[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-515936-105":3,"doc-detail-515936-en":81,"detail-sidebar-cat-0-en-105":116},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","graph-based-humanobject-interaction-detection-for-automated-worker-accountability-monitoring-on-construction-sites","Graph-Based Human–Object Interaction Detection for Automated Worker Accountability Monitoring on Construction Sites","","Effectively monitoring worker accountability in construction project controls requires addressing complex, dynamic interactions between workers and objects. The study proposes a graph-based HOI detection framework using convolutional neural networks and graph attention networks to link workers with specific objects and actions. It recognizes key worker actions (e.g., tying, transporting, pouring) and includes noninteractive behaviors for a comprehensive site view across object categories and sizes. Results show robust detection performance and enable worker, object, and action data for productivity monitoring, quality control, and safety inspections.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/graph-based-humanobject-interaction-detection-for-automated-worker-accountability-monitoring-on-construction-sites/515936/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/graph-based-humanobject-interaction-detection-for-automated-worker-accountability-monitoring-on-construction-sites/515936.png","ImageObject",300,407,{"name":42,"@type":43},"Stanley","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-11-15","2026-10-06",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",6,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What problem does the automated worker accountability monitoring (WAM) approach address?","Question",{"text":63,"@type":64},"It addresses the need to monitor worker accountability in construction controls by capturing complex, dynamic worker–object interactions rather than only limited single-action or single-scale interactions.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"How does the proposed framework detect human–object interactions?",{"text":68,"@type":64},"It leverages convolutional neural networks and graph attention networks to produce robust worker accountability monitoring while recognizing both interactive actions and noninteractive behaviors with spatial context.",{"name":70,"@type":61,"acceptedAnswer":71},"What data outputs does the WAM system support for construction project controls?",{"text":72,"@type":64},"It generates worker, object, and action information that supports productivity monitoring, quality control, and safety inspections, and helps generate detailed daily construction reports.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},515936,1791419631,{"code":4,"msg":82,"data":83},"success",{"doc_id":79,"user_id":84,"nickname":42,"user_avatar":85,"doc_module":4,"category_id":86,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":87,"file_id":88,"file_url":89,"file_type":90,"file_size":91,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":92,"language":93,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":94,"faqs":95,"seo_title":96,"seo_description":12,"update_tm":97,"read_time":98,"preview_page_count":33,"preview_urls":99},2336477405376,"https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Copyright ASCE; all rights reserved, including rights for text and data mining and training of artificial intelligence or similar technologies .  \nGraph-Based Human–Object Interaction  \nDetection for Automated Worker Accountability Monitoring on Construction Sites  \nMik Wanul Khosiin 1 ; Jacob J. Lin, Ph. D. , Aff. M.ASCE 2 ; Eko Andi Suryo, Ph. D.3 ; Kartika Puspa Negara, Ph. D.4 ; Ismiarta Aknuranda, Ph. D.5 ; and Chuin-Shan Chen, Ph. D.6  \n\n| Abstract: Effectively monitoring worker accountability in construction project controls requires addressing the complex, dynamic interactions between workers and objects. However, existing human–object interaction (HOI) approaches are typically limited to single actions and single-scale object sizes, lack spatial context, and overlook how large slab structures require distinguishing between local interaction areas (local objects) and broader object zones (global objects) . To overcome these challenges, this study proposes a comprehensive HOI detection framework that leverages convolutional neural networks and graph attention networks to generate a robust worker accountability monitoring (WAM) system. The research identifies various worker actions, such as tying, transporting, and pouring, as key performance indicators, while also capturing noninteractive behaviors to provide a comprehensive view of on-site activity. Objects are grouped into three categories—concrete, formwork, and steel rebar—and analyzed across three object sizes: big, medium, and small. Additionally, the bounding box design of the objects incorporates both local and global scenarios, which consider the area of the associated objects. The system achieves notable performance, with a mean average precision (mAP) of 0.830 for object detection and mAP scores of 0.553 and 0.502 for HOI tasks involving human interactions in local and global contexts, respectively. These results demonstrate accurate detection and action recognition across diverse scenarios. The WAM system generates essential data: worker, object, and action information supporting holistic project management systems, including productivity monitoring, quality control, and safety inspections. By enabling managers to better understand worker interactions and crew activities on construction sites, this approach provides actionable insights to enhance future performance. DOI: 10.1061/JCCEE5.CPENG-7157. © 2026 American Society of Civil Engineers.\u003Cbr>Practical Applications: This study presents two practical applications that directly support construction project controls. First, it leverages human–object interaction detection to monitor multiple worker–object interactions simultaneously, enabling accurate worker accountability monitoring (WAM) . By identifying which workers are engaging with which objects and where, the system enhances transparency and accountability on site. This helps construction managers track labor more effectively, assess progress in real time, and trace quality or safety issues back to specific actions or individuals. Second, the system can detect multiple workers along with a wide range of object sizes (large, medium, and small) and spatial scopes (local interaction areas and global work zones) in a single frame. This capability allows for the automatic generation of detailed daily construction reports, capturing key operational information without relying on manual documentation. It reduces reporting errors, saves time, and supports better decision-making regarding resource allocation and productivity analysis. Together, these applications demonstrate how vision-based WAM systems can bridge the gap between visual data and construction project controls, offering a scalable and practical tool for enhancing site efficiency and management oversight. |  |\n| --- | --- |\n| Introduction | construction sites. A key aspect of this is understanding how work- |\n| Monitoring worker activities, scheduling progress, and safety compliance is critical for ","cbCaiiDxJ0AlmGZL","https://ap.wps.com/l/cbCaiiDxJ0AlmGZL","pdf",3930966,16,"English","# Abstract\n# Practical Applications\n# Introduction","[{\"question\":\"What problem does the automated worker accountability monitoring (WAM) approach address?\",\"answer\":\"It addresses the need to monitor worker accountability in construction controls by capturing complex, dynamic worker–object interactions rather than only limited single-action or single-scale interactions.\"},{\"question\":\"How does the proposed framework detect human–object interactions?\",\"answer\":\"It leverages convolutional neural networks and graph attention networks to produce robust worker accountability monitoring while recognizing both interactive actions and noninteractive behaviors with spatial context.\"},{\"question\":\"What data outputs does the WAM system support for construction project controls?\",\"answer\":\"It generates worker, object, and action information that supports productivity monitoring, quality control, and safety inspections, and helps generate detailed daily construction reports.\"}]","Graph-Based Human–Object Interaction Detection for Automated Worker Accountability Monitoring on Construction Sites | PDF",1791323703,40,[100,104,108,112],{"page_no":22,"url":101,"width":102,"height":103},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/449a87e123450ceede46a75494adefe1.webp",983,1272,{"page_no":26,"url":105,"width":106,"height":107},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/b76abb8ff412cf26192866f20859a288.webp",982,1270,{"page_no":30,"url":109,"width":110,"height":111},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/c1b97b7c6be6c966143afce20371ce20.webp",981,1269,{"page_no":33,"url":113,"width":114,"height":115},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/64d73e15c3c6dc640280a91b89880b5e.webp",980,1268,{"code":4,"msg":82,"data":117},[118,122,126,130,135,139,143,146,151,154,158],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":119,"show_sort_weight":120,"slug":121},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":123,"show_sort_weight":124,"slug":125},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":127,"show_sort_weight":128,"slug":129},"Exam",70,"exam",{"id":131,"doc_module":4,"doc_module_name":25,"category_name":132,"show_sort_weight":133,"slug":134},5,"Comic",60,"comic",{"id":55,"doc_module":4,"doc_module_name":25,"category_name":136,"show_sort_weight":137,"slug":138},"Technology",50,"technology",{"id":140,"doc_module":4,"doc_module_name":25,"category_name":141,"show_sort_weight":98,"slug":142},7,"Healthcare","healthcare",{"id":86,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":144,"slug":145},30,"research-report",{"id":147,"doc_module":4,"doc_module_name":25,"category_name":148,"show_sort_weight":149,"slug":150},9,"Religion & Spirituality",20,"religion-spirituality",{"id":149,"doc_module":4,"doc_module_name":25,"category_name":152,"show_sort_weight":149,"slug":153},"World Cup","world-cup",{"id":155,"doc_module":4,"doc_module_name":25,"category_name":156,"show_sort_weight":155,"slug":157},10,"Lifestyle","lifestyle",{"id":159,"doc_module":4,"doc_module_name":25,"category_name":160,"show_sort_weight":131,"slug":161},19,"General","general"]