources. At the same time, due to the inherent long-tailed distribution of data in the real world, the number of samples of most objects is relatively small, such as many uncommon diseases, etc., and it is difficult to obtain a large number of labeled images. In this regard, few-shot object detection only needs to provide a small amount of annotation information to detect objects of interest. This paper makes a detailed review of few-shot object detection methods. Firstly, the development of general target detection and its existing problems are reviewed, the concept of few-shot object detection is introduced, and other tasks related to few-shot object detection are differentiated and explained. Then, two classical paradigms based on transfer learning and meta-learning for existing few-shot object detection are introduced. According to the improvement strategies of different methods, few-shot object detection is divided into four types: attention mechanism, graph convolutional neural network, metric learning and data augmentation. The public datasets and evaluation metrics used in these methods are explained. Advantages, disadvantages, applicable scenarios of different methods, and performance on different datasets are compared and analyzed. Finally, the practical application fields and future research trends of few-shot object detection are discussed.
    Reference | Related Articles | Metrics
    Review of Graph Neural Networks Applied to Knowledge Graph Reasoning
    SUN Shuifa, LI Xiaolong, LI Weisheng, LEI Dajiang, LI Sihui, YANG Liu, WU Yirong
    Journal of Frontiers of Computer Science and Technology    2023, 17 (1): 27-52.   DOI: 10.3778/j.issn.1673-9418.2207060
    As an important element of knowledge graph construction, knowledge reasoning (KR) has always been a hot topic of research. With the deepening of knowledge graph application research and the expanding of its scope, graph neural network (GNN) based KR methods have received extensive attention due to their capability of obtaining semantic information such as entities and relationships in knowledge graph, high interpretability, and strong reasoning ability. In this paper, firstly, basic knowledge and research status of knowledge graph and KR are summarized. The advantages and disadvantages of KR approaches based on logic rules, representation learning, neural network and graph neural network are briefly introduced. Secondly, the latest progress in KR based on GNN is comprehensively summarized. GNN-based KR methods are categorized into knowledge reasoning based on recurrent graph neural networks (RecGNN), convolutional graph neural networks (ConvGNN), graph auto-encoders (GAE) and spatial-temporal graph neural networks (STGNN). Various typical network models are introduced and compared. Thirdly, this paper introduces the application of KR based on graph neural network in health care, intelligent manufacturing, military, transportation, etc. Finally, the future research directions of GNN-based KR are proposed, and related research in various directions in this rapidly growing field is discussed.
    Reference | Related Articles | Metrics
    Overview of Facial Deepfake Video Detection Methods
    ZHANG Lu, LU Tianliang, DU Yanhui
    Journal of Frontiers of Computer Science and Technology    2023, 17 (1): 1-26.   DOI: 10.3778/j.issn.1673-9418.2205035
    The illegal use of deepfake technology will have a serious impact on social stability, personal reputation and even national security. Therefore, it is imperative to develop research on facial deepfake videos detection tech-nology, which is also a research hotspot in the field of computer vision in recent years. At present, the research is based on traditional face recognition and image classification technology, building a deep neural network to deter-mine a facial video is real or not, but there are still problems such as the low quality of dataset, the combine of multimodal features and the poor performance of model generalization. In order to further promote the development of deepfake video detection technology, a comprehensive summary of various current algorithms is carried out, and the existing algorithms are classified, analyzed and compared. Firstly, this paper mainly introduces the facial deepfake videos detection datasets. Secondly, taking feature selection as the starting point, this paper summarizes the main method of detecting deepfake videos in the past three years, classifies various detection technologies from the pers-pectives of spatial features, spatial-temporal fusion features and biological features, and introduces some new detec-tion methods based on watermarking and blockchain. Then, this paper introduces the new trends of facial deepfake video detection methods from the aspects of feature selection, transfer learning, model architecture and training ideas. Finally, the full text is summarized and the future technology development is prospected.
    Reference | Related Articles | Metrics
    Survey on 3D Reconstruction Methods Based on Visual Deep Learning
    LI Mingyang, CHEN Wei, WANG Shanshan, LI Jie, TIAN Zijian, ZHANG Fan
    Journal of Frontiers of Computer Science and Technology    2023, 17 (2): 279-302.   DOI: 10.3778/j.issn.1673-9418.2205054
    In recent years, as one of the important tasks of computer vision, 3D reconstruction has received extensive attention. This paper focuses on the research progress of using deep learning to reconstruct the 3D shape of general objects in recent years. Taking the steps of 3D reconstruction by deep learning as the context, according to the data feature representation in the process of 3D reconstruction, it is divided into voxel, point cloud, surface mesh and implicit surface. Then, according to the number of inputting 2D images, it can be divided into single view 3D reconstruction and multi-view 3D reconstruction, which are subdivided according to the network architecture and the training mechanism they use. While the research progress of each category is discussed, the development prospects, advantages and disadvantages of each training method are analyzed. This paper studies the new hotspots in specific 3D reconstruction fields in recent years, such as 3D reconstruction of dynamic human bodies and 3D completion of incomplete geometric data, compares some key papers and summarizes the problems in these fields. Then this paper introduces the key application scenarios and parameters of 3D datasets at this stage. The development prospect of 3D reconstruction in specific application fields in the future is illustrated and analyzed, and the research direction of 3D reconstruction is prospected.
    Reference | Related Articles | Metrics
    Survey on 3D Human Pose Estimation of Deep Learning
    WANG Shichen, HUANG Kai, CHEN Zhigang, ZHANG Wendong
    Journal of Frontiers of Computer Science and Technology    2023, 17 (1): 74-87.   DOI: 10.3778/j.issn.1673-9418.2205070
    The purpose of 3D human pose estimation is to predict information such as the 3D coordinate position and angle of human joint points, and construct human representations (such as human bones) for further analysis of human posture. With the continuous advancement of deep learning methods, more and more high-performance 3D human pose estimation methods based on deep learning have been proposed. However, due to the human occlusion of the picture and the large demand for training scale, there are still challenges in 3D human pose estimation. The research purpose of this paper is to review a number of research papers in recent years, analyze and compare the reasoning process and core elements of these methods, and comprehensively elaborate the 3D human pose estimation methods based on deep learning in recent years. In addition, this paper also introduces the relevant data- sets and evaluation indicators, compares the experimental data of some models on the Human3.6M dataset, Campus dataset and Shelf dataset, and analyzes and compares the experimental results. Finally, according to the results of this survey, the difficulties and challenges faced by the current 3D human pose estimation are discussed, and the future development of 3D human pose estimation is discussed.
    Reference | Related Articles | Metrics
    Survey of Research on Smart Contract Vulnerability Detection
    LI Leixiao, ZHENG Yue, GAO Haoyu, XIONG Xiao, NIU Tieming, DU Jinze, GAO Jing
    Journal of Frontiers of Computer Science and Technology    2022, 16 (11): 2456-2470.   DOI: 10.3778/j.issn.1673-9418.2203024

    As an important part of blockchain technology, smart contracts are widely used in various fields through decentralized applications written by smart contracts, providing important technical support for the development and application of blockchain. However, the development has brought security problems at the same time, and a large number of vulnerability attacks against smart contracts have made researchers pay more attention to the security vulnerabilities of smart contracts. How to quickly and accurately perform vulnerability detection has become an urgent problem to be solved. Firstly, through the analysis of common vulnerabilities such as reentrancy attack vulnerabilities, integer overflow and access control vulnerabilities, researchers can fully understand the common vulnerabilities. Secondly, by investigating the current status of vulnerability detection methods such as formal verification, symbolic execution, machine learning and their corresponding tools at home and abroad, analyzing and discussing the advantages and disadvantages of the tools, at the same time, replicating some tools for experiments, the performance of the vulnerability detection tools is demonstrated based on the detection speed, accuracy, and the number of vulnerabilities that support detection. Finally, suggestions for future research directions are given based on the analysis results of smart contract vulnerability detection tools.

    Table and Figures | Reference | Related Articles | Metrics
    Survey of Sign Language Recognition and Translation
    YAN Siyi, XUE Wanli, YUAN Tiantian
    Journal of Frontiers of Computer Science and Technology    2022, 16 (11): 2415-2429.   DOI: 10.3778/j.issn.1673-9418.2205003

    Different from spoken languages, sign language is mainly composed of continuous gestures. Sign langu-age recognition and translation are important means of facilitating barrier-free communication between the hearing-impaired and the hearing person. The sign language recognition and translation research task is a typical multi-domain cross-study by processing and analyzing sign language videos and displaying the recognition results in text form. In recent years, sign language recognition and translation research based on deep learning has made great progress. In order to facilitate researchers to systematically and comprehensively understand the research tasks of sign language recognition and translation, the review work is carried out from the perspectives of sign language recognition and sign language translation. Firstly, the translation research work is classified and summarized and its characteristics are analyzed. Secondly, the common sign language recognition and translation research datasets of different countries are summarized and classified from the perspectives of isolated sign language words and continuous sign language sentences. Based on the difference in research tasks, the corresponding evaluation index system is introduced. Finally, the major challenges of current research on sign language recognition and translation are summarized from the aspects of effective information extraction of sign language visual features, multi-cue weight assignment, relationship between sign language and natural language grammar, and sign language dataset resources.

    Table and Figures | Reference | Related Articles | Metrics
    Survey of Deep Online Multi-object Tracking Algorithms
    LIU Wenqiang, QIU Hangping, LI Hang, YANG Li, LI Yang, MIAO Zhuang, LI Yi, ZHAO Xinxin
    Journal of Frontiers of Computer Science and Technology    2022, 16 (12): 2718-2733.   DOI: 10.3778/j.issn.1673-9418.2204041

    Video multi-object tracking is a key task in the field of computer vision and has a wide application prospect in industry, commerce and military fields. At present, the rapid development of deep learning provides many solutions to solve the problem of multi-object tracking. However, the challenging problems such as mutation of target appearance, serious occlusion of target area, disappearance and appearance of target have not been completely solved. This paper focuses on online multi-object tracking algorithm based on deep learning, and summarizes the latest progress in this field. According to the three important modules of feature prediction, apparent feature extraction and data association, as will as the two frameworks of detection-based-tracking (DBT) and joint-detection-tracking (JDT), this paper divides deep online multi-object tracking algorithms into six sub-classes, and discusses the principles, advantages and disadvantages of different types of algorithms. Among them, the multi-stage design of the DBT algorithm has a clear structure and is easy to optimize, but multi-stage training may lead to sub-optimal solutions; the sub-modules of the JDT algorithm that integrates detection and tracking achieve faster inference speed, but there is a problem of collaborative training of each module. Currently, multi-target tracking begins to focus on long-term feature extraction of targets, occlusion target processing, association strategy improvement, and end-to-end framework design. Finally, combined with the existing algorithms, this paper summarizes urgent problems to be solved in deep online multi-object tracking and looks forward to possible research directions in the future.

    Table and Figures | Reference | Related Articles | Metrics
    Survey of Research on Instance Segmentation Methods
    HUANG TAO, LI Hua, ZHOU Gui, LI Shaobo, WANG Yang
    Journal of Frontiers of Computer Science and Technology    2023, 17 (4): 810-825.   DOI: 10.3778/j.issn.1673-9418.2209051
    In recent years, with the continuous improvement of computing level, the research of instance segment-ation methods based on deep learning has made great breakthroughs. Image instance segmentation can distinguish different instances of the same class in images, which is an important research direction in the field of computer vision with broad research prospects, and has achieved great actual application value in scene comprehension, medical image analysis, machine vision, augmented reality, image compression, video monitoring, etc. Recently, instance segmentation methods have been updated more and more frequently, but there is a little literature to comprehensively and systematically analyze the research background related to instance segmentation. This paper  provides a comprehensive and systematic analysis and summary of the image instance segmentation methods based on deep learning. Firstly, this paper introduces the currently used common public datasets and evaluation indexes in instance segmentation, and analyzes the challenges of current datasets. Secondly, this paper respectively combs and summarizes the instance segmentation algorithms in the characteristics of two-stage segmentation methods and single-stage segmentation methods, elaborates their central ideas and design thoughts, and summarizes the advantages and shortcomings of the two types of methods. Thirdly, this paper evaluates the segmentation accuracy and speed of the models on a public dataset. Finally, this paper summarizes the current difficulties and challenges of instance segmentation, presents the solution ideas for facing the challenges, and makes a prospect for future research directions.
    Reference | Related Articles | Metrics
    Review of Chinese Named Entity Recognition Research
    WANG Yingjie, ZHANG Chengye, BAI Fengbo, WANG Zumin, JI Changqing
    Journal of Frontiers of Computer Science and Technology    2023, 17 (2): 324-341.   DOI: 10.3778/j.issn.1673-9418.2208028
    With the rapid development of related technologies in the field of natural language processing, as an upstream task of natural language processing, improving the accuracy of named entity recognition is of great significance for subsequent text processing tasks. However, due to the differences between Chinese and English languages, it is difficult to transfer the research results of English named entity recognition into Chinese research effectively. Therefore, the key issues in the current research of Chinese named entity recognition are analyzed from the following four aspects: Firstly, the development of named entity recognition is taken as the main clue, the advantages and disadvantages, common methods and research results of each stage are comprehensively discussed. Secondly, the Chinese text preprocessing methods are summarized from the perspective of sequence annotation, evaluation index, Chinese word segmentation methods and datasets. Then, aiming at the Chinese character and word feature fusion method, the current research is summarized from the perspective of character fusion and word fusion, and the optimization direction of the current Chinese named entity recognition model is discussed. Finally, the practical applications of Chinese named entity recognition in various fields are analyzed. This paper discusses the current research on Chinese named entity recognition, aiming to help researchers understand the research direction and significance of this task more comprehensively, so as to provide a certain reference for proposing new methods and new improvements.
    Reference | Related Articles | Metrics
    Survey of Few-Shot Image Classification Research
    AN Shengbiao, GUO Yuqi, BAI Yu, WANG Tengbo
    Journal of Frontiers of Computer Science and Technology    2023, 17 (3): 511-532.   DOI: 10.3778/j.issn.1673-9418.2210035
    In recent years, artificial intelligence algorithms represented by deep learning have achieved success in many fields by relying on large-scale datasets and huge computing resources. Among them, the image classification technology in the field of computer vision develops vigorously, and many mature visual task classification models emerge. All these models need to use a large number of annotated samples for training. However, in actual scena-rios, due to many restrictions, the amount of data is scarce, and it is often difficult to obtain high-quality annotated samples of corresponding scale. Therefore, how to use a small number of samples for learning has gradually become a research hotspot. In view of the classification task system, this paper reviews the current work related to few-shot image classification. Few-shot learning mainly adopts deep learning methods such as meta-learning, metric learning and data enhancement. This paper summarizes the research progress and typical technical models of few-shot image classification from supervised, semi-supervised and unsupervised levels, as well as the performance of these model methods on several public datasets, and makes comparative analysis from the mechanism, advantages, limitations, etc. Finally, the technical difficulties and future trends of few-shot image classification are discussed.
    Reference | Related Articles | Metrics
    Review of Real-Time Ray Tracing Technique Research
    YAN Run, HUANG Libo, GUO Hui, WANG Yongxin, ZHANG Xincheng, ZHANG Hongru
    Journal of Frontiers of Computer Science and Technology    2023, 17 (2): 263-278.   DOI: 10.3778/j.issn.1673-9418.2207067
    Ray tracing has been regarded as the next generation of mainstream image rendering technology for a long time because of the authenticity of its rendering effect, and it is a hot research point in the field of computer graphics. In recent years, academics and commercials have extensively researched real-time ray tracing. To promote the research of real-time ray tracing, this paper reviews, analyses, and summaries the related literature. Firstly, the concept, algorithms, and classification of acceleration structures are introduced. Three commercial graphics processing units (GPU) supporting ray tracing are introduced and the differences between them are compared. This paper summarizes the optimization of ray tracing from six aspects, ray packet, stackless traversal, ray reorder, wide BVH, denoising techniques, and real-time ray tracing combined with the artificial?neural network, and expounds on the advantages and disadvantages of the relevant specific methods. Based on the acceleration of the algorithms, the hardware acceleration method on GPU and the dedicated architectures are summarized. Finally, this paper makes a brief summary of the content, points out the difficulties that real-time ray tracing is still challenged, and looks forward to the future development direction. It can help researchers systematically understand real-time ray tracing status and provide follow-up research ideas.
    Reference | Related Articles | Metrics
    Improved Grey Wolf Optimizer Based on Cooperative Attack Strategy and Its PID Parameter Optimization
    LIU Wei, GUO Zhiqing, JIANG Feng, LIU Guangwei, JIN Bao, WANG Dong
    Journal of Frontiers of Computer Science and Technology    2023, 17 (3): 620-634.   DOI: 10.3778/j.issn.1673-9418.2105051
    Aiming at the shortcomings of gray wolf optimizer in solving optimization problems, such as slow convergence speed and weak global search ability, Chebyshev and wolf swarm cooperative attack strategy of grey wolf optimizer (CCA-GWO) is proposed and it is successfully applied to PID (proportion integration differen-tiation) parameter optimization. Firstly, by comparing the advantages and disadvantages of three chaotic maps, Chebyshev map is used to initialize the algorithm to enhance the diversity of initial solutions. Secondly, in order to balance the global exploration and local mining ability of the algorithm, a new nonlinear strategy is proposed to modify the control parameters [A] and [C] and the position update equation by simulating the alternate behavior of the first wolf and the second wolf when the gray wolf group is hunting. Finally, the improved algorithm is applied to PID parameter optimization. 8 benchmark functions are tested in 10, 30 and 100 dimensions, and the improved algorithm is compared with BOA, MFO, ASO, MVO, WOA and GWO. Numerical results show that CCA-GWO not only has better optimization and stability in solving benchmark functions of different dimensions, but also has better optimization performance than 6 meta-heuristic algorithms in PID parameter optimization.
    Reference | Related Articles | Metrics
    Survey of Knowledge Graph Recommendation System Research
    ZHAO Yehui, LIU Lin, WANG Hailong, HAN Haiyan, PEI Dongmei
    Journal of Frontiers of Computer Science and Technology    2023, 17 (4): 771-791.   DOI: 10.3778/j.issn.1673-9418.2205052
    Recommendation systems can obtain user preferences in massive data information to better achieve personalized recommendations, improve user physical examination and solve information overload on the Internet. However, it still suffers from cold start and data sparsity problems. A knowledge graph, as a structured knowledge base with a large number of entities and rich semantic relationships, can not only improve the accuracy of recommendation systems, but also provide the interpretability for recommendation items, thus enhancing users?? trust in recommendation systems, and providing new methods and ideas to solve a series of key problems in recommendation systems. This paper firstly studies and analyzes knowledge graph recommendation systems, classifies them into multi-domain knowledge graph recommendation systems and domain-specific knowledge graph recommendation systems based on the classification of application fields, and further classifies them according to the characteristics of these knowledge graph recommendation methods, and conducts quantitative and qualitative analyses for each type of methods. Secondly, this paper lists the datasets commonly used by knowledge graph recommendation systems in the application fields, and gives an overview of the size and characteristics of the datasets. Finally, this paper outlooks and summarizes the future research directions of knowledge graph recommendation systems.
    Reference | Related Articles | Metrics
    Review of Medical Image Segmentation Based on UNet
    XU Guangxian, FENG Chun, MA Fei
    Journal of Frontiers of Computer Science and Technology    2023, 17 (8): 1776-1792.   DOI: 10.3778/j.issn.1673-9418.2301044
    As one of the most important semantic segmentation frameworks in convolutional neural networks (CNN), UNet is widely used in image processing tasks such as classification, segmentation, and target detection of medical images. In this paper, the structural principles of UNet are described, and a comprehensive review of UNet-based networks and variant models is presented. The model algorithms are fully investigated from several perspectives, and an attempt is made to establish an evolutionary pattern among the models. Firstly, the UNet variant models are categorized according to the seven medical imaging systems they are applied to, and the algorithms with similar core composition are compared and described. Secondly, the principles, strengths and weaknesses, and applicable scenarios of each model are analyzed. Thirdly, the main UNet variant networks are summarized in terms of structural principles, core composition, datasets, and evaluation metrics. Finally, the inherent shortcomings and solutions of the UNet network structure are objectively described in light of the latest advances in deep learning, providing directions for continued improvement in the future. At the same time, other technological evolutions and application scenarios that can be combined with UNet are detailed, and the future development trend of UNet-based variant networks is further envisaged.
    Reference | Related Articles | Metrics
    Survey of Deep Learning Table-to-Text Generation
    HU Kang, XI Xuefeng, CUI Zhiming, ZHOU Yueyao, QIU Yajin
    Journal of Frontiers of Computer Science and Technology    2022, 16 (11): 2487-2504.   DOI: 10.3778/j.issn.1673-9418.2204089

    Text generation is a hot field in natural language processing. With the increasing capability of information collection, more and more structured data, such as tables, are collected. How to solve the problem of information overload, understand the table meaning and describe the table content is an important problem of artificial intelli-gence, so the task of table-to-text generation appears. Table-to-text generation refers to the language model input table data generated after the corresponding text description of the table. The text description generated by the model should express the information of the table smoothly and not deviate from the fact of the table. Firstly, this paper describes and defines the task background from table-to-text generation in detail, analyzes the main difficulties of the task, and introduces the main research methods. There are two major issues on table-to-text generation: what to describe and how to describe it. This paper summarizes the methods proposed by different researchers to solve these two problems, and summarizes the characteristics, advantages and disadvantages of the proposed models. The performance of these excellent models on the main dataset is compared and analyzed. At the same time, the models are classified according to the model type, and the horizontal comparative analysis is carried out. This paper also introduces the common evaluation methods in the field of table-to-text generation, and summaries the characte-ristics, advantages and disadvantages of different evaluation methods. Finally, this paper prospects the future development trend of table-to-text generation task.

    Table and Figures | Reference | Related Articles | Metrics
    Survey on Backdoor Attacks and Countermeasures in Deep Neural Network
    QIAN Hanwei, SUN Weisong
    Journal of Frontiers of Computer Science and Technology    2023, 17 (5): 1038-1048.   DOI: 10.3778/j.issn.1673-9418.2210061
    The neural network backdoor attack aims to implant a hidden backdoor into the deep neural network, so that the infected model behaves normally on benign test samples, but behaves abnormally on poisoned test samples with backdoor triggers. For example, all poisoned test samples will be predicted as the target label by the infected model. This paper provides a comprehensive review and the taxonomy for existing attack methods according to the attack objects, which can be categorized into four types, including data poisoning attacks, physical world attacks, model poisoning attacks, and others. This paper summarizes the existing backdoor defense technologies from the perspective of attack and defense confrontation, which include poisoned sample identifying, poisoned model identifying, poisoned test sample filtering, and others. This paper explains the principles of deep neural network backdoor defects from the perspectives of deep learning mathematical principles and visualization, and discusses the difficulties and future development directions of deep neural network backdoor attacks and countermeasures from the perspectives of software engineering and program analysis. It is hoped that this survey can help researchers understand the research progress of deep neural network backdoor attacks and countermeasures, and provide more inspiration for designing more robust deep neural networks.
    Reference | Related Articles | Metrics
    Out of Domain Face Anti-spoofing: A Survey
    SHI Yichen, FENG Jun, XIAO Lixuan, HE Jingjing, HU Jingjing
    Journal of Frontiers of Computer Science and Technology    2022, 16 (11): 2471-2486.   DOI: 10.3778/j.issn.1673-9418.2203082

    Face anti-spoofing (FAS), as an important means to protect face recognition models, can ensure that the system remains secure and reliable in the face of various presentation attacks. The current deep learning-based face anti-spoofing model has satisfactory results when the test data and training data obey the same distribution, but the accuracy of the model decreases considerably when the trained model infers in the scene outside the domain, such as cross-domain transfer and out-of-distribution scenarios. The problems that silent face anti-spoofing models will encounter in real scenarios, i.e., the models encounter unknown environments and unknown attack methods, are mainly described. The corresponding solutions are classified into four categories: methods based on domain adaptation, methods based on domain generalization, methods based on zero shot or few shot learning, and methods based on anomaly detection. Each solution and its deep learning model methods are summarized and compared. The mechanism, network structure, advantages, limitations and application scenarios of some major methods are summarized. After that, common public datasets, evaluation metrics, measurement protocols commonly used for face anti-spoofing in out of domain scenarios and test results of state-of-the-art methods under some protocols are introduced. Finally, the difficulties and challenges of face anti-spoofing in practical applications are discussed, and future research directions are summarized.

    Table and Figures | Reference | Related Articles | Metrics
    Survey of Wind Power Output Power Forecasting Technology
    WU Yuhao, WANG Yongsheng, XU Hao, CHEN Zhen, ZHANG Zhe, GUAN Shijie
    Journal of Frontiers of Computer Science and Technology    2022, 16 (12): 2653-2677.   DOI: 10.3778/j.issn.1673-9418.2205028

    Uncertainty and volatility of wind power generation, bring some serious challenges for the grid-connected wind power system. Prediction of wind power in advance is an important way to solve the above problems. Due to the existence of uncontrollable factors such as sensor transmission and network communication, the data collected for wind power prediction have abnormal values and missing values. Therefore, corresponding outlier detection and missing value interpolation operations should be performed before wind power prediction. To further promote the development of wind power data cleaning and prediction technology, current existing models and methods are analyzed and summarized, and the existing technologies are divided and compared. Starting from time series data, this paper first classifies, analyzes and summarizes the research status of outlier detection methods in the field of wind power prediction, summarizes the deficiencies and defects of existing anomaly detection methods, and prospects the research directions that may become the focus in the future development. Secondly, the evaluation indices of the existing missing value treatment methods are described. According to the different treatment methods, the processing techniques are analyzed and summarized according to the conventional treatment methods, discriminative interpolation methods, generative interpolation methods and physical characteristics methods, and the existing problems in the existing research are analyzed. Finally, the current research status of forecasting methods, multi-level forecasting and adaptive forecasting systems in existing research are analyzed and summarized, and the existing challenges and future development directions of existing forecasting are summarized and prospected.

    Table and Figures | Reference | Related Articles | Metrics
    Overview of Blockchain and Database Fusion
    LI Xinhang, LI Chao, ZHANG Guigang, XING Chunxiao
    Journal of Frontiers of Computer Science and Technology    2023, 17 (4): 761-770.   DOI: 10.3778/j.issn.1673-9418.2211021
    Recently, blockchain has been increasingly applied in finance and other fields, which is designed with the purpose to achieve secure and trusted data storage while reducing the efficiency. Meanwhile, its insufficient technological accumulation causes technology support shortage, which limits its development. As another data storage technology with development history for decades, database has a series of comparatively mature and complete technologies. As two widely-used data storage technologies, it is a significative research direction to integrate these two technologies through system architecture design and achieve a new generation of data storage technology. Based on the description of the design concept, technical characteristics and overall architecture of blockchain and database technology, the commonalities and differences as well as the advantages and disadvantages between these two data storage techniques are analyzed from several perspectives. From these perspectives and taking the two technology integration paradigms of out-of-the blockchain database and out-of-the database blockchain as the benchmark, this paper summarizes the existing works of blockchain and database technology integration. Furthermore, the crucial problems and  future development directions of blockchains and database technology integration are analyzed from a variety of dimensions.
    Reference | Related Articles | Metrics
    Review of Deep Learning in Classification of Tongue Image
    WU Xin, XU Hong, LIN Zhuosheng, LI Shengke, LIU Huilin, FENG Yue
    Journal of Frontiers of Computer Science and Technology    2023, 17 (2): 303-323.   DOI: 10.3778/j.issn.1673-9418.2208052
    With the rapid development of technology and the improvement of computing power, deep learning will be widely used in the field of tongue classification. The classification of tongue image is an important part of tongue diagnosis in traditional Chinese medicine (TCM). Traditional tongue diagnosis is dependent on understanding and judgment skills gained from personal experience under the guidance of basic theory, which leads to ambiguity and variability, affecting diagnostic reproducibility. In order to reduce the error of subjective judgment, many researchers have devoted themselves to realizing the objectification, quantification and automation of tongue diagnosis in TCM through deep learning. This paper analyzes and summarizes the research status of tongue image classification methods based on deep learning. In the study of tongue image classification, various deep learning methods are used as the research objects. The research objects are divided into categories based on early neural networks, convolutional neural networks, regional convolutional neural networks, transfer learning and other methods for summary analysis. TCM syndromes/diseases in tongue diagnosis and classification of physical constitution are discussed. A 5-fold cross-validation experiment is conducted with the public tongue diagnosis dataset on Kaggle. The dataset is a small sample of the dentate tongue, and the classification methods based on deep learning and transfer learning are evaluated. The research development of single-label and multi-label classification is discussed and prospected.
    Reference | Related Articles | Metrics
    Research Progresses of Multi-modal Intelligent Robotic Manipulation
    ZHANG Qiuju, LYU Qing
    Journal of Frontiers of Computer Science and Technology    2023, 17 (4): 792-809.   DOI: 10.3778/j.issn.1673-9418.2212070
    The flexible production trend in manufacturing and the diversified expansion of applications in service industry have prompted fundamental changes in the application demands of robots. The uncertainty of tasks and environments imposes higher requirements on the intelligence of robotic manipulation. The use of multi-modal information to monitor robotic manipulation can effectively improve the intelligence and flexibility of robot. This paper provides an in-depth analysis of the role of multi-modal information in enhancing the intelligence of robotic manipulation from the perspective of multi-modal information fusion on the basis of the two key issues of manipulation cognition and manipulation control. Firstly, the concepts of intelligent robotic manipulation and multi-modal information are clarified, and the merits of applying multi-modal information are also introduced. Then, the commonly used perception models and control methods are deeply analyzed and the existing work is sorted out and introduced in a systematic way. According to different levels of perception goals, robotic manipulation perception is divided into object perception, constraint perception and state perception; according to different control methods, the most commonly used control fusion based on analysis model, imitation learning control and reinforcement learning control are introduced. Finally, the current technical challenges and potential development trends are also discussed.
    Reference | Related Articles | Metrics
    Research Progress on 3D Object Detection of LiDAR Point Cloud
    ZHOU Yan, PU Lei, LIN Liangxi, LIU Xiangyu, ZENG Fanzhi, ZHOU Yuexia
    Journal of Frontiers of Computer Science and Technology    2022, 16 (12): 2695-2717.   DOI: 10.3778/j.issn.1673-9418.2206026

    3D object detection is a new research direction in recent years, and its main task is the location and recognization of targets in space. The existing methods for 3D object detection using monocular or binocular stereo vision are easily affected by object occlusion, viewpoint changing and scale changing in 3D scene, there will be problems such as poor detection accuracy and robustness. LiDAR point cloud can provide 3D scene information, so using deep learning method to complete 3D object detection based on LiDAR point cloud has become a research hotspot in the field of 3D vision. Aiming at the 3D object detection based on LiDAR point cloud, the relevant research in recent years is reviewed. Firstly, the 3D object detection methods based on LiDAR point cloud are divided into point cloud based, point cloud projection based, point cloud voxelization based and multi-modal fusion based 3D object detection methods according to the data form of network input, and the most representative methods in each category are described in detail. Then common datasets are introduced, and the performance of representative methods is evaluated, and the advantages and limitations of each method are discussed from several aspects. Finally, the shortcomings and difficulties are given, and the future development directions are also discussed and put forward.

    Table and Figures | Reference | Related Articles | Metrics
    SSD Object Detection Algorithm with Attention and Cross-Scale Fusion
    LI Qingyuan, DENG Zhaohong, LUO Xiaoqing, GU Xin, WANG Shitong
    Journal of Frontiers of Computer Science and Technology    2022, 16 (11): 2575-2586.   DOI: 10.3778/j.issn.1673-9418.2102001

    In order to further improve the performance of the SSD (single shot multibox detector) algorithm, and solve the problems of unbalanced feature map information and difficulty in small target recognition during multi-scale prediction of the SSD algorithm, in this paper, plug-and-play modules are designed to fully integrate the information contained in feature maps of different scales and model the relationships within feature maps to enhance the representation ability of feature maps. Firstly, a novel feature fusion method is designed to solve the problem of information disparity in cross-scale feature fusion. Secondly, according to the idea of pooling pyramid, a depth feature extraction module is designed to extract the information of different receptive fields, so as to improve the detection ability of the model to object of different sizes. Finally, in order to further optimize the feature map, highlight the effective information of the feature map for the current task, and establish the global long-distance relationship between pixels and the importance relationship between each channel, a lightweight attention module is proposed. Through the above mechanism, the structure of SSD model is modified in this paper, which effectively improves the detection accuracy and robustness of SSD algorithm. Extensive experiments have been conducted on PASCAL VOC datasets to verify the efficiency of the proposed method. On PASCAL VOC2007 test datasets, the proposed method improves 2.9 percentage points mean average precision (mAP) over SSD algorithm, while maintaining the ability of real-time detection.

    Table and Figures | Reference | Related Articles | Metrics
    Survey on Meta-Learning Research of Algorithm Selection
    LI Gengsong, LIU Yi, QIN Wei, LI Hongmei, ZHENG Qibin, SONG Mingwu, REN Xiaoguang
    Journal of Frontiers of Computer Science and Technology    2023, 17 (1): 88-107.   DOI: 10.3778/j.issn.1673-9418.2204019
    With the rapid development of artificial intelligence, the selection of algorithms that meet application requirements from feasible algorithms has become a critical problem to be solved urgently in various fields, that is, the algorithm selection problem. The approach based on meta-learning is an important way to solve the algorithm selection problem, which is widely applied in algorithm selection research and achieves good results. The approach selects appropriate algorithms by constructing the mapping model from problem features to candidate algorithms performance, mainly including the steps of extracting meta-features, calculating candidate algorithms performance, constructing meta-dataset and training meta-model, etc. Firstly, this paper expounds the concept and framework of algorithm selection based on meta-learning, and reviews related surveys. Secondly, it summarizes the research progress from three aspects: meta-features, meta-learners and meta-model performance measures, introduces typical methods and compares the advantages, disadvantages and application scope of different types of methods. Then, it outlines the application of algorithm selection based on meta-learning in different learning tasks. Next, it utilizes 140 classification datasets, 9 candidate classification algorithms and 5 performance indicators to conduct algorithm selection experiments to compare the performance of different algorithm selection methods. Finally, it analyzes the current challenges and problems, and discusses future development directions.
    Reference | Related Articles | Metrics
    Overview of Visual Inertial Odometry Technology Based on Deep Learning
    WANG Wensen, HUANG Fengrong, WANG Xu, LIU Qinglin, YI Boheng
    Journal of Frontiers of Computer Science and Technology    2023, 17 (3): 549-560.   DOI: 10.3778/j.issn.1673-9418.2209014
    Visual inertial odometer can well realize the complementary advantages of vision and inertial sensors, and obtain high precision 6-DOF navigation and positioning, so it has a very wide range of applications. However, the errors of sensors themselves, the disturbance of abnormal visual environment, and the space-time calibration errors between multi-sensor will interfere with the navigation results, leading to the decline of navigation accuracy. In recent years, the deep learning method is developing rapidly. With its powerful data processing and prediction ability, it provides a new direction for the development of visual inertial odometer. This paper reviews the main development achievements of deep learning-based methods. First of all, according to the fusion mode, the research methods are summarized, which are divided into the method combining deep learning with traditional models and the end-to-end method based on deep learning. Then, according to the type of deep learning, visual inertial odometer can be divided into supervised learning and unsupervised/self-supervised learning methods, and the model structures of these methods are described respectively. Next, the optimization and evaluation methods of the system are summarized, and the performance of some of them is compared. Finally, this paper summarizes the key and difficult problems that need to be solved in this field, and looks forward to the future development.
    Reference | Related Articles | Metrics
    Anonymous Communication and Darknet Space Comprehensive Governance
    LAN Haoliang, LI Fujuan, WANG Qun, YIN Jie, XU Jie, HONG Lei, XUE Yishi, XIA Minghui
    Journal of Frontiers of Computer Science and Technology    2022, 16 (11): 2430-2455.   DOI: 10.3778/j.issn.1673-9418.2204004

    The characteristics of anonymous communication, such as difficulty in node discovery, service positio-ning, communication relationship confirmation, and user monitoring, make the darknet built on it full of various illegal and criminal activities of anonymous abuse. To this end, the academic community has carried out a series of targeted research around anonymous communication and darknet. Accordingly, on the basis of systematically intro-ducing the development history of anonymous communication, anonymous mechanisms and typical systems, this paper focuses on combing, summarizing and inducing related research in this field by combining key technologies of anonymous communication, anonymity measurement, anonymous attack, anonymous enhancement, anonymous communication performance evaluation and improvement and darknet space comprehensive governance. Mean-while, this paper focuses and analyzes the development trend of anonymous communication research in the future and the challenges and countermeasures faced by the darknet space comprehensive governance.

    Table and Figures | Reference | Related Articles | Metrics
    Knowledge-Enhanced Interactive Attention Model for Aspect-Based Sentiment Analysis
    HAN Hu, HAO Jun, ZHANG Qiankun, MENG Tiantian
    Journal of Frontiers of Computer Science and Technology    2023, 17 (3): 709-718.   DOI: 10.3778/j.issn.1673-9418.2108082
    Aspect-based sentiment analysis (ABSA) has become one of the hottest research issues in the field of natural language processing. Compared with traditional sentiment analysis technology, aspect-based sentiment analy-sis can judge the sentiment tendency of multiple targets in a sentence, and more accurately mine the sentiment polarity of the aspect. Currently, the models combining attention mechanism and neural network only consider the impact of aspects on the context, and often ignore the context information of sentences and background knowledge. To solve the above problems, an interactive attention neural network model based on knowledge maps and graph convolution network is proposed to inject background information and language knowledge into review text. Firstly, the polysemy problem of vocabulary under different contexts is addressed via knowledge maps. Secondly, text graph convolution networks are used to improve the syntactic structure information of review text. Finally, the context and aspect of the review text are coordinated and optimized through an interactive attention mechanism. Experimental results on five public datasets show that rational use of external knowledge is an effective strategy for enhancing the performance of aspect-based sentiment analysis model.
    Reference | Related Articles | Metrics
    Fast 3D-CNN Combined with Depth Separable Convolution for Hyperspectral Image Classification
    WANG Yan, LIANG Qi
    Journal of Frontiers of Computer Science and Technology    2022, 16 (12): 2860-2869.   DOI: 10.3778/j.issn.1673-9418.2103051

    In the process of feature extraction and classification of hyperspectral images using convolution neural networks, there are problems such as insufficient extraction of spatial spectrum features and too many layers of networks, which lead to large parameters and complex calculations. A lightweight convolution model based on fast three-dimensional convolution neural networks (3D-CNN) and depth separable convolutions (DSC) is proposed.Firstly, incremental principal component analysis (IPCA) is used to preprocess the dimension reduction of the input data. Secondly, the pixels of the input model are divided into small overlapped 3D small convolution blocks, and the ground label is formed on the segmented small blocks based on the center pixel. The 3D kernel function is used for convolution processing to form a continuous 3D feature map, retaining the spatial spectral features. 3D-CNN is used to extract spatial spectrum features at the same time, and then depth separable convolution is added to 3D convolution to extract spatial features again, which enriches spatial spectrum features while reducing the number of parameters, thus reducing the calculation time and improving the classification accuracy. The proposed model is verified on Indian Pines, Salinas Scene and University of Pavia public datasets, and compared with other classical classification methods. Experimental results show that this method can not only greatly save the learnable para-meters and reduce the complexity of the model, but also show good classification performance, in which the overall accuracy (OA), average accuracy (AA) and Kappa coefficient can all reach more than 99%.

    Table and Figures | Reference | Related Articles | Metrics
    Multi-head Self-attention Neural Network for Detecting EEG Epilepsy
    TONG Hang, YANG Yan, JIANG Yongquan
    Journal of Frontiers of Computer Science and Technology    2023, 17 (2): 442-452.   DOI: 10.3778/j.issn.1673-9418.2104089
    Epilepsy is a life-threatening and challenging nervous system disease. There are still many challenges in the detection of epilepsy based on electroencephalogram (EEG). Because the EEG signal is unstable, different patients show different seizure patterns. In addition, EEG detection is time-consuming and laborious, which will not only bring heavy burden to medical staff, but also easily lead to false detection. Therefore, it is necessary to study an efficient automatic epilepsy detection technology across multiple patients. In this paper, an epileptic EEG detection method (convolutional attention bidirectional long short-term memory network, CABLNet) based on the multi-head self-attention mechanism neural network is proposed. Firstly, the convolution layer is used to capture short-term temporal patterns of EEG time series and local dependence among channels. Secondly, this paper uses the multi-head self-attention mechanism to capture the long-distance dependence and time dynamic correlation of the short-term time pattern feature vectors with temporal relationship. Thirdly, the context representation is sent into a bidirectional long short-term memory (BiLSTM) to extract the information in the front and back directions. Finally, logsoftmax function is used for training and classification. Using CHB-MIT scalp EEG database data, the sensitivity, specificity, accuracy and F1-score are 96.18%, 97.04%, 96.61% and 96.59% respectively. The results show that the proposed method is superior to the existing methods and significantly improved in epilepsy detection performance, which is of great significance to the auxiliary diagnosis of epilepsy.
    Reference | Related Articles | Metrics
    Traffic Prediction Method Integrating Graph Wavelet and Attention Mechanism
    XUE Yanming, LI Guanghui, QI Tao
    Journal of Frontiers of Computer Science and Technology    2023, 17 (6): 1405-1416.   DOI: 10.3778/j.issn.1673-9418.2111012
    Traffic predicting is a critical component of modern intelligent transportation systems for traffic management and control. However, the traffic flow is complex. On one hand, the urban road structure is highly correlative, and there often exists a nonlinear structural dependence between different roads. On the other hand, traffic flow data often change dynamically over time. In recent years, many studies have tried to use deep learning methods to extract complex structural features in traffic flow. However, the process of local feature extraction still lacks flexibility, and ignores the dynamic variability as well as the correlation of spatio-temporal features. To this end, this paper proposes a new traffic prediction method integrating graph wavelet and attention mechanism. This method uses wavelet transform and an adaptive matrix to extract local and global spatial features of traffic flow respectively, and combines the improved recurrent neural network to extract local temporal characteristic information. Meanwhile, the attention mechanism is adopted in this method to capture the temporal and spatial dynamic variability. Then this method applies a spatio-temporal feature fusion mechanism to fusing local and global temporal and spatial features. Experimental results show that this method can extract spatial and temporal features of real traffic datasets well, and it outperforms the existing methods.
    Reference | Related Articles | Metrics
    Recommendation Algorithm Combining Social Relationship and Knowledge Graph
    GAO Yang, LIU Yuan
    Journal of Frontiers of Computer Science and Technology    2023, 17 (1): 238-250.   DOI: 10.3778/j.issn.1673-9418.2112088
    Recommendation system can help users quickly find useful information and improve the retrieval efficiency of users effectively. However, the recommendation system has problems such as data sparsity and cold start, most of the existing recommendation algorithms that integrate social relations ignore the sparsity of social relations data, and there are few recommendation algorithms that integrate social relations and item attribute data at the same time. This paper proposes a recommendation model that is multi-task feature learning approach for social relationship and knowledge graph enhanced recommendation (MSAKR) in response to solve the above problems. Firstly, the algorithm extracts the user’s social relations through the graph convolutional neural network to get the user’s feature vector, then selects the neighbor by the graph centrality, and generates the virtual neighbor by the word2vec model, so as to alleviate the sparsity of the social data. This paper uses the attention mechanism to gather the neighbors. Secondly, multi-task learning and semantic-based matching model are used to extract the information of attribute knowledge graph to obtain the feature vector of the item. Finally, comprehensive recommendation is made to the user based on the obtained user and item feature vectors. In order to assess the performance of the recommendation algorithm, experiments are carried out on real datasets Douban and Yelp. Click-through rate predi-ction and Top-K recommendation are used to evaluate the performance of the model respectively. Experimental results show that the proposed model is superior to other benchmark models.
    Reference | Related Articles | Metrics
    Survey on Personality Recognition Based on Social Media Data
    LIN Hao, WANG Chundong, SUN Yongjie
    Journal of Frontiers of Computer Science and Technology    2023, 17 (5): 1002-1016.   DOI: 10.3778/j.issn.1673-9418.2212012
    Personality is a stable construction, which is associated with thoughts, emotions and behaviors of human. Any technology involved in understanding, analyzing and predicting human behaviors may benefit from personality recognition. Accurately recognizing the personality will contribute to the research of human-computer interaction, recommendation system, cyberspace security, etc. Social media provides high-quality data for personality recog-nition, while classic personality measurement methods such as self-report scales and projective tests can no longer match the social media data in the age of big data. Moreover, the current mainstream personality recognition methods based on machine learning still have lots of room for performance improvement. Therefore, this paper investigates the literature on personality recognition based on social media data, introduces the background knowledge of personality recognition and summarizes the research status according to the data types of recognition model input used, specifically based on social text data, social image data, social application data and multimodal data. Finally, this paper proposes seven future research directions of personality recognition based on social media data.
    Reference | Related Articles | Metrics
    Research Review of Image Semantic Segmentation Method in High-Resolution Remote Sensing Image Interpretation
    MA Yan, Gulimila·Kezierbieke
    Journal of Frontiers of Computer Science and Technology    2023, 17 (7): 1526-1548.   DOI: 10.3778/j.issn.1673-9418.2211015
    Rapid acquisition of remote sensing information has important research significance for the development of image semantic segmentation methods in remote sensing image interpretation applications. With more and more types of data recorded by satellite remote sensing images and more and more complex feature information, accurate and effective extraction of information in remote sensing images has become the key to interpret remote sensing images by image semantic segmentation methods. In order to explore the image semantic segmentation method for fast and efficient interpretation of remote sensing images, a large number of image semantic segmentation methods for remote sensing images are summarized. Firstly, the traditional image semantic segmentation methods are reviewed and divided into edge detection-based segmentation methods, region-based segmentation methods, threshold-based segmentation methods and segmentation methods combined with specific theories. At the same time, the limitations of traditional image semantic segmentation methods are analyzed. Secondly, the semantic segmentation methods based on deep learning are elaborated in detail, and the basic ideas and technical characteristics of each method are used as the classification criteria. They are divided into four categories: FCN-based methods, codec-based methods, dilated convolution-based methods and attention-based methods. The sub-methods contained in each type of method are summarized, and the advantages and disadvantages of these methods are compared and analyzed. Then, the common datasets and performance evaluation indexes of remote sensing image semantic segmentation are briefly introduced. Experimental results of classical network models on different datasets are given, and the performance of different models is evaluated. Finally, the challenges of image semantic segmentation methods in high-resolution remote sensing image interpretation are analyzed, and the future development trend is prospected.
    Reference | Related Articles | Metrics
    DnRFD:Progressive Residual Fusion Dense Network for Image Denoising
    CAO Yiqin, RAO Zhechu, ZHU Zhiliang, ZHANG Hongbin
    Journal of Frontiers of Computer Science and Technology    2022, 16 (12): 2841-2850.   DOI: 10.3778/j.issn.1673-9418.2103030

    The denoising method based on deep learning can achieve better denoising effect than the traditional method, but the existing deep learning denoising methods often have the problem of excessive computational complexity caused by too deep network. To solve this problem, a progressive residual fusion dense network (DnRFD) is proposed to remove Gaussian noise. Firstly, dense blocks are used to learn the noise distribution in the image, and the network parameters are greatly reduced while the local features of the image are fully extracted. Then, a progressive strategy is used to connect the shallow convolution features with the deep features to form a residual fusion network to extract more global features for noise. Finally, the output characteristic images of each dense block are fused and input to the reconstructed output layer to get the final output result. Experimental results show that, when the Gaussian white noise level is 25 and 50, the network can achieve higher mean PSNR and mean structural similarity, and the average time of denoising is half of the DnCNN method and one third of the FFDNet method. In general, the overall denoising performance of the network is better than that of the correlative comparison algorithms, and it can effectively remove the white Gaussian noise and natural noise in the image, and can restore the edge and texture details of the image better.

    Table and Figures | Reference | Related Articles | Metrics
    Research on Corn Disease Detection Based on Improved YOLOv5 Algorithm
    SU Junkai, DUAN Xianhua, YE Zhaobing
    Journal of Frontiers of Computer Science and Technology    2023, 17 (4): 933-941.   DOI: 10.3778/j.issn.1673-9418.2210066
    In order to solve the problems of backward identification technology, low efficiency and insufficient accuracy of corn leaf disease, an improved YOLOv5 algorithm is proposed to identify corn disease. In order to maintain low computation of the model, and improve detection speed and algorithm performance, the feature extraction structure of traditional YOLOv5s network is improved, and CA (coordinate attention) attention mechanism is added to the backbone network, which improves the problem of target undetected, and helps the model locate and identify more accurately. In the neck, BiFPN (bidirectional feature pyramid network) is used to replace original PANet (path aggregation network), and the application of multi-scale semantic features is improved through two-way feature fusion to enhance the extraction for deep features of images. A small target monitoring layer is added to enhance the detection effect of small objects. Loss function is improved and Focal-EIOU Loss is introduced to improve the precision of BBox regression. Compared with traditional YOLOv5s, Recall is increased by 4.61 percentage points, AP is increased by 4.5 percentage points, mAP@0.5 is increased by 2.14 percentage points, and detection speed is increased by 4.5 FPS. Experimental results show that the improved YOLOv5 algorithm significantly improves the efficiency and performance of the algorithm with little complexity increase, and the effect is better than traditional YOLOv5s algorithm.
    Reference | Related Articles | Metrics
    Research Progress and Prospect of Ring Signatures
    XIE Jia, LIU Shizhao, WANG Lu, GAO Juntao, WANG Baocang
    Journal of Frontiers of Computer Science and Technology    2023, 17 (5): 985-1001.   DOI: 10.3778/j.issn.1673-9418.2210022
    As a special group signature, ring signature has been widely used in anonymous voting, anonymous deposit and anonymous transaction because it can not only complete the signature without the cooperation of ring members, but also ensure the anonymity of the signer. Firstly, this paper takes time as the main line, divides the development of ring signatures into different stages, and divides ring signatures into threshold ring signatures, linkable ring signatures, ring signatures with revocable anonymity, and repudiable ring signatures according to the attributes in each stage. Through the analysis of the development process of ring signature, it can be seen that the research progress of ring signature in the field of threshold ring signature and linkable ring signature is prominent, and their application fields are also the most extensive. In the post-quantum era, cryptographic schemes based on traditional number theory problems such as large integer factorization and discrete logarithms are no longer secure, and lattice-based public key cryptography has become the best candidate for cryptographic standards in the post-quantum era because of its advantages such as quantum-immune, the reduction of the worst-case to average-case, and so on. Therefore, this paper focuses on the detailed analysis and efficiency comparison of existing lattice-based threshold ring signatures and lattice-based linkable ring signatures. The inherent anonymity of ring signatures makes them have unique advantages in the era of industrial blockchain, so this paper elaborates on several applications of ring signatures in blockchain. For example, the application of ring signature in anonymous voting, medical data sharing, and Internet of vehicles is summarized and analyzed. The application significance of ring signature in the fields of virtual currency, SIP cloud call protocol, and Ad Hoc network is briefly sorted out. Finally,  the research of ring signature technology in recent years is analyzed, and the current problems are summarized.
    Reference | Related Articles | Metrics
    Many-Objective Evolutionary Algorithm Based on Distance Dominance Relation
    GU Qinghua, XU Qingsong, LI Xuexian
    Journal of Frontiers of Computer Science and Technology    2022, 16 (11): 2642-2652.   DOI: 10.3778/j.issn.1673-9418.2103053

    There are two main aspects of research in multi-objective optimization algorithm, namely, convergence and diversity. While, it is difficult for original algorithms to maintain the diversity of solutions in the high-dimensional objective space. In order to enhance the diversity of algorithms in many-objective optimization problems, a new distance dominance relation is proposed in this paper. Firstly, in order to ensure the convergence of the algorithm, in the same niche, the distance dominance relation calculates the distance from the candidate solution to the ideal point as the fitness value, and selects the candidate solution with good fitness value as the non-dominant solution.Then, in order to enhance the diversity of the algorithm, the distance dominance relation sets each candidate solution to have the same niche and ensures that only one optimal solution is retained in the same niche. Finally, the VaEA algorithm is improved based on the proposed distance dominance relation, and the algorithm is named VaEA-DDR. On the DTLZ and IDTLZ test of 5, 8, 10, 15 dimensional objectives, the improved algorithm is compared with six commonly used algorithms. Experimental results show that the improved algorithm is highly competitive and can significantly enhance the diversity of the algorithm.

    Table and Figures | Reference | Related Articles | Metrics