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 on Named Entity Recognition
    LI Dongmei, LUO Sisi, ZHANG Xiaoping, XU Fu
    Journal of Frontiers of Computer Science and Technology    2022, 16 (9): 1954-1968.   DOI: 10.3778/j.issn.1673-9418.2112109

    In the field of natural language processing, named entity recognition is the first key step of information extraction. Named entity recognition task aims to recognize named entities from a large number of unstructured texts and classify them into predefined types. Named entity recognition provides basic support for many natural language processing tasks such as relationship extraction, text summarization, machine translation, etc. This paper first introduces the definition of named entity recognition, research difficulties, particularity of Chinese named entity recognition, and summarizes the common Chinese and English public datasets and evaluation criteria in named entity recognition tasks. Then, according to the development history of named entity recognition, the existing named entity recognition methods are investigated, which are the early named entity recognition methods based on rules and dictionaries, the named entity recognition methods based on statistic and machine learning, and the named entity recognition methods based on deep learning. This paper summarizes the key ideas, advantages and disadvan-tages and representative models of each named entity recognition method, and summarizes the Chinese named entity recognition methods in each stage. In particular, the latest named entity recognition based on Transformer and based on prompt learning are reviewed, which are state-of-the-art in deep learning-based named entity recognition methods. Finally, the challenges and future research trends of named entity recognition are discussed.

    Table and Figures | Reference | Related Articles | Metrics
    Abstract1261
    PDF745
    HTML228
    Review of Deep Learning Applied to Occluded Object Detection
    SUN Fangwei, LI Chengyang, XIE Yongqiang, LI Zhongbo, YANG Caidong, QI Jin
    Journal of Frontiers of Computer Science and Technology    2022, 16 (6): 1243-1259.   DOI: 10.3778/j.issn.1673-9418.2112035

    Occluded object detection has long been a difficulty and hot topic in the field of computer vision. Based on convolutional neural network, the deep learning takes the object detection task as a classification and regression task to handle, and obtains remarkable achievements. The mask confuses the features of object when the object is occluded, making the deep convolutional neural network cannot handle it well and reducing the performance of detector in ideal scenes. Considering the universality of occlusion in reality, the effective detection of occluded object has important research value. In order to further promote the development of occluded object detection, this paper makes a comprehensive summary of occluded object detection algorithms, and makes a reasonable classification and analysis. First of all, based on a simple overview of object detection, this paper introduces the relevant theoretic background, research difficulties and datasets about occluded object detection. After, this paper focuses on the algo-rithms to improve the performance of occluded object detection from the aspects of object structure, loss function, non-maximum suppression and semantic partial. This paper compares the performance of different detection algo-rithms after summarizing the relationship and development of various algorithms. Finally, this paper points out the difficulties of occluded object detection and looks forward to its future development directions.

    Table and Figures | Reference | Related Articles | Metrics
    Abstract941
    PDF544
    HTML108
    Survey on Cross-Chain Protocols of Blockchain
    MENG Bo, WANG Yibing, ZHAO Can, WANG Dejun, MA Binhao
    Journal of Frontiers of Computer Science and Technology    2022, 16 (10): 2177-2192.   DOI: 10.3778/j.issn.1673-9418.2203032

    With the development of blockchain technology, due to the different system architecture and application scenarios of blockchain platforms, it is difficult to realize the interconnection and intercommunication of data and assets on different blockchains, which affects the promotion and application of blockchain. The cross-chain tech-nology of blockchain is an important technical solution to realize the interconnection of blockchain and improve the interoperability and extensibility of blockchain. The blockchain cross-chain protocol is the specific design specifi-cations to realize the cross-chain interoperability between different blockchains through cross-chain technology, so it is of great significance to the realization of blockchain interoperability and the construction of blockchain cross-chain application. This paper systematically arranges and analyzes the latest researches on the integration and implemen-tation of blockchain cross-chain protocols, and places them in four hierarchies: Firstly, the current research status of blockchain cross-chain interoperability is explained from three aspects, Internet of blockchains, cross-chain techno-logy and blockchain interoperability. Secondly, the cross-chain protocols are divided into cross-chain communi-cation agreements, cross-chain asset transaction agreements and cross-chain smart contract call agreements, and the latest research is analyzed. Thirdly, the key design principles of cross-chain protocols are summarized, and the solutions for the problems of security, privacy and scalability of cross-chain protocol are provided. Finally, com-bined with the actual needs of blockchain cross-chain applications, the future research direction of blockchain cross-chain protocol is given.

    Table and Figures | Reference | Related Articles | Metrics
    Abstract831
    PDF659
    HTML108
    Survey on Pseudo-Labeling Methods in Deep Semi-supervised Learning
    LIU Yafen, ZHENG Yifeng, JIANG Lingyi, LI Guohe, ZHANG Wenjie
    Journal of Frontiers of Computer Science and Technology    2022, 16 (6): 1279-1290.   DOI: 10.3778/j.issn.1673-9418.2111144

    With the development of intelligent technology, deep learning has become a hot topic in machine learning. It is playing a more and more important role in various fields. Deep learning requires a lot of labeled data to imp-rove model performance. Therefore, researchers effectively combine semi-supervised learning with deep learning to solve the labeled data problem. It utilizes a small amount of labeled data and a large amount of unlabeled data to build the model simultaneously. It can help to expand the sample space. In view of its theoretical significance and practical application value, this paper focuses on the pseudo-labeling methods as the starting point. Firstly, deep semi-supervised learning is introduced and the advantage of pseudo-labeling methods is pointed out. Secondly, the pseudo-labeling methods are described from self-training and multi-view training and the existing model is comprehensively analyzed. And then, the label propagation method based on graph and pseudo-labeling is introduced. Furthermore, the existing pseudo-labeling methods are analyzed and compared. Finally, the problems and future research direction of pseudo-labeling methods are summarized from the utility of unlabeled data, noise data, rationality, and the combi-nation of pseudo-labeling methods.

    Table and Figures | Reference | Related Articles | Metrics
    Abstract775
    PDF545
    HTML67
    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
    Abstract733
    PDF502
    HTML44
    XR-MSF-Unet: Automatic Segmentation Model for COVID-19 Lung CT Images
    XIE Juanying, ZHANG Kaiyun
    Journal of Frontiers of Computer Science and Technology    2022, 16 (8): 1850-1864.   DOI: 10.3778/j.issn.1673-9418.2203023

    The COVID-19 epidemic has threatened the human being. The automatic and accurate segmentation for the infected area of the COVID-19 CT images can help doctors to make correct diagnosis and treatment in time. However, it is very challenging to achieve perfect segmentation due to the diffuse infections of the COVID-19 to the patient lungs and irregular shapes of the infected areas and very similar infected areas to other lung tissues. To tackle these challenges, the XR-MSF-Unet model is proposed in this paper for segmenting the COVID-19 lung CT images of patients. The XR (X ResNet) convolution module is proposed in this model to replace the two-layer convolution operations of U-Net, so as to extract more informative features for achieving good segmentation results by multiple branches of XR. The plug and play attention mechanism module MSF (multi-scale features fusion module) is proposed in XR-MSF-Unet to fuse multi-scale features from different scales of reception fields, global, local and spatial features of CT images, so as to strengthen the detail segmentation effect of the model. Extensive experiments on the public COVID-19 CT images demonstrate that the proposed XR module can strengthen the capability of the XR-MSF-Unet model to extract effective features, and the MSF module plus XR module can effectively improve the segmentation capability of the XR-MSF-Unet model for the infected areas of the COVID-19 lung CT images. The proposed XR-MSF-Unet model obtains good segmentation results. Its segmentation perfor-mance is superior to that of the original U-Net model by 3.21, 5.96, 1.22 and 4.83 percentage points in terms of Dice, IOU, F1-Score and Sensitivity, and it defeats other same type of models, realizing automatic segmentation to the COVID-19 lung CT images.

    Table and Figures | Reference | Related Articles | Metrics
    Abstract697
    PDF240
    HTML20
    Review of Image Super-resolution Reconstruction Algorithms Based on Deep Learning
    YANG Caidong, LI Chengyang, LI Zhongbo, XIE Yongqiang, SUN Fangwei, QI Jin
    Journal of Frontiers of Computer Science and Technology    2022, 16 (9): 1990-2010.   DOI: 10.3778/j.issn.1673-9418.2202063

    The essence of image super-resolution reconstruction technology is to break through the limitation of hardware conditions, and reconstruct a high-resolution image from a low-resolution image which contains less infor-mation through the image super-resolution reconstruction algorithms. With the development of the technology on deep learning, deep learning has been introduced into the image super-resolution reconstruction field. This paper summarizes the image super-resolution reconstruction algorithms based on deep learning, classifies, analyzes and compares the typical algorithms. Firstly, the model framework, upsampling method, nonlinear mapping learning module and loss function of single image super-resolution reconstruction method are introduced in detail. Secondly, the reference-based super-resolution reconstruction method is analyzed from two aspects: pixel alignment and Patch matching. Then, the benchmark datasets and image quality evaluation indices used for image super-resolution recon-struction algorithms are summarized, the characteristics and performance of the typical super-resolution recons-truction algorithms are compared and analyzed. Finally, the future research trend on the image super-resolution reconstruction algorithms based on deep learning is prospected.

    Table and Figures | Reference | Related Articles | Metrics
    Abstract620
    PDF384
    HTML68
    Review of Knowledge-Enhanced Pre-trained Language Models
    HAN Yi, QIAO Linbo, LI Dongsheng, LIAO Xiangke
    Journal of Frontiers of Computer Science and Technology    2022, 16 (7): 1439-1461.   DOI: 10.3778/j.issn.1673-9418.2108105

    The knowledge-enhanced pre-trained language models attempt to use the structured knowledge stored in the knowledge graph to strengthen the pre-trained language models, so that they can learn not only the general semantic knowledge from the free text, but also the factual entity knowledge behind the text. In this way, the enhanced models can effectively solve downstream knowledge-driven tasks. Although this is a promising research direction, the current works are still in the exploratory stage, and there is no comprehensive summary and systematic arrangement. This paper aims to address the lack of comprehensive reviews of this direction. To this end, on the basis of summarizing and sorting out a large number of relevant works, this paper firstly explains the background information from three aspects: the reasons, the advantages, and the difficulties of introducing knowledge, summarizes the basic concepts involved in the knowledge-enhanced pre-trained language models. Then, it discusses three types of knowledge enhancement methods: using knowledge to expand input features, using knowledge to modify model architecture, and using knowledge to constrain training tasks. Finally, it counts the scores of various knowledge enhanced pre-trained language models on several evaluation tasks, analyzes the performance, the current challenges, and possible future directions of knowledge-enhanced pre-trained language models.

    Table and Figures | Reference | Related Articles | Metrics
    Abstract611
    PDF601
    HTML1618
    Survey of Question Answering Based on Knowledge Graph Reasoning
    SA Rina, LI Yanling, LIN Min
    Journal of Frontiers of Computer Science and Technology    2022, 16 (8): 1727-1741.   DOI: 10.3778/j.issn.1673-9418.2111033

    Knowledge graph question answering (KGQA) is based on analysis and understanding of questions and knowledge graph (KG) to obtain the answers. However, due to the complexity of natural language questions and the incompleteness of KG, the accuracy of answers can not be improved effectively. The knowledge graph reasoning technology can infer the missing entities in the KG and the implied relations between entities. Therefore, its application in KGQA can further improve the accuracy of answer prediction. In recent years, with the development of KGQA datasets and flexible application of knowledge graph reasoning technology, the development of the KGQA is greatly promoted. In this paper, question answering based on knowledge graph reasoning is summarized from three aspects. Firstly, this paper gives a brief overview of question answering based on knowledge graph reasoning, and introduces its challenges and related datasets. Secondly, this paper introduces the application of knowledge graph reasoning in open domain question answering, commonsense question answering and temporary knowledge question answering, and analyzes the advantages and disadvantages of each method. The open domain question answering methods are further summarized as graph embedding methods, deep learning methods and logic methods. Finally, this paper summarizes the work and prospects the future research in view of the current problems of question answering based on knowledge graph reasoning.

    Table and Figures | Reference | Related Articles | Metrics
    Abstract604
    PDF378
    HTML69
    Survey of Graph Neural Network in Recommendation System
    WU Jing, XIE Hui, JIANG Huowen
    Journal of Frontiers of Computer Science and Technology    2022, 16 (10): 2249-2263.   DOI: 10.3778/j.issn.1673-9418.2203004

    Recommendation system (RS) was introduced because of a lot of information. Due to the diversity, complexity, and sparseness of data, traditional recommendation system can not solve the current problem well. Graph neural network (GNN) can extract and represent the features from edges and nodes data in the graphs and has inherent advantages in processing the graphs structure data, so it flourishes in recommendation system. This paper sorts out the main references of graph neural network in recommendation system in recent years, focuses on the two perspectives of method and problem, and systematically reviews graph neural network in recommendation system. Firstly, from the method level, five graph neural networks of the recommendation system are elaborated, including the graph convolutional network in the recommendation system, graph attention network in the recommendation system, graph autoencoder in the recommendation system, graph generation network in the recommendation system and graph spatial-temporal network in the recommendation system. Secondly, from the perspective of problem similarity, six major problem types are summarized: sequence recommendation, social recommendation, cross-domain recommendation, multi-behavior recommendation, bundle recommendation, and session-based recommen-dation. Finally, based on the analysis and summary of the existing methods, this paper points out the main difficu-lties in the current research on graph neural network in recommendation system, proposes the corresponding issues that can be investigated, and looks forward to the future research directions on this topic.

    Table and Figures | Reference | Related Articles | Metrics
    Abstract574
    PDF393
    HTML33
    High Frame Rate Light-Weight Siamese Network Target Tracking
    LI Yunhuan, WEN Jiwei, PENG Li
    Journal of Frontiers of Computer Science and Technology    2022, 16 (6): 1405-1416.   DOI: 10.3778/j.issn.1673-9418.2012016

    With the widespread use of target tracking in many life scenarios, the demand for high-precision and high-speed tracking algorithms is also increasing. For some specific scenarios such as mobile terminals, embedded devices, etc., under the premise of relatively insufficient computing power of the device, it is still necessary to ensure that the tracker achieves good tracking accuracy and high-speed real-time tracking. A high frame rate tracking algorithm based on light-weight siamese network is proposed to solve this problem. Firstly, the light-weight convolutional neural network MobileNetV1 is selected, which is easy to be deployed in embedded devices, as the feature extraction backbone network, and deep network is more capable of extracting target features. Then, two optimization strategies are proposed to address the shortcomings of the backbone network, feature map is cropped and the total network step length is adjusted to make the backbone network suitable for tracking tasks. Finally, after the template branch of the siamese network, an ultra-lightweight channel attention module is added to weight important information that highlights the target characteristics. The proposed algorithm parameters are reduced by 59.8% in comparison with current mainstream algorithm SiamFC. Simulation and experimental results on the OTB2015 dataset show that the tracking accuracy is increased by 5.4%, and the algorithm can better cope with complex and changeable challenges in tracking tasks. Simulation and experimental results on the VOT2018 dataset show that the comprehensive index expected average overlap (EAO) is increased by 26.6%, and the average speed of the algorithm under NVIDIA GTX1080Ti is 120 frame/s, which achieves high frame rate real-time tracking.

    Table and Figures | Reference | Related Articles | Metrics
    Abstract562
    PDF210
    HTML19
    High-Performance Implementation and Optimization of Cooley-Tukey FFT Algorithm
    GUO Jinxin, ZHANG Guangting, ZHANG Yunquan, CHEN Zehua, JIA Haipeng
    Journal of Frontiers of Computer Science and Technology    2022, 16 (6): 1304-1315.   DOI: 10.3778/j.issn.1673-9418.2011092

    The fast Fourier transform (FFT) algorithm is considered as an important element of the processor’s basic software ecology, and it is widely applied in the field of engineering, science, physics and mathematics. Meanwhile, the requirements for the performance of FFT in these applications are also continuously rising. Therefore, it is of definite significance to study the high-performance implementation of FFT algorithm, especially the high-performance implementation of large radices of FFT in ARMv8 and X86-64, and to improve the calculation performance of FFT algorithm. In view of the architectural features of the ARMv8 and X86-64 computing platforms, this paper studies the high-performance implementation and optimization methods of the FFT algorithm. Through the application of butterfly network optimization, large radices network stages decrease, large radices butterfly computation optimization, SIMD (single instruction multiple data) assembly optimization, and register usage optimization methods, this paper effectively improves the performance of the FFT algorithm, considerably improves the calculation performance of the large radices of FFT, and solves the performance bottlenecks of insufficiency of register resources. Lastly, the summary of a set of Cooley-Tukey FFT algorithm high-performance implementation strategies and optimization solutions is made. The experimental results indicate that for the ARM and X86-64 processors, the FFT algorithm implemented can achieve a significant improvement in performance compared with ARMPL (ARM performance library), Intel MKL (math kernel library) and FFTW (fastest Fourier transform in the West) and can achieve a significant improvement in performance compared with small and medium radices.

    Table and Figures | Reference | Related Articles | Metrics
    Abstract548
    PDF312
    HTML37
    Survey on Video Object Tracking Algorithms
    LIU Yi, LI Mengmeng, ZHENG Qibin, QIN Wei, REN Xiaoguang
    Journal of Frontiers of Computer Science and Technology    2022, 16 (7): 1504-1515.   DOI: 10.3778/j.issn.1673-9418.2111105

    Video object tracking is an important research content in the field of computer vision, mainly studying the tracking of objects with interest in video streams or image sequences. Video object tracking has been widely used in cameras and surveillance, driverless, precision guidance and other fields. Therefore, a comprehensive review on video object tracking algorithms is of great significance. Firstly, according to different sources of challenges, the challenges faced by video object tracking are classified into two aspects, the objects’ factors and the backgrounds’ factors, and summed up respectively. Secondly, the typical video object tracking algorithms in recent years are classified into correlation filtering video object tracking algorithms and deep learning video object tracking algorithms. And further the correlation filtering video object tracking algorithms are classified into three categories: kernel correlation filtering algorithms, scale adaptive correlation filtering algorithms and multi-feature fusion corre-lation filtering algorithms. The deep learning video object tracking algorithms are classified into two categories: video object tracking algorithms based on siamese network and based on convolutional neural network. This paper analyzes various algorithms from the aspects of research motivation, algorithm ideas, advantages and disadvantages. Then, the widely used datasets and evaluation indicators are introduced. Finally, this paper sums up the research and looks forward to the development trends of video object tracking in the future.

    Table and Figures | Reference | Related Articles | Metrics
    Abstract533
    PDF379
    HTML176
    Survey on Applications of Knowledge Graph Embedding in Recommendation Tasks
    TIAN Xuan, CHEN Hangxue
    Journal of Frontiers of Computer Science and Technology    2022, 16 (8): 1681-1705.   DOI: 10.3778/j.issn.1673-9418.2112070

    Recommendation systems are designed to recommend personalized content to improve user experience. At present, the recommendation systems still face some challenges such as poor interpretability, cold start problem and serialized recommendation modeling. Recently, the knowledge graph (KG) containing a large amount of semantic and structural information has been widely used in a variety of different recommendation tasks to alleviate the above problems. This paper systematically reviews the innovative applications of knowledge graph embedding (KGE) in different recommendation tasks. It first summarizes three common recommendation tasks and four applying goals of knowledge graph embedding. Then, it generalizes four types of knowledge graph embedding methods according to specific technologies, including traditional embedding method, embedding propagation method, heterogeneous graph embedding method and graph neural network based method. It further elaborates on the applying characteristics and strategies of the above four methods in different recommendation tasks, and evaluates advantages and limitations of each method. Also, it conducts qualitative and quantitative analysis of the associations and differences of four methods from multiple aspects. Finally, it puts forward some views on the development trend of applying knowledge graph embedding for recommendation systems, and proposes several noteworthy development directions in the future from multiple perspectives.

    Table and Figures | Reference | Related Articles | Metrics
    Abstract531
    PDF584
    HTML65
    Survey of Deep Learning Based Multimodal Emotion Recognition
    ZHAO Xiaoming, YANG Yijiao, ZHANG Shiqing
    Journal of Frontiers of Computer Science and Technology    2022, 16 (7): 1479-1503.   DOI: 10.3778/j.issn.1673-9418.2112081

    Multimodal emotion recognition aims to recognize human emotional states through different modalities related to human emotion expression such as audio, vision, text, etc. This topic is of great importance in the fields of human-computer interaction, a.pngicial intelligence, affective computing, etc., and has attracted much attention. In view of the great success of deep learning methods developed in recent years in various tasks, a variety of deep neural networks have been used to learn high-level emotional feature representations for multimodal emotion recog-nition. In order to systematically summarize the research advance of deep learning methods in the field of multi-modal emotion recognition, this paper aims to present comprehensive analysis and summarization on recent multi-modal emotion recognition literatures based on deep learning. First, the general framework of multimodal emotion recognition is given, and the commonly used multimodal emotional dataset is introduced. Then, the principle of representative deep learning techniques and its advance in recent years are briefly reviewed. Subsequently, this paper focuses on the advance of two key steps in multimodal emotion recognition: emotional feature extraction methods related to audio, vision, text, etc., including hand-crafted feature extraction and deep feature extraction; multi-modal information fusion strategies integrating different modalities. Finally, the challenges and opportunities in this field are analyzed, and the future development direction is pointed out.

    Table and Figures | Reference | Related Articles | Metrics
    Abstract526
    PDF481
    HTML94
    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
    Abstract523
    PDF524
    Survey of Research on Image Inpainting Methods
    LUO Haiyin, ZHENG Yuhui
    Journal of Frontiers of Computer Science and Technology    2022, 16 (10): 2193-2218.   DOI: 10.3778/j.issn.1673-9418.2204101

    Image inpainting refers to restoring the pixels in damaged areas of an image to make them as consistent as possible with the original image. Image inpainting is not only crucial in the computer vision tasks, but also serves as an important cornerstone of other image processing tasks. However, there are few researches related to image inpainting. In order to better learn and promote the research of image inpainting tasks, the classic image inpainting algorithms and representative deep learning image inpainting methods in the past ten years are reviewed and analyzed. Firstly, the classical traditional image inpainting methods are briefly summarized, and divided into partial differential equation-based and sample-based image inpainting methods, and the limitations of traditional image methods are further analyzed. Deep learning image inpainting methods are divided into single image inpainting and pluralistic image inpainting according to the number of output images of the model, and different methods are analyzed and summarized in combination with application images, loss functions, types, advantages, and limitations. After that, the commonly used datasets and quantitative evaluation indicators of image inpainting methods are described in detail, and the quantitative data of image inpainting methods to inpaint damaged areas of different areas on different image datasets are given. According to the quantitative data, the performance of image inpainting methods based on deep learning is compared and analyzed. Finally, the limitations of existing image inpainting methods are summarized and analyzed, and new ideas and prospects for future key research directions are proposed.

    Table and Figures | Reference | Related Articles | Metrics
    Abstract522
    PDF535
    HTML23
    Research and Development of Medical Knowledge Graph Reasoning
    DONG Wenbo, SUN Shiliang, YIN Minzhi
    Journal of Frontiers of Computer Science and Technology    2022, 16 (6): 1193-1213.   DOI: 10.3778/j.issn.1673-9418.2111031

    Knowledge graphs can effectively organize and represent knowledge, which have been applied to many advanced applications, for example, intelligent medicine. However, the medical knowledge graphs constructed manually or automatically are usually incomplete, which seriously limits their performance. Medical knowledge reasoning can complete medical knowledge graph and assist doctors in medical diagnosis. This paper first gives the basic concept and definition of medical knowledge reasoning, and then summarizes the key technologies of constructing medical knowledge graphs and the auxiliary diagnosis methods based on medical knowledge reasoning. Subsequently, this paper reviews the research development of medical knowledge reasoning, and classifies its reasoning methods into rule-based medical reasoning, representation learning-based medical reasoning and deep learning-based medical reasoning. For each category, representative algorithms and newly proposed algorithms are presented. The main feature of this survey is that it provides a comprehensive introduction for the recent development of knowledge graph reasoning on the basis of coherence with early methods. Finally, this paper prospects the development of medical knowledge reasoning based on the major challenges and key problems faced by medical knowledge reasoning, hoping to promote further research in this rapidly developing field.

    Table and Figures | Reference | Related Articles | Metrics
    Abstract521
    PDF240
    HTML172
    Review of Super-Resolution Image Reconstruction Algorithms
    ZHONG Mengyuan, JIANG Lin
    Journal of Frontiers of Computer Science and Technology    2022, 16 (5): 972-990.   DOI: 10.3778/j.issn.1673-9418.2111126

    In human visual perception system, high-resolution (HR) image is an important medium to clearly express its spatial structure, detailed features, edge texture and other information, and it has a very wide range of practical value in medicine, criminal investigation, satellite and other fields. Super-resolution image reconstruction (SRIR) is a key research task in the field of computer vision and image processing, which aims to reconstruct a high-resolution image with clear details from a given low-resolution (LR) image. In this paper, the concept and mathematical model of super-resolution image reconstruction are firstly described, and the image reconstruction methods are systematically classified into three kinds of super-resolution image reconstruction methods:based on interpolation, based on reconstruction, based on learning (before and after deep learning). Secondly, the typical, commonly used and latest algorithms among the three methods and their research are comprehensively reviewed and summarized, and the listed image reconstruction algorithms are combed from the aspects of network structure, learning mechanism, application scenarios, advantages and limitations. Then, the datasets and image quality evaluation indices used for super-resolution image reconstruction algorithms are summarized, and the characteristics and performance of various super-resolution image reconstruction algorithms based on deep learning are compared. Finally, the future research direction or angle of super-resolution image reconstruction is prospected from four aspects.

    Table and Figures | Reference | Related Articles | Metrics
    Abstract489
    PDF453
    HTML248
    Survey on Blockchain Consensus Algorithms and Application
    WANG Qun, LI Fujuan, NI Xueli, XIA Lingling, WANG Zhenli, LIANG Guangjun
    Journal of Frontiers of Computer Science and Technology    2022, 16 (6): 1214-1242.   DOI: 10.3778/j.issn.1673-9418.2112077

    The consensus algorithm, as the core technology of blockchain, provides mechanism support and guarantee for the realization of functions such as decentralization, openness, autonomy, information tamperability and anonymous traceability, and realizes efficient achievement of strong and final consistency in distributed system. The consensus algorithms are divided into the previous classical distributed consensus algorithms and the subsequent blockchain consensus algorithms by taking the emergence of bitcoin as the time node. On this basis, the consensus algorithms are further classified according to the implementation principle, the typical algorithms are selected, and then the discussion is focused on decentralization, scalability, security, consistency and so on. Firstly, a general model of blockchain consensus algorithm is proposed, and the basic definition of consensus algorithm is given. Secondly, while introducing the characteristics of the classical distributed consensus algorithms, the distributed consistency algorithms and their improvements such as the two armed forces problem, the Byzantine generals problem, the FLP impossibility theorem, the CAP theorem and Paxos algorithm are studied, and then the execution process and functional characteristics of the algorithm are analyzed. Thirdly, the blockchain consensus algorithms are divided into POW consensus algorithm, POS consensus algorithm, POW+POS hybrid consensus algorithm and POW/POS+BFT/PBFT hybrid consensus algorithm according to different implementation principles and application scenarios. The algorithm flow is given respectively after selecting representative algorithms in each category, and then the specific application scenarios are deeply analyzed. Finally, the research hotspots and development directions of blockchain consensus algorithms in performance and scalability, incentive mechanism, security and privacy, parallel processing and so on are pointed out.

    Table and Figures | Reference | Related Articles | Metrics
    Abstract452
    PDF362
    HTML63
    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
    Abstract435
    PDF480
    Multi-modal Public Opinion Analysis Based on Image and Text Fusion
    LIU Ying, WANG Zhe, FANG Jie, ZHU Tingge, LI Linna, LIU Jiming
    Journal of Frontiers of Computer Science and Technology    2022, 16 (6): 1260-1278.   DOI: 10.3778/j.issn.1673-9418.2110056

    Due to the continuous popularization of the Internet and mobile phones, people have gradually entered a participatory network era. More and more people like to publish their opinions, comments and emotions through text and image on the Internet. Effective analysis of these text and image information can not only help companies better improve the quality of their products, but also provide guidance for government decision-making and social production and life. This paper summarizes the sentiment analysis of online public opinion based on multi-modal image and text fusion. Firstly, it summarizes the basic concepts of public opinion analysis. Secondly, it explains the process of single-modal text and visual sentiment analysis on social media. Thirdly, it summarizes the public opinion analysis algorithms based on image and text fusion, and divides the algorithms into feature layer fusion, decision layer fusion and linear regression model according to different fusion strategies. In addition, it summarizes the commonly used multi-modal sentiment analysis for social media dataset. Finally, the difficulties of online opinion analysis and future research directions are discussed.

    Table and Figures | Reference | Related Articles | Metrics
    Abstract419
    PDF313
    HTML18
    Medical Image Classification Algorithm Based on Weight Initialization-Sliding Window CNN
    AN Fengping, LI Xiaowei, CAO Xiang
    Journal of Frontiers of Computer Science and Technology    2022, 16 (8): 1885-1897.   DOI: 10.3778/j.issn.1673-9418.2011091

    Deep learning has the following problems in medical image classification application: first, it is impossible to construct a deep learning model hierarchy for medical image properties; second, the network initialization weight of the deep learning model has not been optimized. To this end, this paper starts from the perspective of network optimization, and then improves the nonlinear modeling ability of the network through optimization methods. Then, this paper proposes a new network weight initialization method, which alleviates the problem that the initialization theory of existing deep learning is limited by the nonlinear unit type, and increases the potential of neural network to deal with different visual tasks. At the same time, in order to make full use of the characteristics of medical images, this paper deeply studies the multi-column convolutional neural network framework and finds that through changing the number of features and the convolution kernel size of different levels of convolutional neural networks, it can construct different convolutional neural network models to better adapt to the medical characteristics of the medical images to be processed and train the obtained heterogeneous multi-column convolutional neural networks. Finally, the classification task of medical images is completed by the method proposed in this paper. Based on the above ideas, this paper proposes a medical classification algorithm based on weight initialization-sliding window fusion of multi-layer convolutional neural networks. The methods of this paper are used to classify breast mass classification, brain tumor tissue classification experiment and medical image database classification. The experimental results show that the proposed method not only has higher average accuracy than traditional machine learning and other deep learning methods, but also has better stability and robustness.

    Table and Figures | Reference | Related Articles | Metrics
    Abstract419
    PDF157
    HTML2
    Knowledge Graph Link Prediction Based on Subgraph Reasoning
    YU Huilin, CHEN Wei, WANG Qi, GAO Jianwei, WAN Huaiyu
    Journal of Frontiers of Computer Science and Technology    2022, 16 (8): 1800-1808.   DOI: 10.3778/j.issn.1673-9418.2104084

    Relationship prediction in knowledge graph aims to identify and infer new relationships from existing data, and provides knowledge services for many downstream tasks. At present, many researches solve the link prediction problem between entities by mapping entities and relations into a vector space or searching the paths between entities. These methods only consider the influence of single path or first-order information but ignore more complex relation information between entities. Therefore, this paper proposes a novel link prediction method based on subgraph reasoning in knowledge graph, uses the subgraph structure to obtain the entity pair neighborhood structure information, combines the advantages of representation learning and path reasoning, and realizes the relationship prediction between entities. This paper first extends the paths between entities to subgraphs, constructs node subgraph and relationship subgraph from entity level and relationship level respectively, then combines the graph embedding representation with the graph neural network to calculate the subgraph features, to get richer entity characteristics and relationship characteristics. Finally, this paper calculates the neighborhood structure information of entity pairs from the subgraph structure to conduct link prediction between entities. Experimental results demons-trate that the proposed approach outperforms other reasoning-based link prediction methods on two benchmark datasets.

    Table and Figures | Reference | Related Articles | Metrics
    Abstract402
    PDF520
    HTML53
    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
    Abstract402
    PDF487
    HTML60
    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
    Abstract398
    PDF389
    Target Tracking System Constructed by ELM-AE and Transfer Representation Learning
    YANG Zheng, DENG Zhaohong, LUO Xiaoqing, GU Xin, WANG Shitong
    Journal of Frontiers of Computer Science and Technology    2022, 16 (7): 1633-1648.   DOI: 10.3778/j.issn.1673-9418.2012028

    In the target tracking algorithm, the feature model’s ability to quickly learn image features and the ability to adapt to changes in target features during tracking has always been one of the main research directions of target tracking algorithms. Especially for discriminative target trackers based on image block learning, these two points have become decisive factors affecting the efficiency and robustness of the tracker. However, the performance of most existing similar algorithms on these two abilities cannot achieve satisfactory results. To solve this problem, an efficient and robust feature model is proposed. The feature model first uses extreme learning machine autoencoder (ELM-AE) to quickly perform random feature mapping on complex image features of the target and background image blocks, and then uses the transfer learning ability of transfer representation learning (TRL) to improve the adaptability of random feature space. The feature model is named transfer representation learning with ELM-AE (TRL-ELM-AE). Compared with original complex image features, this model can provide the classifier with more compact and expressive shared features, so that the classifier can learn and classify more quickly and efficiently. In addition, in the target tracking process, the target and background usually change continuously over time. Although the feature migration capability of TRL can already adapt to this, in order to further improve the robustness of the tracker, a strategy of dynamically updating training samples is adopted. Through a large number of experimental and analysis results on the 11 target tracking challenge scenarios proposed by OTB, it is proven that the proposed target tracker has significant advantages over the existing target tracker.

    Table and Figures | Reference | Related Articles | Metrics
    Abstract387
    PDF550
    HTML25
    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
    Abstract386
    PDF154
    HTML29
    Hybrid Recommendation Model of Knowledge Graph and Graph Convolutional Network
    GUO Xiaowang, XIA Hongbin, LIU Yuan
    Journal of Frontiers of Computer Science and Technology    2022, 16 (6): 1343-1353.   DOI: 10.3778/j.issn.1673-9418.2110057

    Concerning the failure of most current recommendation models based on knowledge graph to adequately model users’ characteristics, the neighborhood relationship between entities in the knowledge graph is not considered. This paper proposes a hybrid recommendation model that combines knowledge graph and graph convolutional network (HKC). Firstly, the KGCN (knowledge graph convolutional networks for recommender systems) algorithm is used to capture the correlation between items, and obtain the feature vector of the item through neighborhood aggregation unit. The entities associated with the user in the knowledge graph are extracted through collaborative propagation. Then the model uses the alternate learning method to optimize the model prediction unit and the knowledge graph embedding unit at the same time, and calculate the user’s feature vector through the interaction unit. Finally, the user feature vector and the item feature vector are sent to the prediction link and the interaction probability between the user and the item is calculated through the inner product operation and normalization of the vector. Comparative experiments are conducted on three public datasets with seven baseline models. On the MovieLens-1M dataset, AUC is increased by 0.25% to 37.41%, and ACC is increased by 0.78% to 49.44%; on the Book-Crossing dataset, AUC is increased by 0.04% to 19.38%, and ACC is increased by 6.49% to 18.60%; on the Last.FM dataset, AUC is increased by 1.33% to 33.50%, and ACC is increased by 0.36% to 30.66%. Experimental results show that the model proposed has improved performance compared with other benchmark models.

    Table and Figures | Reference | Related Articles | Metrics
    Abstract384
    PDF223
    HTML19
    Research Progress of Blockchain in Internet of Vehicles Data Sharing
    XIONG Xiao, LI Leixiao, GAO Jing, GAO Haoyu, DU Jinze, ZHENG Yue, NIU Tieming
    Journal of Frontiers of Computer Science and Technology    2022, 16 (5): 1008-1024.   DOI: 10.3778/j.issn.1673-9418.2110024

    Efficiently and safely sharing data in the Internet of vehicles (IOV) is of great significance to the development of intelligent transportation. To combine with blockchain has great potential in promoting the extent of sharing and privacy for IOV, however, there still exists a problem how to ensure its safety. From the perspective of solving the problem, this paper systematically arranges and analyzes the latest researches on the integration and implementation of blockchain of data sharing with IOV. Firstly, it summarizes the traditional vehicle networking data sharing model and analyzes its characteristics. Secondly, it introduces the current situation of data secure sharing of IOV based on blockchain from six aspects, including the reliability of sharing data, the security of sharing data, incentive mechanism, access control, scalability and storage mode. Thirdly, it lists and analyzes the characteristics of three general models for secure data sharing of IOV based on blockchain. Finally, it discusses the directions of future research and the development of this field, and presents feasible solutions to solve the security problem of data sharing in IOV, so as to provide theoretical support for the construction of data sharing in the future Internet of vehicles.

    Table and Figures | Reference | Related Articles | Metrics
    Abstract381
    PDF514
    HTML152
    Research and Application Progress of Chinese Medical Knowledge Graph
    FAN Yuanyuan, LI Zhongmin
    Journal of Frontiers of Computer Science and Technology    2022, 16 (10): 2219-2233.   DOI: 10.3778/j.issn.1673-9418.2112118

    Knowledge graph is a large-scale semantic network that gives machine background knowledge. Using knowledge graph to organize heterogeneous medical information can effectively improve the utilization value of massive medical resources and promote the development of medical intelligence. This paper describes the research, construction and application status of knowledge graph in medical field from three dimensions: the key technology of knowledge graph, the construction of medical knowledge graph and the application of medical knowledge graph, and explores the topics worthy of research in the future. Firstly, the development of knowledge representation, knowledge extraction, knowledge fusion and knowledge inference are systematically summarized, their latest progress is discussed, and the technical difficulties in the construction of Chinese medical knowledge graph are analyzed. Secondly, the existing research on Chinese medical knowledge graph is illustrated from three perspectives of medical ontology, general practice knowledge graph and single disease medical knowledge graph. The research characteristics of Chinese medical knowledge graph are also analyzed. Finally, the application of medical know-ledge graph in semantic search, decision support and intelligent question answering are analyzed, and the new app-lication scenarios are discussed. In view of the challenges faced by Chinese medical knowledge graph, such as low standardization of terminology, lack of annotated corpus, insufficient technical research and limitations of applica-tion scenarios, the future research directions of Chinese medical knowledge graph are prospected.

    Table and Figures | Reference | Related Articles | Metrics
    Abstract380
    PDF252
    HTML19
    Review of Point of Interest Recommendation Systems in Location-Based Social Networks
    CHEN Jiangmei, ZHANG Wende
    Journal of Frontiers of Computer Science and Technology    2022, 16 (7): 1462-1478.   DOI: 10.3778/j.issn.1673-9418.2112037

    Point of interest recommendation is recently one of the hotspots in the field of location-based social networks and recommendation systems. Understanding the research status of the point of interest recommendation in location-based social networks can provide a direction for the next step of work. The recent literatures of the point of interest recommendation systems are analyzed. Firstly, the definition is introduced, and the difference from traditional recommendation is discussed from three aspects: influencing factors, recommendation approaches and existing problems. Secondly, the general framework of the point of interest recommendation is proposed, which includes data sources, recommendation approaches and evaluation. Based on this framework, the various influencing factors are introduced, the current recommendation algorithms are generalized, and the evaluation metrics are summarized. Meanwhile, the representative works are analyzed, the research contents and characteristics of each type of methods are summarized in detail, and their advantages and limitations are evaluated. Finally, the challenges and potential directions for possible extensions in this filed are summarized and prospected, and the future research trends and development directions are concluded.

    Table and Figures | Reference | Related Articles | Metrics
    Abstract374
    PDF214
    HTML36
    Review of Research on Imbalance Problem in Deep Learning Applied to Object Detection
    REN Ning, FU Yan, WU Yanxia, LIANG Pengju, HAN Xi
    Journal of Frontiers of Computer Science and Technology    2022, 16 (9): 1933-1953.   DOI: 10.3778/j.issn.1673-9418.2203070

    The current scheme of manually extracting features for object detection has been replaced by deep learning. Deep learning technology has greatly promoted the development of object detection technology. Object detection has also become one of the most important application fields of deep learning. Object detection is to simultaneously predict the category and position of object instances in a given image. This technology has been widely used in medical imaging, remote sensing technology, monitoring and security, automatic driving and other fields. However, with the diversification of object detection application fields, the imbalance problem in the application of deep learning to object detection has become a new entry point to optimize the object detection training model. This paper mainly analyzes the use of machine learning technology to solve the object detection problem. There are four kinds of imbalance problems in each training stage of the model: data imbalance, scale imbalance, relative space imbalance and classification and regression imbalance. This paper analyzes the main reasons for the problem, studies representative classical solutions, and expounds the problems existing in object detection in various fields. By analyzing and summarizing the object detection imbalance problems, this paper discusses the directions of the imbalance of object detection in the future.

    Table and Figures | Reference | Related Articles | Metrics
    Abstract371
    PDF263
    HTML26
    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
    Abstract370
    PDF530
    HTML20
    Particle Swarm Optimization Combined with Q-learning of Experience Sharing Strategy
    LUO Yixuan, LIU Jianhua, HU Renyuan, ZHANG Dongyang, BU Guannan
    Journal of Frontiers of Computer Science and Technology    2022, 16 (9): 2151-2162.   DOI: 10.3778/j.issn.1673-9418.2102070

    Particle swarm optimization (PSO) has shortcomings such as easy to fall into local optimum, insufficient diversity and low precision. Recently, adopting the strategy of combining the reinforcement learning method like Q-learning to improve the PSO algorithm has become a new idea. However, this method has been proven to suffer the insufficient objectiveness of parameter selection and the limited strategy is not capable of coping with various situations. This paper proposes a Q-learning PSO with experience sharing (QLPSOES). The algorithm combines the PSO algorithm with the reinforcement learning method to construct a Q-table for each particle for dynamic selection of particle parameter settings. At the same time, an experience sharing strategy is designed, in which the particles share the “behavior experience” of the optimal particle through the Q-table. This method can accelerate the convergence of Q-table, enhance the learning ability between particles, and balance the global and local search ability of the algorithm. In addition, this paper uses orthogonal analysis experiments to find reinforcement learning methods for the selection of state, action parameters and reward functions in the PSO algorithm. The experiment is tested on the CEC2013 test function. The results show that the convergence speed and convergence accuracy of the QLPSOES algorithm are significantly improved compared with other algorithms, which verifies that the algorithm has better performance.

    Table and Figures | Reference | Related Articles | Metrics
    Abstract367
    PDF175
    HTML9
    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
    Abstract354
    PDF223
    Object Tracking Algorithm with Fusion of Multi-feature and Channel Awareness
    ZHAO Yunji, FAN Cunliang, ZHANG Xinliang
    Journal of Frontiers of Computer Science and Technology    2022, 16 (6): 1417-1428.   DOI: 10.3778/j.issn.1673-9418.2011057

    In order to solve the problem of drift or overfitting in the tracking process of depth feature description target, an object tracking algorithm combining multiple features and channel perception is proposed. The depth feature of the tracking target is extracted by the pre-training model, the correlation filter is built according to the feature, and the weight coefficient of each channel filter is calculated. According to the weight coefficient, the feature channel generated by the pre-training model is screened. The standard deviation of the retained features is calculated to generate statistical features and they are fused with the original features. The fused features are used to construct related filters and correlation operations are performed to obtain feature response maps to determine the location and scale of the target. Based on the depth feature of the tracking result area, the filter constructed by fusion feature is made sparse online updates. The algorithm in this paper and some current mainstream tracking algorithms are tested on the public datasets OTB100, VOT2015 and VOT2016. Compared with UDT, without affecting the tracking speed, the proposed algorithm has stronger robustness and higher tracking accuracy. The experimental results show that the proposed algorithm shows strong robustness under the challenges of target scale variation, fast motion and background clutters.

    Table and Figures | Reference | Related Articles | Metrics
    Abstract353
    PDF343
    HTML7
    Practice on Program Energy Consumption Optimization by Energy Measurement and Analysis Using FPowerTool
    WEI Guang, QIAN Depei, YANG Hailong, LUAN Zhongzhi
    Journal of Frontiers of Computer Science and Technology    2022, 16 (6): 1291-1303.   DOI: 10.3778/j.issn.1673-9418.2102046

    Energy-aware programming (EAP) is a new approach to reduce energy consumption of computing systems. It introduces energy as one of the main design metrics into the process of software development to reduce program energy consumption by adjusting the way of programming. The implementation of EAP is facing some difficulties in finding energy consumption hot spots, identifying main factors which cause excessive energy consumption, and locating inappropriate code segments in the program. To address these issues, this paper proposes a new method called EPC (energy-performance correlation) for joint measurement and analysis of energy consumption and perfor-mance events during program execution. Firstly, the basic principles of EPC are introduced and the implementation of an EPC-based tool, FPowerTool, for program energy consumption measurement and analysis is presented. Then, the method of energy-performance events correlation analysis for identifying the main factors influencing energy consumption is presented. Finally, a set of programs is used as case studies to show how to locate the code segments related to high energy consumption by correlation analysis, and how to change the coding and data placement and access to reduce the program energy consumption. The experiment results show that based on the energy-aware and analysis capabilities provided by the EPC method, program performance and energy efficiency can be improved by improving data definition, assignment, placement, and access methods.

    Table and Figures | Reference | Related Articles | Metrics
    Abstract345
    PDF136
    HTML5
    Review of Knowledge Tracing Model for Intelligent Education
    ZENG Fanzhi, XU Luqian, ZHOU Yan, ZHOU Yuexia, LIAO Junwei
    Journal of Frontiers of Computer Science and Technology    2022, 16 (8): 1742-1763.   DOI: 10.3778/j.issn.1673-9418.2111054

    As one of the key research directions in the field of intelligent education, knowledge tracing (KT) makes use of a large amount of learning trajectory information provided by the intelligent tutoring system (ITS) to model students, measure their knowledge level automatically, and provide personalized learning programs for them, to achieve the purpose of AI-assisted education. The research progress of knowledge tracing models for intelligent education is reviewed comprehensively. Three representative models are knowledge tracing based on Bayes, knowledge tracing based on Logistic regression model, and deep learning knowledge tracing which has developed rapidly in recent years and shows better performance. Knowledge tracing based on Bayes is divided into Bayesian knowledge tracing (BKT) and BKT model combining personalization, knowledge correlation, node state and real problem expansion. Knowledge tracing based on Logistic regression model is divided into item response theory (IRT) and factor analysis model. Knowledge tracing based on deep learning can be divided into deep knowledge tracing (DTK) and its improved model, designing network structure and introducing attention mechanism. The international open education datasets available to researchers and the commonly used model evaluation indicators are introduced. The performance, characteristics and application scenarios of different types of methods are compared and analyzed. It also discusses the existing problems of the current research and looks forward to future develop-ment direction.

    Table and Figures | Reference | Related Articles | Metrics
    Abstract345
    PDF137
    HTML13
    Link Prediction Model for Dynamic Graphs
    TANG Chen, ZHAO Jieyu, YE Xulun, ZHENG Yang, YU Shushi
    Journal of Frontiers of Computer Science and Technology    2022, 16 (10): 2365-2376.   DOI: 10.3778/j.issn.1673-9418.2101055

    In the real world, any complex relationships can be represented as graphs, such as communication networks, biological networks, recommendation systems, etc. Link prediction is an important research topic in the field of graphs, but most of the current link prediction models are only for static graphs, and they ignore the evolution pattern of graphs in the time domain and the importance of global features in the evolution process. To this end, this paper proposes a link prediction model for dynamic graphs. First, in order to obtain high-quality global features, the model uses adversarial training to optimize the mutual information loss of global features and higher-order local features. Then a perceptual model based on a wide smooth stochastic process is used to ensure the smoothness of the global features in the time domain by constraining the mean and autocorrelation function values of the global features in the time dimension. The evolution pattern of the dynamic graph is then captured using a long and short-term memory (LSTM) network. Finally, the loss of predicted and true values is optimized using adversarial networks. The experimental results on USCB, SBM and AS datasets show that the proposed model performs well in the link prediction task of dynamic graphs, and it not only significantly improves the AUC values, but also reduces the MSE values. Also, the results of the ablation experiments show that the local features contribute to the global feature ground extraction, and the quality and smoothness of the global features play an important role in network link prediction.

    Table and Figures | Reference | Related Articles | Metrics
    Abstract341
    PDF227
    HTML7