{"id":"https://openalex.org/W7129334979","doi":"https://doi.org/10.1109/icipw68931.2025.11386061","title":"Optimizing Construction Safety: Multimodal Prompts For Automated Image Descriptions In Daily Construction Reports","display_name":"Optimizing Construction Safety: Multimodal Prompts For Automated Image Descriptions In Daily Construction Reports","publication_year":2025,"publication_date":"2025-09-14","ids":{"openalex":"https://openalex.org/W7129334979","doi":"https://doi.org/10.1109/icipw68931.2025.11386061"},"language":null,"primary_location":{"id":"doi:10.1109/icipw68931.2025.11386061","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icipw68931.2025.11386061","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Image Processing Workshops (ICIPW)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067715980","display_name":"Chia\u2010Hsuin Chang","orcid":"https://orcid.org/0000-0003-0024-6177"},"institutions":[{"id":"https://openalex.org/I75357094","display_name":"National Yunlin University of Science and Technology","ror":"https://ror.org/04qkq2m54","country_code":"TW","type":"education","lineage":["https://openalex.org/I75357094"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chuan-Yu Chang","raw_affiliation_strings":["National Yunlin University of Science and Technology,Intelligent Recognition Industry Service Research Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Yunlin University of Science and Technology,Intelligent Recognition Industry Service Research Center","institution_ids":["https://openalex.org/I75357094"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052884912","display_name":"Abida Khanum","orcid":null},"institutions":[{"id":"https://openalex.org/I75357094","display_name":"National Yunlin University of Science and Technology","ror":"https://ror.org/04qkq2m54","country_code":"TW","type":"education","lineage":["https://openalex.org/I75357094"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Abida Khanum","raw_affiliation_strings":["National Yunlin University of Science and Technology,Intelligent Recognition Industry Service Research Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Yunlin University of Science and Technology,Intelligent Recognition Industry Service Research Center","institution_ids":["https://openalex.org/I75357094"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113035456","display_name":"Sheng-Gui Su","orcid":null},"institutions":[{"id":"https://openalex.org/I75357094","display_name":"National Yunlin University of Science and Technology","ror":"https://ror.org/04qkq2m54","country_code":"TW","type":"education","lineage":["https://openalex.org/I75357094"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Sheng-Gui Su","raw_affiliation_strings":["National Yunlin University of Science and Technology,Intelligent Recognition Industry Service Research Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Yunlin University of Science and Technology,Intelligent Recognition Industry Service Research Center","institution_ids":["https://openalex.org/I75357094"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100875133","display_name":"Ming\u2010Hsiu Tsai","orcid":null},"institutions":[{"id":"https://openalex.org/I107470533","display_name":"Tamkang University","ror":"https://ror.org/04tft4718","country_code":"TW","type":"education","lineage":["https://openalex.org/I107470533"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ming-Hsiu Tsai","raw_affiliation_strings":["Tamkang University,Department of Civil Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tamkang University,Department of Civil Engineering","institution_ids":["https://openalex.org/I107470533"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126205770","display_name":"Hui-Huang Hsu","orcid":null},"institutions":[{"id":"https://openalex.org/I107470533","display_name":"Tamkang University","ror":"https://ror.org/04tft4718","country_code":"TW","type":"education","lineage":["https://openalex.org/I107470533"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hui-Huang Hsu","raw_affiliation_strings":["Tamkang University,Department of Computer Science Information Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tamkang University,Department of Computer Science Information Engineering","institution_ids":["https://openalex.org/I107470533"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126191691","display_name":"Wei-Ting Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I75357094","display_name":"National Yunlin University of Science and Technology","ror":"https://ror.org/04qkq2m54","country_code":"TW","type":"education","lineage":["https://openalex.org/I75357094"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Wei-Ting Chen","raw_affiliation_strings":["National Yunlin University of Science and Technology,Intelligent Recognition Industry Service Research Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Yunlin University of Science and Technology,Intelligent Recognition Industry Service Research Center","institution_ids":["https://openalex.org/I75357094"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048240971","display_name":"Hsiang\u2010Wei Lu","orcid":"https://orcid.org/0000-0003-4683-2438"},"institutions":[{"id":"https://openalex.org/I4210121820","display_name":"Taiwan Geographic Information Center","ror":"https://ror.org/02k7g3c43","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210121820"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsiang-Wei Lu","raw_affiliation_strings":["CECI Engineering Consultants, Inc,Building Information Modeling Center,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CECI Engineering Consultants, Inc,Building Information Modeling Center,Taiwan","institution_ids":["https://openalex.org/I4210121820"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"263","last_page":"268"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10809","display_name":"Occupational Health and Safety Research","score":0.8104000091552734,"subfield":{"id":"https://openalex.org/subfields/3614","display_name":"Radiological and Ultrasound Technology"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10809","display_name":"Occupational Health and Safety Research","score":0.8104000091552734,"subfield":{"id":"https://openalex.org/subfields/3614","display_name":"Radiological and Ultrasound Technology"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11006","display_name":"BIM and Construction Integration","score":0.12099999934434891,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10395","display_name":"Construction Project Management and Performance","score":0.013299999758601189,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6266999840736389},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.5932999849319458},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5277000069618225},{"id":"https://openalex.org/keywords/clarity","display_name":"CLARITY","score":0.45089998841285706},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4388999938964844},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4068000018596649},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.39730000495910645},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3716000020503998}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7437000274658203},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6266999840736389},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.5932999849319458},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5277000069618225},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5016000270843506},{"id":"https://openalex.org/C2777146004","wikidata":"https://www.wikidata.org/wiki/Q14949826","display_name":"CLARITY","level":2,"score":0.45089998841285706},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4388999938964844},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4068000018596649},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.39730000495910645},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3716000020503998},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33820000290870667},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3249000012874603},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.3133000135421753},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2921999990940094},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.29190000891685486},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28999999165534973},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2786000072956085},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C2777488183","wikidata":"https://www.wikidata.org/wiki/Q6900510","display_name":"Safety monitoring","level":2,"score":0.257999986410141},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.2556000053882599},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.2542000114917755},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icipw68931.2025.11386061","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icipw68931.2025.11386061","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Image Processing Workshops (ICIPW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W4293294953","https://openalex.org/W4399043766","https://openalex.org/W4399153128","https://openalex.org/W4400146581","https://openalex.org/W4404019936","https://openalex.org/W4404280355","https://openalex.org/W4404575436","https://openalex.org/W4404914726","https://openalex.org/W4405382136","https://openalex.org/W4407189925"],"related_works":[],"abstract_inverted_index":{"We":[0,214],"explore":[1],"the":[2,12,113,182],"potential":[3],"of":[4,14,115,223],"Multimodal":[5,89],"Large":[6],"Language":[7],"Models":[8],"(MLLMs)":[9],"that":[10,194],"combine":[11],"strengths":[13],"GPT,":[15],"LLaMA,":[16],"and":[17,27,38,58,71,77,128,163,184,188,200],"VLMs":[18],"to":[19,101,126],"handle":[20],"multimodal":[21,98,117,160],"inputs":[22],"such":[23],"as":[24],"text,":[25],"image,":[26],"more":[28],"in":[29,48,203],"various":[30],"natural":[31],"language":[32],"understanding":[33,122,157],"tasks.":[34],"Despite":[35],"advances,":[36],"managing":[37],"analyzing":[39],"images":[40,149],"from":[41,108,140,177],"construction":[42,49,109,133,211],"sites":[43],"remains":[44],"a":[45,75,96,151,159,171,178,207],"significant":[46],"challenge":[47],"projects.":[50],"Daily":[51,94],"site":[52,110,212],"monitoring":[53],"ensures":[54],"safety,":[55],"maintains":[56],"quality,":[57],"meets":[59],"regulatory":[60],"requirements.":[61],"Traditionally,":[62],"this":[63,82],"process":[64],"relies":[65],"on-site":[66],"managers":[67],"manually":[68],"capturing":[69],"photos":[70],"writing":[72],"daily":[73,105],"reports,":[74],"time-consuming":[76],"labor-intensive":[78],"task.":[79,227],"To":[80],"address":[81],"challenge,":[83],"we":[84],"proposed":[85],"CSMMP-Dr":[86,119,146,195],"(Construction":[87],"Safety":[88],"Monitoring":[90],"with":[91,123],"Prompts":[92],"for":[93,155,165,210],"Reporting),":[95],"novel":[97],"framework":[99,136],"designed":[100],"automatically":[102],"generate":[103],"comprehensive":[104],"safety":[106,130,204],"reports":[107],"images.":[111,190],"Using":[112],"capabilities":[114],"large":[116],"models,":[118],"combines":[120],"image":[121],"textual":[124,186],"generation":[125],"detect":[127],"describe":[129],"conditions":[131],"on":[132],"sites.":[134],"The":[135],"uses":[137],"real-world":[138],"data":[139],"CECI":[141],"Engineering":[142],"Consultants,":[143],"Inc.,":[144],"Taiwan.":[145],"processes":[147],"input":[148],"through":[150],"dual-branch":[152],"architecture:":[153],"one":[154],"scene":[156],"using":[158],"SafeSceneView":[161],"module":[162],"another":[164],"deep":[166],"visual":[167],"feature":[168],"extraction":[169],"via":[170],"Vision":[172],"Transformer.":[173],"Retrieved":[174],"contextual":[175],"information":[176],"visual-textual":[179],"database":[180],"enhances":[181],"prompt":[183],"produces":[185],"summaries":[187],"annotated":[189],"Experimental":[191],"results":[192],"demonstrate":[193],"significantly":[196],"reduces":[197],"reporting":[198],"workload":[199],"improves":[201],"clarity":[202],"monitoring,":[205],"offering":[206],"practical":[208],"solution":[209],"management.":[213],"processed":[215],"1,409":[216],"images,":[217],"achieving":[218],"an":[219],"average":[220],"inference":[221],"time":[222],"12":[224],"seconds":[225],"per":[226]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-02-18T00:00:00"}