{"id":"https://openalex.org/W4414463945","doi":"https://doi.org/10.1109/bmsb65076.2025.11165699","title":"Generating Images to Enhance Situational Awareness in Nuclear Power Plants Through Caption-Assisted Computer Vision","display_name":"Generating Images to Enhance Situational Awareness in Nuclear Power Plants Through Caption-Assisted Computer Vision","publication_year":2025,"publication_date":"2025-06-11","ids":{"openalex":"https://openalex.org/W4414463945","doi":"https://doi.org/10.1109/bmsb65076.2025.11165699"},"language":"en","primary_location":{"id":"doi:10.1109/bmsb65076.2025.11165699","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bmsb65076.2025.11165699","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB)","raw_type":"proceedings-article"},"type":"article","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/A5101295729","display_name":"Yutao Jin","orcid":"https://orcid.org/0009-0004-9189-2258"},"institutions":[{"id":"https://openalex.org/I132369690","display_name":"Tianjin University of Science and Technology","ror":"https://ror.org/018rbtf37","country_code":"CN","type":"education","lineage":["https://openalex.org/I132369690"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yutao Jin","raw_affiliation_strings":["Tianjin University of Science and Technology,Tianjin,China"],"affiliations":[{"raw_affiliation_string":"Tianjin University of Science and Technology,Tianjin,China","institution_ids":["https://openalex.org/I132369690"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065225723","display_name":"Mingjun Zhou","orcid":"https://orcid.org/0000-0001-8261-6949"},"institutions":[{"id":"https://openalex.org/I4210099297","display_name":"Jilian Technology Group (China)","ror":"https://ror.org/016q5ce10","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210099297"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingjun Zhou","raw_affiliation_strings":["Beiiing JJC Technology Co., Ltd,Tianjin,China"],"affiliations":[{"raw_affiliation_string":"Beiiing JJC Technology Co., Ltd,Tianjin,China","institution_ids":["https://openalex.org/I4210099297"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033578245","display_name":"Jie Jiang","orcid":"https://orcid.org/0000-0002-5831-7268"},"institutions":[{"id":"https://openalex.org/I132369690","display_name":"Tianjin University of Science and Technology","ror":"https://ror.org/018rbtf37","country_code":"CN","type":"education","lineage":["https://openalex.org/I132369690"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Jiang","raw_affiliation_strings":["Tianjin University of Science and Technology,Tianjin,China"],"affiliations":[{"raw_affiliation_string":"Tianjin University of Science and Technology,Tianjin,China","institution_ids":["https://openalex.org/I132369690"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068303462","display_name":"Wenxu Wu","orcid":"https://orcid.org/0009-0002-9622-3665"},"institutions":[{"id":"https://openalex.org/I198091727","display_name":"Tianjin Polytechnic University","ror":"https://ror.org/00xsr9m91","country_code":"CN","type":"education","lineage":["https://openalex.org/I198091727"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenxu Wu","raw_affiliation_strings":["Tiangong University,School of Electrical and Information Engineering,Tianjin,China"],"affiliations":[{"raw_affiliation_string":"Tiangong University,School of Electrical and Information Engineering,Tianjin,China","institution_ids":["https://openalex.org/I198091727"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101295729"],"corresponding_institution_ids":["https://openalex.org/I132369690"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28566962,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13715","display_name":"Power Line Inspection Robots","score":0.982200026512146,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13715","display_name":"Power Line Inspection Robots","score":0.982200026512146,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical Engineering"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9763000011444092,"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/T12597","display_name":"Fire Detection and Safety Systems","score":0.9200999736785889,"subfield":{"id":"https://openalex.org/subfields/2213","display_name":"Safety, Risk, Reliability and Quality"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.52920001745224},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.48339998722076416},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.444599986076355},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.43380001187324524},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4154999852180481},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.38499999046325684},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.36719998717308044},{"id":"https://openalex.org/keywords/automatic-image-annotation","display_name":"Automatic image annotation","score":0.3594000041484833},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.35569998621940613},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.3400999903678894}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7336999773979187},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6844000220298767},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.52920001745224},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.48429998755455017},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.48339998722076416},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.444599986076355},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.43380001187324524},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4154999852180481},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.38499999046325684},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.36719998717308044},{"id":"https://openalex.org/C199579030","wikidata":"https://www.wikidata.org/wiki/Q2851778","display_name":"Automatic image annotation","level":4,"score":0.3594000041484833},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.35569998621940613},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34060001373291016},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.3400999903678894},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.3386000096797943},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.33500000834465027},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3285999894142151},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.32249999046325684},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.321399986743927},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3188999891281128},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.3131999969482422},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.30820000171661377},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.30149999260902405},{"id":"https://openalex.org/C145804949","wikidata":"https://www.wikidata.org/wiki/Q478123","display_name":"Situation awareness","level":2,"score":0.2928999960422516},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.29109999537467957},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.2854999899864197},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.28360000252723694},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2831000089645386},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.2806999981403351},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27810001373291016},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.26179999113082886},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.2615000009536743},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.26100000739097595},{"id":"https://openalex.org/C2776429412","wikidata":"https://www.wikidata.org/wiki/Q4688011","display_name":"Aerial image","level":3,"score":0.259799987077713},{"id":"https://openalex.org/C79106606","wikidata":"https://www.wikidata.org/wiki/Q735197","display_name":"Afterimage","level":3,"score":0.257999986410141},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.257099986076355},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.2531000077724457}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bmsb65076.2025.11165699","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bmsb65076.2025.11165699","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB)","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":11,"referenced_works":["https://openalex.org/W2093593565","https://openalex.org/W2106231349","https://openalex.org/W2539046007","https://openalex.org/W2949380861","https://openalex.org/W2963163163","https://openalex.org/W2963966654","https://openalex.org/W2964024144","https://openalex.org/W3006729919","https://openalex.org/W3198513953","https://openalex.org/W4321512706","https://openalex.org/W4388037665"],"related_works":[],"abstract_inverted_index":{"Artificial":[0],"intelligence":[1],"has":[2],"made":[3],"tremendous":[4],"strides":[5],"in":[6,49,163],"computer":[7],"vision":[8],"and":[9,138,147,186],"natural":[10,50,194],"language":[11],"processing,":[12],"enabling":[13],"new":[14,58,115],"multimodal":[15,25,180],"systems":[16],"to":[17,29,78,86,143,189],"fuse":[18],"these":[19],"capabilities.":[20],"This":[21,176],"study":[22],"proposes":[23],"a":[24,55,71,114,179,203],"deep":[26,181],"learning":[27,182],"model":[28,39,74],"augment":[30],"images":[31,108,167],"based":[32],"on":[33],"descriptive":[34,164],"textual":[35,63,145,174],"prompts.":[36],"Specifically,":[37],"the":[38,61,73,80,83,87,95,118,128,144,156],"takes":[40],"as":[41,109],"input":[42,137],"an":[43,68],"image":[44,59,69,116,160,191],"along":[45],"with":[46,170],"constraints":[47,121],"expressed":[48],"language.":[51,165,195],"It":[52,111],"then":[53,112],"generates":[54],"visually":[56,168],"similar":[57,106],"incorporating":[60],"specified":[62],"modifications.":[64],"For":[65],"instance,":[66],"given":[67],"of":[70,158,205],"train,":[72],"could":[75],"be":[76],"instructed":[77],"alter":[79],"background":[81],"outside":[82],"carriage":[84],"windows":[85],"night":[88],"sky.":[89],"To":[90,126],"achieve":[91],"this,":[92],"we":[93,130],"introduce":[94],"Text-based":[96],"Image":[97],"Refinement":[98],"Generator":[99],"(TIRG)":[100],"algorithm.":[101],"TIRG":[102,153],"first":[103],"retrieves":[104],"semantically":[105],"existing":[107],"references.":[110],"synthesizes":[113],"integrating":[117],"provided":[119],"text":[120],"utilizing":[122],"generative":[123],"adversarial":[124],"networks.":[125],"evaluate":[127],"model,":[129],"assess":[131],"key":[132],"metrics":[133],"including":[134],"similarity":[135],"between":[136],"output":[139],"images,":[140],"accuracy":[141],"adhering":[142],"modifications,":[146],"generation":[148],"speed.":[149],"Preliminary":[150],"results":[151],"indicate":[152],"capably":[154],"fulfills":[155],"aim":[157],"content-aware":[159],"enhancement":[161,206],"grounded":[162],"Output":[166],"align":[169],"inputs":[171],"while":[172],"reflecting":[173],"specifications.":[175],"work":[177],"presents":[178],"approach":[183],"tying":[184],"visual":[185],"linguistic":[187],"modalities":[188],"enrich":[190],"content":[192],"through":[193],"The":[196],"proposed":[197],"algorithm":[198],"demonstrates":[199],"promising":[200],"potential":[201],"for":[202],"variety":[204],"applications.":[207]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}