[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-327298-105":59,"doc-detail-327298-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","multi-modal-rail-crossing-safety-analysis","Multi-modal Rail Crossing Safety Analysis","","Given one or more images of a railway crossing, the work evaluates how visual cues can estimate safety reliably and whether adding structured information—such as official accident reports—improves the prediction. The proposed multimodal pipeline targets safety scoring that aligns with expert judgment and Federal Railroad Administration (FRA) safety scoring. Results identify HIGH-RISK and LOW-RISK crossings with a macro F1 of 0.757 and estimate FRA safety scores with RMSE 0.078 and correlation 0.492 using a routed fine-tuned compact VLM approach, producing qualitative agreement with domain experts.",{"@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/multi-modal-rail-crossing-safety-analysis/327298/",{"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/multi-modal-rail-crossing-safety-analysis/327298.png","ImageObject",300,407,{"name":92,"@type":93},"Olivia Brown","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-04","2026-09-21",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",11,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"How does the study use images to assess railway crossing safety?","Question",{"text":113,"@type":114},"It investigates visual cues from one or more images to robustly estimate how safe a crossing is, aiming to support AI-driven safety assessment.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"What role do structured data like accident reports play in the models?",{"text":118,"@type":114},"Structured data about a crossing’s accident history is introduced to improve predictions beyond what visual cues alone can provide, aligning outputs with expert and FRA scoring.",{"name":120,"@type":111,"acceptedAnswer":121},"What performance does the proposed system achieve?",{"text":122,"@type":114},"It reports macro F1 of 0.757 for identifying HIGH-RISK vs LOW-RISK crossings, and FRA-based safety score estimates with RMSE 0.078 and correlation 0.492 using a routed fine-tuned compact vision-language model pipeline.","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},327298,1791152926,{"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":39,"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":46,"preview_page_count":4},16904993612988,"https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd","Multi-modal Rail Crossing Safety Analysis  \nPaimon Goulart∗ University of California, Riverside Riverside, California, USA  \nChansong Lim∗ University of California, Riverside Riverside, California, USA  \nNícolas Roque dos Santos∗ University of California, Riverside Riverside, California, USA  \nYue Dong  \nUniversity of California, Riverside Riverside, California, USA  \nSheldon Peterson  \nRiverside County Transportation Commission Riverside, California, USA  \nJia Chen  \nUniversity of California, Riverside Riverside, California, USA  \narXiv :2607 .0 1365v 1 [ cs .LG] 1 Jul 2026  \nEvangelos E. Papalexakis  \nUniversity of California, Riverside Riverside, California, USA  \nAbstract  \nGiven one or more images of a railway crossing, can we leverage visual cues that allow us to robustly estimate how safe it is? Can we improve our ability to do so by introducing structured data (such as official accident reports) about the accident history of that crossing into our models? In this work, we explore how to best answer those questions towards building an AI system that can ingest multimodal data for railway crossings and provide safety assessment and scores that align with expert opinion and with safety scoring used by the Federal Railroad Administration (FRA) . To that end, we propose a proof-of-concept pipeline that delivers on that goal, while at the same time exploring and tackling a number of critical research challenges that pertain to different parts of the pipeline, from data preparation to different learning paradigms that can allow us to realize such a system. Indicatively, our proposed system identifies HIGH-RISK and LOW-RISK crossings with a macro F1 score of 0.757 and estimates FRA-based safety scores with an RMSE of 0.078 and correlation of 0.492 using a routed fine-tuned compact VLM pipeline, while producing qualitative results that align with domain-expert assessment.  \nCCS Concepts  \n• Computing methodologies → Scene understanding; Machine learning; • Applied computing → Transportation.  \nKeywords  \nRailway Crossing Safety, Intelligent Transportation Systems, Vision Language Models  \n∗ Three authors contributed equally to this research.  \nPermission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission [and/or a fee. Request permissions from permissions@acm.org](and/or a fee. Request permissions from permissions@acm.org).  \nConference acronym ’XX, Woodstock, NY  \n© 2018 Copyright held by the owner/author(s) . Publication rights licensed to ACM. ACM ISBN 978-1-4503-XXXX-X/2018/06  \n[https://doi.org/XXXXXXX.XXXXXXX](https://doi.org/XXXXXXX.XXXXXXX)  \nACM Reference Format:  \nPaimon Goulart, Chansong Lim, Nícolas Roque dos Santos, Yue Dong, Sheldon Peterson, Jia Chen, and Evangelos E. Papalexakis. 2018. Multi-modal Rail Crossing Safety Analysis. In Proceedings of Make sure to enter the correct conference title from your rights confirmation email (Conference acronym ’XX) . ACM, New York, NY, USA, 8 pages. [https://doi.org/XXXXXXX.XXXXXXX](https://doi.org/XXXXXXX.XXXXXXX)  \n1 Introduction  \nHighway–rail grade crossings are a critical safety concern in United States transportation systems. Each year, more than 2,000 collisionsand over 200 fatalities occur at these crossings, making them the second leading cause of rail-related deaths nationally [6]. Therefore, improving crossing safety requires reliable ways to assess risk and prioritize interventions. However, this is challenging because crossing risk depends on multiple interacting factors, including railway traffic, roadway ","cbCaimTi2BvJZ8aA","https://ap.wps.com/l/cbCaimTi2BvJZ8aA","pdf",21609920,"English","# Abstract\n# CCS Concepts\n# Keywords\n# 1 Introduction","[{\"question\":\"How does the study use images to assess railway crossing safety?\",\"answer\":\"It investigates visual cues from one or more images to robustly estimate how safe a crossing is, aiming to support AI-driven safety assessment.\"},{\"question\":\"What role do structured data like accident reports play in the models?\",\"answer\":\"Structured data about a crossing’s accident history is introduced to improve predictions beyond what visual cues alone can provide, aligning outputs with expert and FRA scoring.\"},{\"question\":\"What performance does the proposed system achieve?\",\"answer\":\"It reports macro F1 of 0.757 for identifying HIGH-RISK vs LOW-RISK crossings, and FRA-based safety score estimates with RMSE 0.078 and correlation 0.492 using a routed fine-tuned compact vision-language model pipeline.\"}]","Multi-modal Rail Crossing Safety Analysis | PDF",1789976934]