[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-327166-105":59,"doc-detail-327166-en":130},{"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":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","partial-skeleton-visibility-for-action-recognition-a-constrained-field-of-view-approach","Partial Skeleton Visibility for Action Recognition - A Constrained Field-of-View Approach","","Skeleton-based action recognition leverages joint coordinates and their topology, but most methods rely on complete, clean skeleton inputs. In constrained field-of-view scenarios—such as egocentric vision, crowded surveillance, wearable sensing, and edge robotics—joint visibility dropout causes major performance collapse. The work presents PartialVisGraph, a hypergraph framework with learnable virtual hyperedges and a visibility-prior gated transformer to prevent occluded joints from corrupting propagation. Experiments on NTU RGB+D 60/120 validate robust gains under realistic FoV simulation.",{"@graph":69,"@context":122},[70,84,105],{"@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/partial-skeleton-visibility-for-action-recognition-a-constrained-field-of-view-approach/327166/",{"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/partial-skeleton-visibility-for-action-recognition-a-constrained-field-of-view-approach/327166.png","ImageObject",300,407,{"name":92,"@type":93},"Anda","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-09","2026-09-21",true,{"@type":102,"interactionType":103,"userInteractionCount":52},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What problem does the paper address in skeleton-based action recognition?","Question",{"text":112,"@type":113},"It addresses performance degradation when constrained field-of-view causes substantial joint visibility dropout, making common complete-skeleton assumptions unreliable in real deployments.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How does PartialVisGraph model higher-order joint relationships?",{"text":117,"@type":113},"It constructs expressive hypergraphs using learnable virtual hyperedges, enabling a soft incidence matrix that captures flexible high-order dependencies beyond pairwise graphs.",{"name":119,"@type":110,"acceptedAnswer":120},"What role does the visibility prior play in the proposed transformer?",{"text":121,"@type":113},"The visibility prior selectively gates information flow so that occluded or out-of-view joints do not corrupt reliable feature propagation for action prediction.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},327166,1790783232,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":52,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":144,"read_time":145,"preview_page_count":4},962075006959,"https://ap-avatar.wpscdn.com/avatar/e0002397efbe92a78e?_k=1776741047341049297","arXiv :2607 .007 16v 1 [ cs .CV] 1 Jul 2026  \nPartial Skeleton Visibility for Action Recognition: A Constrained Field-of-View Approach  \nYingjie Dai 1, Tianyang Xu 1 ⋆, Yanglin Deng 1, Xiao-Jun Wu 1, and Josef Kittler2  \n1 Jiangnan University, Wuxi, China  \n2 University of Surrey, Guildford, UK [daiyingjie2024@gmail.com](daiyingjie2024@gmail.com) ; {tianyang.xu,[wu_xiaojun}@jiangnan.edu.cn](wu_xiaojun}@jiangnan.edu.cn) ;  \n[yanglin_deng@163.com](yanglin_deng@163.com) ; [j.kittler@surrey.ac.uk](j.kittler@surrey.ac.uk) ;  \nAbstract. Skeleton-based action recognition has achieved remarkable success by exploiting joint coordinates and their topological connections, yet prevailing methods overwhelmingly assume complete and clean skeleton inputs. In real-world deployments, such as egocentric vision, crowded surveillance, wearable devices, or edge robotics, limited field-ofview (FoV) frequently causes substantial joint visibility dropout, leading to severe performance degradation that existing models are largely unprepared to handle. To bridge this critical yet underexplored gap, we introduce PartialVisGraph, a novel hypergraph framework tailored for robust skeleton action recognition under constrained FoV. We first construct highly expressive hypergraphs by introducing learnable virtual hyperedges that form a soft incidence matrix, capturing flexible highorder dependencies beyond conventional pairwise graphs. We then propose the Single-Head Sample-Adaptive Transformer, which adaptively aggregates joint features onto hyperedges while explicitly incorporating a visibility prior. This prior selectively gates information flow, preventing occluded or out-of-view joints from corrupting reliable feature propagation. We further establish rigorous evaluation protocols with realistic FoV simulation benchmarks on NTU RGB+D 60 and 120 . Extensive experiments demonstrate that PartialVisGraph consistently achieves stateof-the-art accuracy under partial visibility, with gains of up to 68.8% on subsets with severe FoV restrictions compared to recent strong baselines, while remaining superior on full-visibility settings. Our approach offers a principled and practical pathway toward deployable skeletonbased action understanding in unconstrained environments. Resources related to the constrained FoV setting used in this work are available at:  \n[https://github.com/yaa1haa1/PartialVisGraph](https://github.com/yaa1haa1/PartialVisGraph).  \nKeywords: Skeleton-based Action Recognition · Constrained Field of View · Hypergraph  \n2 Y. Dai et al.  \n\n| Full\u003Cbr>field-of-view | |  |  | \"falling down\"\u003Cbr>| \"kicking something\" |  |  |  |\n| --- | --- | --- | --- | --- | --- | --- | --- | --- |\n|  |  |  |  |  | | | | |\n|  |  |  |  | \"falling down\" | \"kicking something\" |  |  |  |\n\nConstrained field-of-view  \nFig. 1: Skeleton-based action recognition under constrained field-of-view. The dashed box indicates the restricted visible region, and joints whose features in the final layer contribute most to the model’s prediction are highlighted in red.  \n1 Introduction  \nRecently, skeleton-based human action recognition [5, 29, 31, 38, 47, 52, 53] has demonstrated significant potential across a wide range of applications, including medical rehabilitation, virtual reality, intelligent surveillance, and autonomous driving. By representing human motion through joints and their topological structure, skeleton sequences provide a structured and geometry-aware description of body dynamics. This representation directly captures the kinematic relationships among joints and the temporal evolution of movements. Owing to its abstraction from appearance, skeleton data is inherently more robust to complex backgrounds, illumination variations, and viewpoint changes. Meanwhile, its compact and low-dimensional structure substantially reduces computational overhead. With the continuous advancement of depth sensors and 3D pose estimation algorithms [2, 11, 17, 26, 28], the accuracy and stabi","cbCaiuMlqUF9DK0k","https://ap.wps.com/l/cbCaiuMlqUF9DK0k","pdf",887598,18,"English","# Abstract\n# Introduction\n## Skeleton-based action recognition and deployment challenges\n## Normal graph modeling vs higher-order dependencies\n## Constrained FoV motivation and proposed direction","[{\"question\":\"What problem does the paper address in skeleton-based action recognition?\",\"answer\":\"It addresses performance degradation when constrained field-of-view causes substantial joint visibility dropout, making common complete-skeleton assumptions unreliable in real deployments.\"},{\"question\":\"How does PartialVisGraph model higher-order joint relationships?\",\"answer\":\"It constructs expressive hypergraphs using learnable virtual hyperedges, enabling a soft incidence matrix that captures flexible high-order dependencies beyond pairwise graphs.\"},{\"question\":\"What role does the visibility prior play in the proposed transformer?\",\"answer\":\"The visibility prior selectively gates information flow so that occluded or out-of-view joints do not corrupt reliable feature propagation for action prediction.\"}]","Partial Skeleton Visibility for Action Recognition - A Constrained Field-of-View Approach | PDF",1789976580,45]