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: Download Citations EndNote Ris BibTeX Toggle Thumbnails

Select

Research Review of UAV Recognition Based on Multi-Modal Fusion LI Minshu, ZHOU Mohan, ZHI Ruicong Computer Engineering and Applications    2025, 61 (21): 1-14.   DOI: 10.3778/j.issn.1002-8331.2501-0014 Abstract （1195）      PDF（pc） （17525KB）（986）       Knowledge map    Save With the rapid development of UAV technology, the application of related technologies is increasing, but it also brings many security risks and regulatory problems. As an important means to deal with these challenges, Anti-UAV detection technology has received extensive attention. Traditional UAV detection methods rely on a single modal data, such as vision, audio, radar and radio frequency signals, etc. However, these single modal data can obtain limited information in complex scenes. In recent years, deep learning methods have made good progress in the field of small object detection, and the related research of multi-modal fusion technology has further improved the accuracy and robustness of object detection. This paper reviews the research progress in the field of UAV detection, and focuses on summarizing the current research status of multimodal fusion technology. In addition, the evaluation indicators and public datasets of related UAV detection are sorted out, the limitations of existing technologies are analyzed, and the research directions for improving detection accuracy and robustness in the future are also pointed out. Reference | Related Articles | Metrics

Select

Computer Engineering and Applications    2026, 62 (1): 0-0.   Abstract （1165）      PDF（pc） （703KB）（151）       Knowledge map    Save Related Articles | Metrics

Select

Review on Development of Spatio-Temporal Graph Neural Networks for Traffic Flow Prediction YAN Jiahe, LI Honghui, SUN Jing, LIU Jie, ZHANG Junwen, YANG Xiaorui, XU Yi Computer Engineering and Applications    2025, 61 (22): 1-19.   DOI: 10.3778/j.issn.1002-8331.2502-0225 Abstract （897）      PDF（pc） （1418KB）（437）       Knowledge map    Save In recent years, the application of deep learning in traffic flow prediction has attracted wide attention, especially the spatio-temporal graph neural network has achieved remarkable success in capturing spatio-temporal dependencies and predicting traffic characteristics. Although some reviews have examined the application of spatio-temporal graph neural networks, most of these studies focus primarily on application scenarios and fail to provide an in-depth analysis from the perspective of model design. Furthermore, a unified model classification framework is absent. This paper proposes a hierarchical classification method that considers the key elements such as module selection, fusion mechanism, architecture design, and training strategy. The spatio-temporal graph neural networks can be divided into six categories, namely recurrent graph convolutional network, spatio-temporal fully convolutional network, spatio-temporal attention network, spatio-temporal encoder network, spatio-temporal hybrid architecture network, and spatio-temporal networks with additional strategies. For each category, the unique model construction and fusion mechanisms are analyzed in detail, and the different model variants are compared. By analyzing both representative and recent works, the development trend of spatio-temporal graph neural networks is discussed, and the code addresses of open-source models are provided. Subsequently, the commonly used public datasets are gathered, and the performance of the latest advanced models is visually analyzed by comparing the results of previous experiments. Finally, the development opportunities and challenges in this field are summarized to offer insights for future research. Reference | Related Articles | Metrics

Select

Survey of Medical Image Registration Based on Unsupervised Learning SHEN Longfeng, YU Yexun Computer Engineering and Applications    2026, 62 (18): 18-32.   DOI: 10.3778/j.issn.1002-8331.2509-0271 Abstract （887）      PDF（pc） （3330KB）（641）       Knowledge map    Save Medical image registration is a fundamental task in the field of medical image analysis and has been widely used in clinical applications such as disease progression tracking, atlas construction, statistical analysis, and surgical navigation. However, traditional registration algorithms are limited by their relatively low computational efficiency, making it difficult to meet the diverse application demands nowadays. In recent years, deep learning-based medical image registration methods have gradually become a major research focus in the industry. Furthermore, due to the difficulty in obtaining annotated datasets with realistic deformation fields, how to construct registration models through unsupervised learning has emerged as a prominent research topic. By reviewing relevant literature on unsupervised medical image registration over the past decade, this paper categorizes the mainstream registration frameworks into three types：single-stream, cascade, and pyramid architectures. Based on this categorization, it systematically elaborates on the development trajectory, key deep learning technologies, and future directions of unsupervised medical image registration. Reference | Related Articles | Metrics

Select

Improved YOLOv13 for Infrared Remote Sensing Small Object Detection LI Ping, CHEN Jifeng Computer Engineering and Applications    2026, 62 (7): 131-142.   DOI: 10.3778/j.issn.1002-8331.2509-0101 Abstract （528）      PDF（pc） （5813KB）（4342）       Knowledge map    Save To address the challenges of small object size, low signal-to-noise ratio, and susceptibility to complex background interference in infrared remote sensing, the YOLOv13 model is improved to meet the requirements of real-time and lightweight detection. A multi-level feature aggregation module (MFAM) is constructed to aggregate hierarchical information from different semantic depths and spatial resolutions in a bottom-up manner, while adaptively recalibrating their contributions to alleviate the dilution of small objects in deep semantic layers. A dual-path fusion pyramid network (DFPN) is designed, where a top-down semantic enhancement path and a bottom-up detail refinement path interact in a complementary manner to achieve cross-scale information circulation, thereby enhancing the separability of weak thermal targets. The proposed context-aware fusion block (CAFBlock) adopts a dual-branch structure of global self-attention and local depthwise convolution to jointly model long-range dependencies and fine-grained local features. In addition, it integrates a dual-path processing strategy of dilated convolution with multiple receptive fields and depthwise convolution for local details, combined with a gated fusion mechanism, to comprehensively strengthen multi-scale context modeling. Comparative experiments on the SIRST and HIT-UAV datasets demonstrate that the improved model achieves 90.06% and 64.37% AP, with relative gains of 7.65 percentage points and 8.55 percentage points, respectively, which verifies the effectiveness and feasibility of the proposed approach. Reference | Related Articles | Metrics

Select

Review of Neural Network-Based Machine Translation Research MA Xiao, TIAN Yonghong, ZHAO Wei Computer Engineering and Applications    2025, 61 (22): 36-54.   DOI: 10.3778/j.issn.1002-8331.2501-0086 Abstract （520）      PDF（pc） （1474KB）（199）       Knowledge map    Save With the advancement of computer technology, machine translation has become a key tool for cross-language communication. Its development process can be divided into rule-based machine translation, statistics-based machine translation, and deep learning-based neural machine translation. Focusing on the application and innovation of large language models in the field of translation, this paper comprehensively reviews and systematically sorts out the latest developments of neural machine translation (NMT). The evolution of machine translation is summarized, and the mainstream architecture development of NMT is analyzed, from the early recurrent neural network to the convolutional neural network, and then to the widely used Transformer model and its variants. Three key dimensions of large language model translation are deeply analyzed, and the differences between full parameter fine-tuning and efficient parameter fine-tuning in translation tasks are systematically compared. The technical challenges and solutions of multilingual large model translation technology, zero-sample and few-sample cross-language transfer are discussed in detail. The large-scale model translation methods of knowledge graph enhancement, domain professional knowledge fusion and multi-modal knowledge fusion are comprehensively reviewed. In addition, the evaluation indicators and commonly used datasets of machine translation are introduced, and the research prospects of low-resource language translation promotion, interpretable and controllable translation systems, cross-cultural adaptive translation, computing resource optimization, privacy protection and security controllability are discussed. Reference | Related Articles | Metrics

Select

Survey on Multi-Label Learning Under Complex Data Environment DU Guodong, WANG Ao, LU Pengwei, YE Qianzhi, ZHANG Jia Computer Engineering and Applications    2026, 62 (11): 41-61.   DOI: 10.3778/j.issn.1002-8331.2507-0192 Abstract （503）      PDF（pc） （1120KB）（564）       Knowledge map    Save Multi-label learning is an important learning paradigm in the field of machine learning, which shows advanced performance in many applications. Data with the main characteristics of large-scale, incomplete information, multiple dimensions and dynamic evolution are bringing many challenges to multi-label learning. It is necessary to carry out a more refined design of the multi-label learning method according to the characteristics of different learning tasks under complex data environment. Therefore, this paper analyzes the source of the complexity of multi-label data and reviews the research progress of multi-label learning under complex data environment. Firstly, the paper introduces the problem definition, learning form and development trend of multi-label learning in detail. Next, the complexity of multi-label data from three levels：label, feature and sample is discussed. Then, the summarized, elaborated and analyzed multi-label learning methods under complex data environment are provided. Finally, the challenges and the possible future application directions of multi-label learning are summarized. Reference | Related Articles | Metrics

Select

Review of 3D LiDAR SLAM Research for Embodied Intelligent Robots in Dynamic Environments LI Jingdan, YU Junqi, FENG Chunyong, WANG Ben, WANG Kaiwen, WU Yonghua Computer Engineering and Applications    2025, 61 (22): 55-74.   DOI: 10.3778/j.issn.1002-8331.2503-0065 Abstract （470）      PDF（pc） （1875KB）（189）       Knowledge map    Save Simultaneous localization and mapping (SLAM) is a key technology for ambient interaction and autonomous decision-making in embodied intelligent robots, and most of the current SLAM algorithms based on 3D LiDAR are based on static environments, whereas the presence of dynamic objects will lead to a reduction in the localization and mapping accuracy of LiDAR SLAM algorithms. Based on this issue, the relevant research on dynamic LiDAR SLAM algorithms by scholars at home and abroad is elaborated in detail. According to the different principles of dynamic object detection, the methods of removing dynamic objects are classified into semantic segmentation-based, ray tracing-based, visibility-based, etc. , and the main ideas and related application algorithms of each method are analyzed. The objects with different degrees of dynamics are classified, and the processing strategies corresponding to the different categories of dynamic objects in the LiDAR SLAM framework are summarized, and the difficulties and mainstream algorithms of online real-time processing, offline post-processing, lifelong SLAM strategies are introduced. The main accuracy evaluation indexes and datasets of dynamic LiDAR SLAM algorithms are also outlined. The future development trend of dynamic LiDAR SLAM algorithms is outlooked. Reference | Related Articles | Metrics

Select

Review of Monocular Vision Object Detection Based on Deep Learning LIU Guichao, WANG Huaiguang, REN Guoquan, WU Dinghai Computer Engineering and Applications    2026, 62 (1): 1-19.   DOI: 10.3778/j.issn.1002-8331.2504-0330 Abstract （436）      PDF（pc） （2212KB）（427）       Knowledge map    Save Monocular visual object detection, characterized by its low hardware cost and high real-time performance, has gradually become a core technology in fields such as autonomous driving and intelligent surveillance, playing an indispensable role. However, issues such as geometric ambiguity, occlusion robustness, and small object detection accuracy remain significant bottlenecks in current research. This paper primarily focuses on algorithm-level advancements, systematically quantifying the progress in monocular visual object detection technology from three perspectives: algorithm evolution, performance evaluation, and lightweight design. Firstly, single-stage detection algorithms are ?deconstructed into classic convolutional architectures and Transformer architectures, analyzing and summarizing their structural innovations and performance bottlenecks, revealing the trade-off patterns between accuracy, speed, and complexity. Secondly, from the three levels of network design, algorithm optimization, and model compression, this paper explores the integration strategies of lightweight technologies with object detection algorithms. It also consolidates multi-dimensional evaluation metrics from the three main official datasets used for training and evaluation in object detection, building a cross-model comparison framework based on the MS-COCO-2017 dataset to conduct a horizontal performance comparison of different single-stage detectors. Finally, the paper looks ahead to cutting-edge directions such as multimodal fusion and lightweight improvements, aiming to provide systematic references for the engineering application and theoretical breakthroughs of monocular visual object detection algorithms. Reference | Related Articles | Metrics

Select

Survey of Research on Encrypted Traffic Classification Based on Deep Learning WANG Ying, WANG Gang, GAO Yunpeng, HUO Chuang Computer Engineering and Applications    2025, 61 (21): 61-80.   DOI: 10.3778/j.issn.1002-8331.2501-0218 Abstract （426）      PDF（pc） （1964KB）（135）       Knowledge map    Save With the rapid development of Internet technology, the types of network traffic have become complex and variable. At the same time, to ensure data security, a large amount of information is transmitted through encryption protocols. Under the encryption condition, the original information of the traffic is invisible, which makes traditional traffic classification methods no longer applicable. In this context, the encryption traffic classification technology has emerged. Its aim is to identify and distinguish the types and sources of encrypted traffic. Encryption traffic classification not only needs to correctly distinguish various known traffic for traffic control but also needs to identify unknown traffic that may carry malicious information for security protection. This paper introduces the research status of encryption traffic classification technology in a general environment, analyzing from three aspects: known traffic classification, unknown traffic classification, and data sets. It discusses the future development trends of encryption traffic classification technology in a general environment. Furthermore, it analyzes the research status of encryption traffic classification technology in an industrial internet environment, including the lack of public traffic data, diverse industrial protocols, and complex feature extraction. Finally, it looks forward to future research directions, including building high-quality data sets, optimizing feature extraction methods, and improving the accuracy of unknown traffic detection. To achieve precise classification of encrypted traffic and ensure network service quality and security protection, it provides references and inspirations. Reference | Related Articles | Metrics

Select

YOLO-PD:Lightweight Real-Time Pedestrian Detection Algorithm CHEN Shengbao, SHI Longzhao Computer Engineering and Applications    2026, 62 (6): 122-133.   DOI: 10.3778/j.issn.1002-8331.2507-0218 Abstract （410）      PDF（pc） （13743KB）（544）       Knowledge map    Save To address the limited resources of edge devices and the low detection accuracy of pedestrian detection algorithms on small objects, multi-scale objects, and geometrically deformed objects caused by overlapping occlusions, YOLO-PD is proposed which is a YOLOv8-based pedestrian detection algorithm suitable for edge deployment. For small objects, a partial Transformer block (PTB) is designed to enhance feature extraction. Hybrid structure of PTB maintains efficient feature extraction while reducing computational costs. For multi-scale objects, a pyramid shared dilation convolution (PSDC) is introduced, leveraging shared-weight multi-scale dilation convolutions to improve multi-scale feature extraction while minimizing module size. For geometrically deformed objects, a light deformable dynamic head (LDDH) is developed. It dynamically adjusts weighting factors to improve detection accuracy and employs deformable convolutions to better capture features of deformed objects. Experimental results show that compared to the baseline model YOLOv8n, YOLO-PD achieves 2.9 and 1.9 percentage points higher mAP50 on the custom pedestrian detection datasets COCO-Person and VOC-Person, respectively, while reducing parameters by 34.3%. On the public dataset WidePerson, it improves mAP50 by 1.8 percentage points and mAP50:95 by 1.1 percentage points. The algorithm excels in pedestrian detection with high accuracy, strong generalization, and minimal parameters, making it ideal for edge devices. Reference | Related Articles | Metrics

Select

Enhanced YOLOv11s for Detecting Small Objects in Aerial Images GUO Jialin, CAO Yunfeng Computer Engineering and Applications    2026, 62 (8): 80-92.   DOI: 10.3778/j.issn.1002-8331.2507-0111 Abstract （395）      PDF（pc） （7612KB）（469）       Knowledge map    Save Aiming at the challenges of high-dynamic scenarios, limited target feature information, and constrained onboard computational resources in small object detection from UAV aerial images, this paper proposes a detection method for small aerial objects based on an improved YOLOv11s. Firstly, a dense cross-path feature pyramid network (DCP-FPN) is introduced as the Neck structure, where the large-object detection layer is removed and a small-object detection layer is added. By adopting dense connections to maximize feature utilization efficiency, the model significantly reduces the number of parameters while effectively enhancing the capability to capture small object features. Secondly, a novel lightweight convolutional module named Ghost-DSConv is proposed, which integrates dynamic channel adjustment and dual-branch feature interaction. The main branch employs depthwise separable convolution (DSConv), supplemented by a low-cost branch composed of group convolutions to generate supplementary features. This design extracts spatial features at a lower computational cost and enhances feature diversity. Finally, the paper proposes a lightweight small-target attention mechanism module (lightweight small-target attention, LSTA), which introduces a triple attention reinforcement mechanism to significantly enhance the model??s detection performance for small targets with minimal computational overhead. The experimental results on the VisDrone2019-DET dataset demonstrate that the improved algorithm proposed in this paper achieves 44.8% mAP50 and 27.4% mAP50-95. The enhanced YOLOv11s model has only 3.51×106 parameters and is deployed on an RK3588s?based embedded platform, where it successfully meets real-time detection requirements, achieving a favorable balance between accuracy and efficiency. Additionally, the proposed algorithm??s strong generalization capability and effectiveness are further validated on the CARPK and Tinyperson datasets. Reference | Related Articles | Metrics

Select

Review of Question Answering Techniques for Knowledge Graph QIAN Shenyi, FU Bowen, LI Daiyi, LIANG Yaoyao Computer Engineering and Applications    2025, 61 (23): 1-23.   DOI: 10.3778/j.issn.1002-8331.2501-0066 Abstract （394）      PDF（pc） （1714KB）（326）       Knowledge map    Save Intelligent question answering is a key technology to obtain demand information accurately and quickly from massive data. In recent years, intelligent question answering technology has achieved remarkable development, such as problem-based information extraction technology, semantic understanding technology and vector modeling method. However, with the rapid development of intelligent question answering technology, people are eager to have a reasonable division of intelligent question answering model to facilitate the use of users in different fields. In order to divide intelligent question answering model reasonably, it is convenient for researchers in the field of intelligent question answering to conduct in-depth research. Through the investigation of relevant literature in the field of knowledge graph Q&A, this paper summarizes the key technologies of knowledge graph Q&A, including entity linking and knowledge embedding, and introduces the related concepts and processing flow of knowledge graph Q&A in detail. In addition, according to different methods, knowledge graph-oriented question answering techniques are divided into three main categories: semantic parsing, information retrieval and large language model-based methods, and their advantages and disadvantages are introduced and the evaluation indexes of knowledge graph question answering models are summarized respectively. Finally, some suggestions and thoughts are put forward for the existing problems and the future development direction of knowledge graph question-answering technology. Reference | Related Articles | Metrics

Select

Survey on Traffic Engineering in Software-Defined Networking Based on Reinforcement Learning LIU Yanfei, WANG Chengjin, LI Chao Computer Engineering and Applications    2025, 61 (24): 1-28.   DOI: 10.3778/j.issn.1002-8331.2412-0248 Abstract （389）      PDF（pc） （1399KB）（306）       Knowledge map    Save Software-defined networking（SDN）, with its global and centralized management architecture, has brought revolutionary changes to the management of complex and dynamic networks, and has also created favorable conditions for network traffic engineering. Concurrently, reinforcement learning has garnered significant attention due to its pronounced advantages in decision optimization. The integration of reinforcement learning with the unique architecture of SDN and its application to SDN traffic engineering holds substantial practical significance. Firstly, from both theoretical and practical perspectives, based on the trajectory of technological development, the paper reviews the advancements in reinforcement learning, deep reinforcement learning, and multi-agent deep reinforcement learning in SDN traffic engineering. Additionally, it conducts a thorough synthesis and analysis of existing research outcomes across various dimensions, including methodological categorization, network scenarios, reinforcement learning algorithms, and traffic engineering objectives, providing a multidimensional perspective on the integration of reinforcement learning with SDN traffic engineering. Subsequently, it further summarizes the research progress of reinforcement learning combined with other technologies, demonstrating its potential to enhance the performance of traffic engineering. Ultimately, based on a summary of the current research progress, the paper analyzes the challenges faced and proposes future research directions, providing some reference for deepening exploration in this domain. Reference | Related Articles | Metrics

Select

Review of Security Protection of Industrial Control Systems Based on Digital Twin WANG Kunkun, LI Yahui, DU Xin, XU Peihang, ZHOU Chunjie Computer Engineering and Applications    2026, 62 (6): 1-15.   DOI: 10.3778/j.issn.1002-8331.2508-0252 Abstract （384）      PDF（pc） （1788KB）（392）       Knowledge map    Save Digital twin technology constructs high-fidelity dynamic models of physical entities in a digital space, enabling real-time simulation of their behaviors in virtual spaces, and facilitating interactive coevolution between the digital twin and its physical counterpart. It offers a novel perspective for addressing security challenges in industrial control systems (ICSs). This paper outlines the multiple challenges faced by ICSs in ensuring system availability. The fundamental principles, evolutionary history, and key enabling technologies of digital twins are delineated. The applications of digital twin technology in ICSs security are surveyed, emphasizing progress in system emulation, protective architectures, anomaly detection, and risk assessment, alongside an assessment of current research shortcomings. The future development directions of digital twins in the information security protection of ICSs are summarized and prospected. Reference | Related Articles | Metrics

Select

Multimodal Industrial Defect Detection and Intelligent Decision-Making Driven by Large Vision-Language Models DONG Yutong, HOU Huifang, GONG Mingming, CHEN Zikang Computer Engineering and Applications    2026, 62 (8): 176-188.   DOI: 10.3778/j.issn.1002-8331.2507-0389 Abstract （379）      PDF（pc） （10817KB）（208）       Knowledge map    Save Defect detection is an important application scenario in the industrial field. Aiming at the problems of low traditional detection efficiency, intelligent analysis and processing of industrial data, insufficient generalization ability of single-modal system and hallucination of large models, an enhanced industrial defect intelligent inspection system is proposed and implemented to support multi-source heterogeneous data collaborative processing and efficient decision-making. The system fine-tunes a multimodal large model for industrial anomaly detection. Through improved cross-modal feature alignment algorithms and prompt learning, it achieves semantic fusion of multi-source data such as images and texts, and synchronously outputs semantic descriptions of defect recognition results. It constructs an industrial data knowledge base, uses RAG retrieval to enhance generation, suppresses model hallucinations and improves detection credibility and decision-making effects. Combined with Depth-Anything-V2, it generates highly consistent depth maps to support 3D quantitative analysis of defects, breaking through the limitations of traditional 2D detection. A natural language-driven Excel intelligent analysis module automatically extracts and visualizes quality inspection table data. The OCR intelligent inspection module integrates PaddleOCR and ErnieBot to realize text extraction and semantic understanding of industrial documents. Finally, the agent integrates the core functional modules to provide comprehensive decision-making advice. Tests on 5 typical industrial parts such as metals and screws show that the system’s average recognition accuracy for defect types reaches 95.26%, with an average error of 2.9 pixels in defect location positioning. It expands the automation level and analysis dimensions of industrial quality inspection, providing a practical technical solution for the intelligent transformation of manufacturing. Reference | Related Articles | Metrics

Select

Survey of Vision-Language-Action Models： Towards General-Purpose Robots CHEN Wenqi, CHEN Jiafeng, ZHI Pengxiang, SHI Lulu, WEN Luhong Computer Engineering and Applications    2026, 62 (11): 17-40.   DOI: 10.3778/j.issn.1002-8331.2511-0018 Abstract （370）      PDF（pc） （1516KB）（267）       Knowledge map    Save The vision-language-action (VLA) model, as an important research direction in embodied intelligence, aims to overcome the semantic fragmentation and generalization bottleneck of traditional robot systems in open environments by deeply integrating perception, understanding, and action. Based on the relevant progress in the VLA field, this paper first reviews the development history and current research status of VLA models. Then, from the perspective of system architecture, existing models are classified into three types： monolithic, cascaded, and hierarchical, and the design ideas and representative progress of each type of architecture are analyzed in depth. At the same time, the relevant datasets and evaluation benchmarks that support VLA research are systematically summarized. Finally, based on the representative achievements in recent years, the core challenges faced by current VLA models are analyzed, and the future development directions are prospected. Reference | Related Articles | Metrics

Select

Review of Research on Multimodal Fusion Event-Based Camera SLAM Technology ZHAO Junyang, YU Han, ZHANG Zhili, ZHU Huixin, LYU Shenhua, ZHANG Kefan Computer Engineering and Applications    2026, 62 (9): 1-19.   DOI: 10.3778/j.issn.1002-8331.2505-0237 Abstract （356）      PDF（pc） （3751KB）（311）       Knowledge map    Save Event cameras are an emerging type of sensor that offer high dynamic range, low latency, high temporal resolution, and low data redundancy. Applying event cameras to simultaneous localization and mapping (SLAM) technology can fully leverage their advantages, breaking the limitations of traditional sensors in various application scenarios. Therefore, this paper reviews the current research status of multimodal fusion event camera SLAM technologies and analyzes the characteristics and limitations of different approaches. Firstly, the paper introduces the fundamental principles of SLAM technology and event cameras, elaborating on the advantages of event cameras over traditional vision sensors. Secondly, from the perspectives of unimodal event camera SLAM (monocular, stereo) and multimodal fusion event camera SLAM (event-inertial, visual-inertial, multi-source sensor fusion), the paper analyzes the strengths and weaknesses of both in terms of real-time performance, application scenarios, and computational requirements, and summarizes their developmental trajectories. Subsequently, it discusses the impact of unimodal and multimodal fusion event cameras on system performance and provides a comparative analysis of the performance of some multimodal fusion event camera systems. Finally, this paper outlines future research directions for multimodal fusion event camera SLAM technology, such as optimization of multimodal event SLAM algorithms, enhancement of generalization capabilities, and expansion of multi-source heterogeneous sensor fusion architectures, aiming to provide references and inspiration for the application of event cameras in the field of SLAM. Reference | Related Articles | Metrics

Select

PV-HSD-2025：Infrared Benchmark Dataset for Photovoltaic Hotspot Detection with YOLOv8-P1 Architecture LIU Yuanlin, JIN Jianhui, LI Shenghong, ZHANG Tianfu Computer Engineering and Applications    2026, 62 (6): 240-252.   DOI: 10.3778/j.issn.1002-8331.2503-0078 Abstract （344）      PDF（pc） （3399KB）（210）       Knowledge map    Save In response to the challenges in the field of infrared defect detection for photovoltaic panels, including the lack of publicly available datasets, ambiguous definitions of small targets, and the suboptimal performance of existing models in detecting small targets, this paper constructs and releases the PV-HSD-2025 dataset. This dataset comprises 4?025 images and 25?181 annotated bounding boxes, supporting 16-bit raw infrared radiation data and multiple palette analyses. Through experiments, performance baseline data for mainstream object detection models, including the YOLO series, EfficientDet, and RTDETR-l, are established. It is demonstrated that defining small targets based on absolute pixel scale better aligns with the characteristics of convolutional networks. Defects are categorized into ultra-small targets （0-10?pixels）, small targets（10-20?pixels）, and medium targets （20+ pixels）. The YOLOv8-P1 model is proposed, which enhances small target detection performance by adding detection heads with larger input features in the shallow network layers, thereby reducing information attenuation caused by deeper network layers. Compared to the YOLOv8 model, YOLOv8-P1 achieves a maximum improvement of 10.0% in mAP@50 and a maximum improvement of 16.5% in mAP@50 for ultra-small targets. The study also investigates the use of auxiliary super-resolution inference in YOLOv8, showing a maximum improvement of 7.5% in mAP@50 and a maximum improvement of 13.3% in mAP@50 for ultra-small targets. The dataset, improved model source code, and weights have been open-sourced on Gitee：https：//gitee. com/liuyuanlin6445/pv-hsd-2025. Reference | Related Articles | Metrics

Select

Review of Path Planning Algorithms for Mobile Robots ZHANG Yonghong, GUO Zijian, LU Zhuheng, JIANG Liang, CAO Haixiao Computer Engineering and Applications    2026, 62 (2): 26-39.   DOI: 10.3778/j.issn.1002-8331.2507-0291 Abstract （343）      PDF（pc） （1715KB）（212）       Knowledge map    Save Path planning algorithms are one of the key technologies for enabling autonomous navigation of mobile robots, and their performance determines the quality of path planning. To comprehensively understand the research status and development of mobile robot path planning algorithms, a systematic review of commonly used algorithms is conducted. Firstly, based on the characteristics of path planning algorithms, they are classified into traditional algorithms, sampling-based algorithms, artificial intelligence-based algorithms, and intelligent-biologically-inspired algorithms. Secondly, based on this classification, the algorithm principles and practical application scenarios are briefly introduced, with a focus on the research achievements of various algorithms in recent years, and the advantages and disadvantages of each algorithm are summarized and compared. Then, four algorithms are selected to verify the effectiveness of the algorithms in the same simulation environment. Finally, the future development trends of mobile robots are prospected to provide a reference for the research on mobile robot path planning. Reference | Related Articles | Metrics

Select

Review of Attention Mechanism in Era of Large Language Models SHI Denghui, XI Xuefeng, CUI Zhiming, ZHU Run, WANG Jian Computer Engineering and Applications    2026, 62 (8): 34-47.   DOI: 10.3778/j.issn.1002-8331.2506-0314 Abstract （343）      PDF（pc） （1217KB）（161）       Knowledge map    Save Since the attention mechanism was proposed, the Transformer architecture based on the attention mechanism has quickly established the core position of large models. The large language model has ushered in a new development direction and promoted fruitful results in many fields such as natural language processing and computer vision. In recent years, with the rapid development of large models, the parameter scale of the model has continued to grow, and the traditional Transformer architecture has been difficult to meet the requirements of large model training. In addition to accumulating computing power, the adjustment of the model architecture and further exploration of the attention mechanism are effective ways to solve this challenge and have become a hot topic of research. This paper first introduces the traditional Transformer architecture and the current status of research on the Transformer architecture and its variants in recent years, and analyzes the principles of its core self-attention mechanism and the bottlenecks it faces. Subsequently, the improvements of the attention module in recent years are analyzed and summarized. Then, taking DeepSeek as an example, the core technical path of the Transformer-based MoE architecture and the multi-head latent attention mechanism (MLA) behind its explosion are explored. Finally, the current status of research on optimizing the attention mechanism is summarized and future research directions are prospected. Reference | Related Articles | Metrics

Select

Improved RT-DETR Algorithm for Small Object Detection in UAV Images GUO Jie, HU Jianlong, ZHANG Junchao, WANG Yuxiang, ZHANG Xinyi Computer Engineering and Applications    2026, 62 (8): 93-104.   DOI: 10.3778/j.issn.1002-8331.2507-0309 Abstract （338）      PDF（pc） （2233KB）（294）       Knowledge map    Save To address challenges in UAV aerial imagery, such as small object size, blurred features, and frequent occlusions, an improved real-time detection Transformer (RT-DETR) algorithm is proposed to enhance detection accuracy and robustness in complex scenes. A feature enhancement module, C2f synergistic multi-attention Transformer (C2f_SMT), is designed in the backbone to integrate shallow details and high-level semantics by combining the synergistic multi-attention (SMA) mechanism with Transformer architecture, thereby improving feature representation for small objects. To optimize feature interaction, a dual-attention feature interaction module (DAFI) is introduced, employing a parallel lightweight structure that reduces model complexity while preserving global modeling capacity. To address the issue of small-object information loss during multi-scale fusion, a cross-OmniKernel and small-target preservation feature fusion module (COSPFM) is proposed to enhance multi-scale perception of small targets. Experimental results on the VisDrone2019 dataset show that the improved model achieves a mAP@0.5 of 51.0% and a mAP@0.5:0.95 of 31.5%, outperforming the baseline RT-DETR by 3.1 and 2.2 percentage points, respectively. To evaluate generalization, the model is further tested on the UAVDT dataset, where it demonstrates improved accuracy across various traffic categories (car, truck, bus), achieving a mAP@0.5 of 34.4%, confirming the effectiveness and generalizability of the proposed method in multi-scenario small object detection tasks. Reference | Related Articles | Metrics

Select

Harmony-YOLO11：Lightweight Small Object Detector via High-Frequency Enhancement and Feature Guidance SUN Zhongyi, WANG Dong, CAO Guogang, ZONG Ming Computer Engineering and Applications    2026, 62 (10): 111-122.   DOI: 10.3778/j.issn.1002-8331.2509-0361 Abstract （324）      PDF（pc） （2129KB）（347）       Knowledge map    Save Small object detection in drone-captured images faces challenges including scale imbalance, limited visual information, and constrained computational resources. Existing detection models often struggle to balance accuracy and complexity for this task. To address these issues, this paper proposes Harmony-YOLO11, an improved YOLO11n-based algorithm for drone-captured small object detection. It introduces a high-frequency enhancement and cross-scale adaptive module (HCM) to strengthen small object edges and focus on object regions, enhancing model adaptability. An efficient feature guide feature pyramid network (FG-FPN) is developed with a feature fusion guide block (FFGB), achieving lightweight and effective feature fusion through simplified network paths. The C3K2_CCA module integrates CoordConv and CoordATT to improve spatial perception for small objects. A lightweight downsampling module MGC (maxpooling-ghost convolution) further reduces model complexity. Experiments on the VisDrone2019 dataset demonstrate that Harmony-YOLO11 improves mAP50 and mAP50-95 by 5.10 and 3.12 percentage points respectively compared to YOLO11n, while reducing parameters and model size by 31% and 25%. Additional evaluations on the TinyPerson dataset confirm the generalization and robustness of the algorithm. Reference | Related Articles | Metrics

Select

Survey of Vision Transformers for Fine-Grained Image Classification WEN Shixiong, ZHI Min Computer Engineering and Applications    2025, 61 (23): 24-37.   DOI: 10.3778/j.issn.1002-8331.2503-0014 Abstract （322）      PDF（pc） （2320KB）（221）       Knowledge map    Save Fine-grained image classification (FGIC) aims to identify subcategories that are visually highly similar yet exhibit subtle differences. With the rapid advancement of deep learning, FGIC algorithms have gradually evolved from traditional fully supervised learning to weakly supervised approaches. Vision Transformers (ViTs), leveraging multi-head self-attention mechanisms, eliminate the reliance on manual annotations and overcome the limitations of convolutional neural networks (CNNs) in terms of receptive field size and global modeling capacity, becoming one of the mainstream methods for this task. This paper first outlines the key characteristics and challenges of FGIC, and briefly introduces the architecture and advantages of ViT. Based on different feature fusion strategies, existing ViT-based improvements are categorized into hierarchical fusion, multi-local fusion, and multi-granularity fusion. The modifications of each category are illustrated in detail, and their underlying mechanisms are systematically analyzed and summarized. In addition, commonly used public datasets are reviewed, and future research directions are proposed based on current limitations, aiming to further explore the potential of ViT in FGIC tasks. Reference | Related Articles | Metrics

Select

MCT-YOLO: Small Object Detection Algorithm for Aerial Imagery ZHOU Zhongkun, ZHANG Yang, ZHANG Yu, MENG Ke, YUAN Zhaoyang Computer Engineering and Applications    2026, 62 (8): 130-141.   DOI: 10.3778/j.issn.1002-8331.2509-0032 Abstract （321）      PDF（pc） （2760KB）（251）       Knowledge map    Save To address the issue of low detection accuracy caused by small scale, low resolution, and high-density distribution of image targets in unmanned aerial vehicle-assisted intelligent transportation scenarios, an improved YOLOv11n-based algorithm for small object detection from an aerial perspective, named MCT-YOLO, is proposed. The detection layer structure is optimized by specifically adding a very small object detection head and removing the large object detection head to capture more local information and reduce feature interference, thereby adapting to small object detection tasks. A multi-frequency interactive downsampling (MFID) module is proposed to minimize feature loss during downsampling and retain more image information. The MobiVari structure is introduced to build the C3k2_MV module for deep feature extraction, enhancing detailed feature representation. Additionally, a multi-scale information fusion method called triple complementary fusion (TCF) is designed to integrate contextual information of different semantics, achieving complementary semantic and detailed information to improve small object detection capability. The proposed algorithm achieves mAP50 and mAP50-95 scores of 40.9% and 25.0%, respectively, on the VisDrone2019-DET dataset, representing improvements of 7.7 and 5.8 percentage points over the baseline network YOLOv11n. Meanwhile, the algorithm??s parameter count is reduced by 7.6%, making it suitable for small object detection scenarios in drone aerial imagery. Reference | Related Articles | Metrics

Select

Survey of User Interest Modeling for Recommendation Systems LYU Xueqiang, WANG Xiayu, MA Denghao Computer Engineering and Applications    2025, 61 (21): 15-29.   DOI: 10.3778/j.issn.1002-8331.2501-0190 Abstract （320）      PDF（pc） （818KB）（141）       Knowledge map    Save Focusing on the task of user interest modeling, this paper summarizes and analyzes the methods of click intention identification and interest construction, and discusses the existing challenges in this field. User interest modeling includes two cascade stages: click intention recognition and interest construction. According to whether or not differential attention is paid to the features involved in user click behavior, click intention recognition methods are classified into two categories: personalized and non-personalized. According to the different processing methods of user click intention sequence, the interest construction method is divided into two categories: aggregation and generation, which provides clear research ideas for this field. Experiments are carried out on ml-20m and Amazon_all_beauty datasets, and Recall, Precision, MRR and NDCG are used as evaluation indicators to verify the advantages and disadvantages of various interest construction methods. User interest modeling can construct interest representation according to behavior sequence and its context information, help the model learn the implicit relationship between user behaviors, and then realize personalized recommendation service. However, this task still faces some challenges, such as personalized click intention recognition method does not fully explore the potential correlation between unary click intentions, interest construction phase needs a deep understanding of interest diversity in order to capture different granularity of user interests and so on. Reference | Related Articles | Metrics

Select

ACED-YOLO：Multi-Feature Enhancement and Scale-Adaptive Intelligent Driving Detection Algorithm XUE Zhiyang, PAN Lihu, SONG Zeju, ZHANG Rui, ZHANG Guoyou Computer Engineering and Applications    2026, 62 (10): 230-244.   DOI: 10.3778/j.issn.1002-8331.2507-0369 Abstract （317）      PDF（pc） （5734KB）（328）       Knowledge map    Save Object detection is crucial for the accurate identification and localization of various traffic objects, such as motor vehicles, non-motorized vehicles, and pedestrians, in complex traffic scenarios for intelligent driving systems, which directly affects driving safety and reliability. However, existing methods still have limitations in edge feature representation, multi-scale feature processing, and long-range dependency capturing, which affect detection performance and computational efficiency. To address these issues, a lightweight intelligent driving detection algorithm ACED-YOLO is proposed with multi-dimensional feature enhancement and scale adaptability. A bidirectional axial context-aware feature integration neck network (BC-FIN) is developed. This network captures global context synchronously in both horizontal and vertical dimensions and explicitly characterizes rectangular key regions using axial features. A spatial feature reconstruction and dynamic interpolation fusion design is proposed to obtain rich multi-level features and contextual information. An edge Sobel enhanced spatial integration module (E-SESIM) is constructed, optimizing the C3k2 module. By paralleling Sobel and convolution branches, edge and spatial features are effectively fused, and a residual structure is embedded to suppress gradient vanishing, enhancing the object contour representation capability. An adaptive dynamic multi-scale detection head (DMDH-DCNv4) is designed, utilizing a multi-level attention mechanism and deformable convolutions to dynamically adjust feature extraction. This design adapts to multi-scale and multi-dimensional spatial features, improving both detection speed and feature capture efficiency. Experiments on the KITTI dataset show that ACED-YOLO achieves an mAP@0.5 of 85.2%, which is a nearly 10 percentage points improvement over YOLOv11n. Additionally, ACED-YOLO demonstrates excellent performance in detection accuracy and computational efficiency on the TinyPerson and UrbanNMV custom datasets. This method shows a significant advantage in object detection tasks for intelligent driving scenarios. Reference | Related Articles | Metrics

Select

Review on Machine Learning Modeling and Optimization of Battery Thermal Management Systems for Electric Vehicles GUO Hongfei, CUI Yu, ZHANG Rui Computer Engineering and Applications    2026, 62 (16): 1-20.   DOI: 10.3778/j.issn.1002-8331.2509-0387 Abstract （314）      PDF（pc） （1225KB）（254）       Knowledge map    Save The battery thermal management system (BTMS) is a key subsystem that ensures the safe operation, energy efficiency, and longevity of traction batteries in electric vehicles. Traditional physics-based methods rely on fine-grained modeling and parameter tuning, and under complex operating conditions they often suffer from model mismatch, limited real-time performance, and high computational cost. With advances in sensing and computing, machine learning has been widely applied to thermal-state modeling, thermal anomaly detection, and cooling-control optimization, and has also driven the adoption of lightweight techniques, such as model compression, quantization, and distillation on in-vehicle embedded platforms. This paper systematically reviews related progress of machine learning in thermal state modeling and prediction：Supervised learning shows clear advantages in temperature prediction, unsupervised and semi-supervised learning perform well in thermal anomaly detection, and reinforcement learning exhibits adaptive strengths in optimizing cooling-control strategies. By comparing trade-offs among accuracy, real-time capability, and computational demand, this paper emphasizes that physics-data integration and lightweight implementation are pivotal for engineering deployability. Overall, machine learning complements traditional approaches, improves prediction and control performance, and provides guidance for the intelligent development and engineering application of BTMS. Reference | Related Articles | Metrics

Select

Review of Metaheuristic Algorithms Research ZHANG Mengting, ZHANG Jun, HE Chengfeng Computer Engineering and Applications    2026, 62 (2): 40-53.   DOI: 10.3778/j.issn.1002-8331.2507-0022 Abstract （312）      PDF（pc） （905KB）（157）       Knowledge map    Save Meta-heuristic is an improvement of heuristics and an effective tool for solving complex optimization problems. In order to facilitate researchers to understand the research status and development trend of meta-heuristic algorithms more systematically, the meta-heuristic algorithms are reviewed. Firstly, the essence of meta-heuristics is clarified and a new classification framework is proposed. Different from the traditional review, the types of meta-heuristics are divided into five categories according to different sources of inspiration, and the inspiration sources, application scenarios and advantages of each type are discussed, so as to provide a direction for algorithm selection. Then, the application of meta-heuristic algorithms in four main fields： combinatorial optimization, scheduling problems, machine learning and data mining, and network design and routing is emphatically introduced, and the new research progress in different fields is expounded. Finally, the meta-heuristic algorithm is summarized, and the future research direction is prospected. Reference | Related Articles | Metrics

Select

Improved YOLOv11 Algorithm for Aerial Small Target Detection in UAVs JING Tingting, CAO Yudong, CHEN Xin, WANG Dongxia Computer Engineering and Applications    2026, 62 (2): 138-148.   DOI: 10.3778/j.issn.1002-8331.2506-0186 Abstract （306）      PDF（pc） （2738KB）（243）       Knowledge map    Save In the field of unmanned aerial vehicle aerial photography, the proportion of small targets is high, and the resources on board are limited, which results in low precision of existing detection models and difficulty in achieving a good balance between detection performance and resource consumption. To alleviate these issues, an improved YOLOv11 model is proposed. Firstly, the MDPE module is constructed as the attention module of the backbone network. By introducing a dynamic channel splitting strategy and a lightweight smoothing network, it achieves adaptive allocation of feature resources and enhancement of local details. Secondly, the DAFI module is designed to replace the feature fusion module in the neck network. By combining the feature enhancement module with a dual dynamic weighting mechanism, it enhances the algorithm’s perception of the spatial distribution of targets. Thirdly, block-based dynamic alignment convolution is embedded in the regression branch of the detection head to achieve adaptive alignment and fusion of feature maps, thereby improving the model’s detection capability for targets of different scales. Finally, by introducing the aspect ratio difference term and combining it with the small target weight adjustment mechanism, the ARSIoU loss function is designed to improve the model’s localization accuracy and bounding box regression efficiency for small targets. Experiments on the VisDrone2019 dataset demonstrate that the improved model outperforms the original YOLOv11 model in terms of precision, recall, mAP@50 by 3.5, 1.9, 3.2 percentage points respectively, indicating superior comprehensive performance compared to other small target detection algorithms tested, making it suitable for unmanned aerial vehicle aerial small target detection applications in complex scenarios. Reference | Related Articles | Metrics

Select

Survey on Question Answering Systems and Evaluation in the Era of Large Models CUI Longfei, WANG Zongshui, BAO Yingxu, ZHAO Hong Computer Engineering and Applications    2026, 62 (5): 1-17.   DOI: 10.3778/j.issn.1002-8331.2503-0004 Abstract （306）      PDF（pc） （1660KB）（299）       Knowledge map    Save In the era of large models (LMs), question answering (QA) systems exhibit new characteristics. This paper reviews QA system features and evaluation methods. From the stages of training data for question-answering model inference training, pre-training frameworks, model post-processing, and efficient model fine-tuning, it contrasts the early “pursuit of data and parameter scale” training methods with the current “emphasis on data and model efficiency, ” and systematically analyzes the new characteristics of large-model-based automatic question-answering systems. The paper summarizes existing QA evaluation methods, reviewing HELM (holistic evaluation of language model) regarding datasets, metrics, and quantitative assessment for QA tasks. Future research on LM-based QA systems will further expand and deepen in several asp-ects, including multimodal fusion, high security, high interpretability, low resource consumption, and a comprehensive evaluation system combining large models and automation. Reference | Related Articles | Metrics

Select

Review on Research and Applications of Deep Learning in Music Generation ZHAO Mingyuan, ZHOU Ruohua, YUAN Qingsheng, ZHOU Zhitong Computer Engineering and Applications    2026, 62 (10): 1-25.   DOI: 10.3778/j.issn.1002-8331.2505-0135 Abstract （304）      PDF（pc） （2110KB）（324）       Knowledge map    Save Music generation is an important interdisciplinary research direction in artificial intelligence and computer science, which has achieved remarkable progress in recent years with the breakthroughs of deep learning technologies. This paper presents a systematic review of research and applications of deep learning in the field of music generation. Music representations are categorized into three types：symbolic representation, audio representation, and multimodal representation. The architectural characteristics and performance comparisons of mainstream deep generative models, including LSTM, VAE, GAN, Transformer, and diffusion models, are outlined. Music generation tasks are divided into three categories according to generation requirements：symbolic music generation, audio music generation, and vocal music generation, with representative methods and key technological advancements in each task category systematically sorted out. On this basis, commonly used datasets suitable for different generation tasks, as well as subjective and objective evaluation metric systems, are summarized, and the performance of representative models is compared and analyzed through experimental data. The main challenges currently faced in music generation are discussed, including difficulties in music information modeling, data scarcity, lack of unified evaluation systems, and ethical and commercialization issues. Future application prospects in fields such as music education and psychotherapy are also explored. Reference | Related Articles | Metrics

Select

Review of Intelligent Analysis Methods for Electrocardiograms in Diagnosis of Arrhythmia and Myocardial Infarction HAN Chuang, FAN Baoqi, YU Mengyao, QUE Wenge Computer Engineering and Applications    2025, 61 (23): 59-71.   DOI: 10.3778/j.issn.1002-8331.2503-0022 Abstract （300）      PDF（pc） （2002KB）（123）       Knowledge map    Save Electrocardiogram (ECG) remains the gold standard for diagnosing arrhythmia and myocardial infarction (MI), offering advantages such as non-invasiveness, real-time monitoring, and portability, making it widely used in clinical practice. Research on intelligent analysis of ECG for these conditions holds great significance. Firstly, this paper introduces commonly used ECG databases for arrhythmia and MI. Then it reviews recent advances in ECG intelligent analysis over the past three years, including manual feature extraction, convolutional neural networks and their variants, graph neural networks, self-supervised learning, federated learning, active learning, deterministic learning, and generative model. Subsequently, it conducts an in-depth analysis of these methodologies from perspectives including data scale, classification patterns, model comparisons, and model complexity. The study compares the requirements, advantages, disadvantages, interpretability, and application scenarios of different approaches. Finally, it summarizes existing limitations in areas such as data quality and imbalance issues, conflicts between model generalizability and interpretability, trade-offs between privacy protection and collaborative efficiency, mismatches between computational resources and clinical deployment. Feasible solutions are proposed to address these challenges. Reference | Related Articles | Metrics

Select

Review of Knowledge Graph Entity Alignment Research：from Traditional Methods to Cutting-Edge Technologies CONG Shuo, SU Guibin, LIU Lin, WANG Hailong Computer Engineering and Applications    2026, 62 (1): 47-67.   DOI: 10.3778/j.issn.1002-8331.2412-0384 Abstract （300）      PDF（pc） （1204KB）（162）       Knowledge map    Save With the development of Internet and big data technologies, knowledge graphs, as a critical structured tool for describing entities and their relationships, have been widely applied across multiple domains. The entity alignment task in knowledge graphs aims to integrate entity information from heterogeneous knowledge graphs, addressing data silos and significantly enhancing the quality of knowledge graph construction and enabling cross-domain applications. This paper provides a comprehensive review of research progress in knowledge graph entity alignment. Firstly, it introduces the fundamental concepts and types of knowledge graphs. Subsequently, it elaborates on traditional entity alignment methods, including feature similarity-based approaches, machine learning-based techniques, and reasoning-based methodologies. The paper then focuses on entity alignment methods leveraging knowledge representation learning technologies, and explores challenges in aligning entities within multimodal and temporal knowledge graphs. Finally, it discusses the broad prospects of entity alignment in natural language processing and intelligent applications, as well as the potential of combining existing methods with emerging technologies to improve alignment accuracy and efficiency. Reference | Related Articles | Metrics

Select

Survey of Large Language Model Driven Intelligent Processing of Tabular Data WANG Xingkai, XI Xuefeng, CUI Zhiming, WANG Fei, ZHENG Qian Computer Engineering and Applications    2026, 62 (9): 20-45.   DOI: 10.3778/j.issn.1002-8331.2506-0198 Abstract （298）      PDF（pc） （2442KB）（221）       Knowledge map    Save Due to the structured and semi-structured characteristics of tabular data, it plays an irreplaceable pivotal role in tasks such as data warehouse construction, knowledge graph alignment and feature engineering. In recent years, large language models provide new technical possibilities for intelligent processing of “unified modeling” tables by means of extremely long context windows, zero/few-shot transfer capabilities, and pluggable tool interfaces. Firstly, this paper systematically combs the mainstream representation forms of tabular data and their influence on the complexity of subsequent tasks, and establishes the mapping between task pedigrees and typical datasets covering four categories of tasks：structure understanding, data understanding, reasoning, and data augmentation. From four dimensions of pre-training strategy, text serialization and embedding, prompt engineering and inference chain design, and retrieval enhancement generation and dynamic feedback mechanism, the key technologies of large language models enabling intelligent processing of forms are summarized. Secondly, according to the four modules of structure parsing, table understanding, reasoning generation and data governance, the latest applications of large language models in table detection and positioning, entity alignment, Text-to-SQL and other tasks are analyzed. Finally, the core bottlenecks faced by large language models in tabular scenarios are pointed out：insufficient structural understanding, cross-modal alignment errors, scarcity of labeled data, and poor execution reliability. Looking forward to the future, with the continuous evolution of the multi-agent collaborative decision-making framework, the structure-symbol hybrid reasoning paradigm, and the industry-specific instruction fine-tuning technology, the large language model is expected to complete the intelligent processing tasks of forms robustly, interpretable, and efficient in real business scenarios. Reference | Related Articles | Metrics

Select

Survey on Semi-Supervised Semantic Segmentation Methods for Remote Sensing Images DONG Yifan, SUN Wenli, ZHAO Yang, HUANG Pingping Computer Engineering and Applications    2025, 61 (24): 86-102.   DOI: 10.3778/j.issn.1002-8331.2504-0043 Abstract （293）      PDF（pc） （4481KB）（166）       Knowledge map    Save As an important research direction in the field of remote sensing technology, semantic segmentation of remote sensing images aims to segment remote sensing images at the pixel level and accurately classify them into predefined ground object categories. Traditional methods rely on a large number of pixel-level annotation data, but manual annotation is time-consuming and laborious. In order to solve this problem, a semi-supervised learning method is introduced. By combining a small number of labeled samples and a large number of unlabeled data for model training, the labeling requirements are significantly reduced. By analyzing and summarizing the related research on semi-supervised semantic segmentation of remote sensing images in recent years, the classification system of existing methods is systematically sorted out, and its advantages and disadvantages are deeply analyzed. Starting from the core ideas and technical strategies, the existing semi-supervised semantic segmentation methods of remote sensing images are systematically summarized and classified, and their innovations and limitations are discussed respectively. The datasets widely used in the research of semi-supervised semantic segmentation of remote sensing images are introduced. Based on the commonly used experimental settings and evaluation indicators, multi-method comparative analysis is carried out on different datasets. Finally, the future research trends of semi-supervised semantic segmentation of remote sensing images are discussed. Reference | Related Articles | Metrics

Select

Review of Research on Causal Discovery Techniques HU Zhiyuan, GAO Jintao Computer Engineering and Applications    2025, 61 (24): 40-67.   DOI: 10.3778/j.issn.1002-8331.2501-0440 Abstract （291）      PDF（pc） （1496KB）（164）       Knowledge map    Save Causal discovery techniques have broad applications in fields such as medicine, biology, economics, and social sciences, enabling the identification of causal relationships between variables, thereby enhancing the interpretability of prediction results. Causal discovery refers to the process of identifying causal relationships among variables from data, including determining whether a causal relationship exists between variables and understanding the direction and strength of such relationships. Currently, causal discovery faces challenges such as effectively leveraging high-dimensional data, precisely controlling confounding variables, and managing complex interactions among variables. Traditional causal discovery methods are based on conditional independence tests, heavily relying on data quality and performing poorly in high-dimensional contexts. Machine learning techniques have significantly advanced the development of causal discovery, including efficient data processing and analysis, uncertainty estimation, and credibility analysis. This review summarizes the current progress in causal discovery： it introduces representative methods in traditional causal discovery, exploring the issues in their core processes; subsequently, it summarizes popular causal discovery methods in the field of statistical learning, detailing their core ideas and comparing their performance and applicable data types and scenarios. The primary objective is to provide more valuable references for researchers in the fields of data science and statistical learning. Finally, future research directions for causal discovery are summarized. Reference | Related Articles | Metrics

Select

Review of Surrogate-Assisted Meta-Heuristic?Algorithms for High-Dimensional Computationally Expensive Optimization Problems WANG Hong, KANG Ling, GUO Yulin Computer Engineering and Applications    2025, 61 (22): 75-91.   DOI: 10.3778/j.issn.1002-8331.2501-0412 Abstract （289）      PDF（pc） （922KB）（93）       Knowledge map    Save High-dimensional and expensive optimization problems are widely present in fields such as energy and resource optimization, urban and environmental planning, industrial design and manufacturing, aerospace, communication and information, etc. The increasing of dimension leads to an expansion of the search space, while the computational expense limits the times that the true solution can be evaluated. The aforementioned reasons render traditional optimization algorithms ineffective. Surrogate-assisted meta-heuristic algorithms, which use surrogate models to replace the expensive real fitness evaluations and utilize meta-heuristic algorithms to guide the optimization direction, can significantly reduce computational time and cost while maintaining optimization accuracy. This paper, focusing on the characteristics of high-dimension and expensive computation in optimization problems, organizes recent literature on surrogate-assisted meta-heuristic algorithms from six perspectives： generating initial sample points, constructing and updating surrogate models, using evolutionary algorithms, balancing exploration and exploitation, designing adaptability, and practical applications. The paper summarizes how surrogate-assisted meta-heuristic algorithms address these two major challenges. Finally, it proposes future research directions for aspects that are currently under-researched. Reference | Related Articles | Metrics

Select

MDQF-YOLO: Railway Foreign Object Detection Algorithm for Complex Environments NIU Hongxia, LI Shuo, HOU Tao, ZHANG Wentao Computer Engineering and Applications    2026, 62 (8): 116-129.   DOI: 10.3778/j.issn.1002-8331.2507-0211 Abstract （289）      PDF（pc） （3040KB）（180）       Knowledge map    Save Existing railway foreign object detection methods suffer from false positives, missed detections, and slow detection speeds under complex conditions including low illumination, dusty weather, distant small objects, and occlusion scenarios. To address these challenges, this paper proposes MDQF-YOLO, an improved railway foreign object detection algorithm based on YOLO11. Firstly, an efficient feature extraction module, MEAN-C3K2, is designed to enhance feature extraction capability for multi-scale and distant small objects in complex environments. Secondly, a new neck structure DRFPN is designed, which improves the detection performance in complex occlusion scenarios by combining bidirectional feature pyramids, cross-stage feature connections and dynamic sampling mechanisms. Thirdly, quality-enhanced shared head (QESH) is proposed to reduce parameter count while addressing the mismatch between classification confidence and localization accuracy. Finally, the Focaler-ShapeIoU loss function replaces the CIoU loss function, focusing on different regression samples to address sample distribution imbalance while optimizing bounding box regression accuracy. Experimental results demonstrate that MDQF-YOLO achieves improvements of 3.6 and 6.0 percentage points in mAP@0.5 and mAP@0.5:0.95, respectively, compared to the baseline model on a custom railway foreign object dataset, with detection speed reaching 154 FPS, meeting requirements for both detection accuracy and real-time performance in railway intrusion foreign object detection. Additionally, generalization tests on VisDrone2019-DET and SODA-A datasets yield favorable results, fully validating the effectiveness and generalizability of the proposed model. Reference | Related Articles | Metrics

Select

Overview of Security Research on Jailbreak Attacks Against Generative Large Models LI Yan, WANG Gang, WANG Hao Computer Engineering and Applications    2026, 62 (6): 27-50.   DOI: 10.3778/j.issn.1002-8331.2509-0303 Abstract （282）      PDF（pc） （1907KB）（179）       Knowledge map    Save In recent years, generative large models have been widely used in a variety of key scenarios, including text generation, conversational interaction, and content creation. However, jailbreak attacks are emerging as a threat to these models. Jailbreak attacks can bypass their built-in security mechanisms and induce them to produce harmful outputs, posing security challenges such as ethical risks, privacy leaks, and model abuse. To address this threat, this paper comprehensively reviews recent research progress on jailbreak attacks against two mainstream generative models: large language models and multimodal large language models. This review focuses on three aspects: jailbreak attack types, defense strategies, and security assessment frameworks. It details the basic principles, implementation methods, and research conclusions of current jailbreak attack methods, providing valuable insights for future research. Building on this work, this paper further summarizes the current deficiencies in jailbreak security research for these two mainstream generative models and identifies key challenges and development opportunities for future research on the security of generative large models. This review provides guidance for researchers working on the complex applications and security of generative large models. Reference | Related Articles | Metrics