[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-462826-105":59,"doc-detail-462826-en":131},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","hierarchical-local-global-feature-fusion-network-for-robust-ship-target-recognition-in-complex-maritime-environment","Hierarchical Local-Global Feature Fusion Network for Robust Ship Target Recognition in Complex Maritime Environment","","Accurate ship target recognition remains challenging in complex maritime environments because sea clutter, multiscale target appearance, and limited discriminative features from single-type networks reduce classification reliability. This paper introduces a hierarchical local-global feature fusion network (HLGF-Net) that combines local structural cues from a CNN encoder with global semantic dependencies modeled by a Transformer. Stacked Transformer blocks progressively build hierarchical dependencies, enabling simultaneous capture of fine-grained contours and long-range contextual relationships. Experiments on ship recognition datasets show HLGF-Net outperforms traditional CNNs, pure Transformers, and recent vision architectures, especially with cluttered backgrounds, partial occlusion, and limited samples, providing a general strategy for robust maritime recognition.",{"@graph":69,"@context":123},[70,84,106],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/hierarchical-local-global-feature-fusion-network-for-robust-ship-target-recognition-in-complex-maritime-environment/462826/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/hierarchical-local-global-feature-fusion-network-for-robust-ship-target-recognition-in-complex-maritime-environment/462826.png","ImageObject",300,407,{"name":92,"@type":93},"Elsa","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-30","2026-09-30",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",14,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"What core idea does HLGF-Net use for ship target recognition?","Question",{"text":113,"@type":114},"HLGF-Net hierarchically fuses local structural cues from a CNN encoder with global semantic dependencies modeled by a Transformer using progressive stacked self-attention blocks.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"What problems in complex maritime environments does the paper target?",{"text":118,"@type":114},"It addresses background clutter, multiscale target appearance, and limited discriminative features produced by single-type networks, which together hinder accurate recognition.",{"name":120,"@type":111,"acceptedAnswer":121},"How does the proposed method perform compared with existing models?",{"text":122,"@type":114},"Experiments on ship recognition datasets show superior classification performance and F1 scores versus traditional CNNs, pure Transformers, and representative recent vision architectures, with strong robustness under low SNR and limited sample conditions.","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},462826,1790970076,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":140,"language":141,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":67,"update_tm":145,"read_time":146,"preview_page_count":19,"preview_urls":147},137455077381,"https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d","Article  \nHierarchical Local-Global Feature Fusion Network for Robust Ship Target Recognition in Complex Maritime Environment Xuanhe Liu , Shuning Zhang *, Si Chen, Jianchao Li and Yingying Luo  \nAcademic Editor: Wei Yi  \nReceived: 27 November 2025  \nRevised: 13 December 2025  \nAccepted: 18 December 2025  \nPublished: 19 December 2025  \nCopyright: © 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license.  \nSchool of Electronic and Optical Engineering, Nanjing University of Science and Technology, Nanjing 210094,  \nChina; [xuanheliu@njust.edu.cn](xuanheliu@njust.edu.cn) (X.L.); [chensi354@njust.edu.cn](chensi354@njust.edu.cn) (S.C.); [lijianchao@njust.edu.cn](lijianchao@njust.edu.cn) (J.L.);  \n[124104010614@njust.edu.cn](124104010614@njust.edu.cn) (Y.L.)  \n* Correspondence: [shuningzhangnjust@163.com](shuningzhangnjust@163.com)  \nHighlights  \nWhat are the main findings?  \n• This paper proposes a hierarchical local-global feature fusion model that integrates local structural features extracted by convolutional neural networks with global semantic dependencies modeled by Transformer architectures through a progressive multilayer self-attention mechanism.  \n• Extensive experiments on both the FUSAR dataset and a measured dataset demonstrate that the proposed model achieves superior classification accuracy and F1 scores compared with traditional CNNs, pure Transformer models, and representative recent vision architectures, while maintaining competitive inference efficiency. The model also exhibits strong robustness under low signal-to-noise ratios and limited sample conditions.  \nWhat are the implications of the main findings?  \n• Hierarchical encoding of local structural features and global contextual dependencies provides a novel approach for extracting vessel target features under complex sea conditions, enhancing the reliability of maritime target recognition.  \n• Transfer learning methods based on partial fine-tuning can efficiently adapt to limited labeled data, enabling rapid deployment of high-precision recognition systems in resource-constrained environments.  \nAbstract  \nAccurate ship target recognition remains challenging in complex maritime environments due to background clutter, multiscale target appearance, and limited discriminative features extracted by single-type networks. To address these issues, this paper proposes a hierarchical local-global feature fusion network (HLGF-Net) that integrates local structural cues from a CNN encoder with global semantic dependencies modeled by a Transformer. The proposed model progressively constructs hierarchical dependencies through stacked Transformer blocks, enabling comprehensive integration of local structural details and global semantic context. This design enhances the capability to capture fine-grained local contours and long-range global contextual relationships simultaneously. Extensive experiments on ship recognition datasets demonstrate that HLGF-Net achieves superior performance compared with traditional CNNs, pure Transformers, and representative recent vision architectures, particularly under conditions of cluttered backgrounds, partial occlusion, and limited target samples. The proposed framework provides an effective solution for robust maritime target recognition and offers a general strategy for hierarchical local-global feature integration.  \nKeywords: ship target recognition; local-global feature integration; hybrid model; self-attention representation; maritime scene analysis; limited sample learning  \n1. Introduction  \nMaritime target recognition plays a critical role in ocean surveillance, maritime security, and rescue missions [1,2] . However, accurate ship recognition remains challenging because sea clutter, originating from radar backscattering of the dynamic sea surface, often masks target echoes, while target appearanc","cbCaipLOdSJbseaa","https://ap.wps.com/l/cbCaipLOdSJbseaa","pdf",3260815,17,"English","# Highlights\n## Main findings\n## Implications of the main findings\n# Abstract\n# Keywords\n# 1. Introduction","[{\"question\":\"What core idea does HLGF-Net use for ship target recognition?\",\"answer\":\"HLGF-Net hierarchically fuses local structural cues from a CNN encoder with global semantic dependencies modeled by a Transformer using progressive stacked self-attention blocks.\"},{\"question\":\"What problems in complex maritime environments does the paper target?\",\"answer\":\"It addresses background clutter, multiscale target appearance, and limited discriminative features produced by single-type networks, which together hinder accurate recognition.\"},{\"question\":\"How does the proposed method perform compared with existing models?\",\"answer\":\"Experiments on ship recognition datasets show superior classification performance and F1 scores versus traditional CNNs, pure Transformers, and representative recent vision architectures, with strong robustness under low SNR and limited sample conditions.\"}]","Hierarchical Local-Global Feature Fusion Network for Robust Ship Target Recognition in Complex Maritime Environment | PDF",1790765325,43,[148,152,156,160],{"page_no":8,"url":149,"width":150,"height":151},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/2f255c2052a3e1a92f3d940065684ef7.webp",983,1390,{"page_no":14,"url":153,"width":154,"height":155},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/fd9a75a5fabbf4cf24d5b84661609fbd.webp",982,1388,{"page_no":81,"url":157,"width":158,"height":159},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/35fd5a254659ba84b459fa11979c49d1.webp",981,1387,{"page_no":19,"url":161,"width":162,"height":163},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/9c1551f4d567b02928fd757bb76b5861.webp",980,1385]