{"id":"https://openalex.org/W7154965062","doi":"https://doi.org/10.1109/access.2026.3685213","title":"CaptionPS: Benchmarking and Analyzing Worker-Centric Detailed Image Captioning in Power Scenarios","display_name":"CaptionPS: Benchmarking and Analyzing Worker-Centric Detailed Image Captioning in Power Scenarios","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7154965062","doi":"https://doi.org/10.1109/access.2026.3685213"},"language":"en","primary_location":{"id":"doi:10.1109/access.2026.3685213","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3685213","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3685213","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134026363","display_name":"Zixiang Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I17442442","display_name":"State Grid Corporation of China (China)","ror":"https://ror.org/05twwhs70","country_code":"CN","type":"company","lineage":["https://openalex.org/I17442442"]},{"id":"https://openalex.org/I4210126065","display_name":"Shanghai Electric (China)","ror":"https://ror.org/0314qy595","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210126065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zixiang Wang","raw_affiliation_strings":["State Grid Zhejiang Electric Power Company Ltd., Research Institute, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Grid Zhejiang Electric Power Company Ltd., Research Institute, Zhejiang, China","institution_ids":["https://openalex.org/I17442442","https://openalex.org/I4210126065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134039796","display_name":"Xin Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I17442442","display_name":"State Grid Corporation of China (China)","ror":"https://ror.org/05twwhs70","country_code":"CN","type":"company","lineage":["https://openalex.org/I17442442"]},{"id":"https://openalex.org/I4210126065","display_name":"Shanghai Electric (China)","ror":"https://ror.org/0314qy595","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210126065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Chen","raw_affiliation_strings":["State Grid Zhejiang Electric Power Company Ltd., Research Institute, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Grid Zhejiang Electric Power Company Ltd., Research Institute, Zhejiang, China","institution_ids":["https://openalex.org/I17442442","https://openalex.org/I4210126065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134039255","display_name":"Jiajia Han","orcid":null},"institutions":[{"id":"https://openalex.org/I17442442","display_name":"State Grid Corporation of China (China)","ror":"https://ror.org/05twwhs70","country_code":"CN","type":"company","lineage":["https://openalex.org/I17442442"]},{"id":"https://openalex.org/I4210126065","display_name":"Shanghai Electric (China)","ror":"https://ror.org/0314qy595","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210126065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiajia Han","raw_affiliation_strings":["State Grid Zhejiang Electric Power Company Ltd., Research Institute, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Grid Zhejiang Electric Power Company Ltd., Research Institute, Zhejiang, China","institution_ids":["https://openalex.org/I17442442","https://openalex.org/I4210126065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064225064","display_name":"Junyu Cai","orcid":"https://orcid.org/0000-0003-4850-4374"},"institutions":[{"id":"https://openalex.org/I17442442","display_name":"State Grid Corporation of China (China)","ror":"https://ror.org/05twwhs70","country_code":"CN","type":"company","lineage":["https://openalex.org/I17442442"]},{"id":"https://openalex.org/I4210126065","display_name":"Shanghai Electric (China)","ror":"https://ror.org/0314qy595","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210126065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junyu Cai","raw_affiliation_strings":["State Grid Zhejiang Electric Power Company Ltd., Research Institute, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0003-4850-4374","affiliations":[{"raw_affiliation_string":"State Grid Zhejiang Electric Power Company Ltd., Research Institute, Zhejiang, China","institution_ids":["https://openalex.org/I17442442","https://openalex.org/I4210126065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045933207","display_name":"S Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuangchen Wang","raw_affiliation_strings":["Zhejiang University, Zhejiang, China"],"raw_orcid":"https://orcid.org/0009-0000-7649-4930","affiliations":[{"raw_affiliation_string":"Zhejiang University, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081987954","display_name":"Junjie Huang","orcid":"https://orcid.org/0000-0003-2382-4443"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junjie Huang","raw_affiliation_strings":["Zhejiang University, Zhejiang, China"],"raw_orcid":"https://orcid.org/0009-0009-2663-0848","affiliations":[{"raw_affiliation_string":"Zhejiang University, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.49763603,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"97432","last_page":"97452"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.989300012588501,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.989300012588501,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.002199999988079071,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13310","display_name":"Subtitles and Audiovisual Media","score":0.0012000000569969416,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.9214000105857849},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.8406000137329102},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.5350000262260437},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5329999923706055},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3357999920845032}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9214000105857849},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.8406000137329102},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8374999761581421},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.5350000262260437},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5329999923706055},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4259999990463257},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3400000035762787},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3357999920845032},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.3181000053882599},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3122999966144562},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.26820001006126404},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2547999918460846}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2026.3685213","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3685213","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:d4bd75e74c7c4c349a12753ba6d59160","is_oa":false,"landing_page_url":"https://doaj.org/article/d4bd75e74c7c4c349a12753ba6d59160","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 14, Pp 97432-97452 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3685213","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3685213","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G756766449","display_name":null,"funder_award_id":"B311DS240012","funder_id":"https://openalex.org/F4320336311","funder_display_name":"State Grid Zhejiang Electric Power Company"}],"funders":[{"id":"https://openalex.org/F4320336311","display_name":"State Grid Zhejiang Electric Power Company","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Image":[0],"captioning":[1],"has":[2,142],"long":[3],"been":[4,143],"a":[5,70,117],"persistent":[6],"challenge":[7],"in":[8,30,52,206],"the":[9,15,84,87,91,94,99,102,108,136,147,152,163,190],"field":[10],"of":[11,17,76,86,93,101,104,110,119,139,189],"vision-language":[12],"research.":[13],"With":[14],"rise":[16],"Large":[18],"Language":[19],"Models":[20,24],"(LLMs),":[21],"modern":[22],"Vision-Language":[23],"(VLMs)":[25],"can":[26],"produce":[27],"effective":[28],"captions":[29],"general-purpose":[31],"scenarios.":[32,208],"However,":[33,132],"when":[34],"confronted":[35],"with":[36,73,174],"complex":[37],"power":[38,207],"safety":[39,53,103,109,170],"violation":[40,46,64,88,200],"scenarios,":[41],"they":[42],"often":[43],"omit":[44],"critical":[45],"details,":[47],"greatly":[48],"limiting":[49],"their":[50],"reliability":[51],"supervision.":[54],"Therefore,":[55],"we":[56],"propose":[57],"CaptionPS,":[58,114],"an":[59],"image-captioning":[60],"dataset":[61],"tailored":[62],"for":[63],"detection.":[65],"CaptionPS":[66,195],"is":[67],"constructed":[68],"through":[69],"systematic":[71],"pipeline":[72],"multiple":[74],"rounds":[75],"manual":[77],"annotation.":[78],"Each":[79],"sample":[80],"includes":[81],"not":[82],"only":[83],"classification":[85,168],"scene":[89,167,204],"and":[90,160,169,179,184,202],"description":[92],"image":[95],"content,":[96],"but":[97],"also":[98],"prediction":[100,171],"subsequent":[105],"behaviors,":[106],"ensuring":[107],"workers.":[111],"Based":[112],"on":[113,155,166],"We":[115],"evaluate":[116],"suite":[118],"VLMs.":[120],"Experimental":[121],"results":[122],"show":[123],"that":[124],"open-source":[125],"pretrained":[126],"models":[127,141],"generally":[128],"exhibit":[129],"low":[130],"performance.":[131],"after":[133],"supervised":[134],"fine-tuning,":[135],"overall":[137],"performance":[138,154,165],"all":[140],"significantly":[144],"improved.":[145],"Among":[146],"evaluated":[148],"models,":[149],"InternVL3.5-8B":[150,159],"achieves":[151],"highest":[153],"detailed":[156],"captioning.":[157],"Meanwhile,":[158],"Llama-3.2-11B":[161],"achieve":[162],"best":[164],"tasks,":[172],"respectively,":[173],"accuracy":[175],"rates":[176],"reaching":[177],"87.32%":[178],"78.51%,":[180],"which":[181],"are":[182],"48.47%":[183],"45.66%":[185],"higher":[186],"than":[187],"those":[188],"baseline":[191],"models.":[192],"The":[193],"proposed":[194],"helps":[196],"MLLMs":[197],"better":[198],"learn":[199],"characteristics":[201],"improve":[203],"recognition":[205]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-04-21T00:00:00"}