{"id":"https://openalex.org/W4283809957","doi":"https://doi.org/10.1609/aaai.v36i11.21705","title":"Towards Multimodal Vision-Language Models Generating Non-generic Text","display_name":"Towards Multimodal Vision-Language Models Generating Non-generic Text","publication_year":2022,"publication_date":"2022-06-28","ids":{"openalex":"https://openalex.org/W4283809957","doi":"https://doi.org/10.1609/aaai.v36i11.21705"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v36i11.21705","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v36i11.21705","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/21705/21454","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/21705/21454","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089225887","display_name":"Wes Robbins","orcid":null},"institutions":[{"id":"https://openalex.org/I23732399","display_name":"Montana State University","ror":"https://ror.org/02w0trx84","country_code":"US","type":"education","lineage":["https://openalex.org/I23732399","https://openalex.org/I4210126032"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Wes Robbins","raw_affiliation_strings":["Montana State University"],"affiliations":[{"raw_affiliation_string":"Montana State University","institution_ids":["https://openalex.org/I23732399"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5089225887"],"corresponding_institution_ids":["https://openalex.org/I23732399"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04555825,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"11","first_page":"13138","last_page":"13139"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9973999857902527,"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":0.9973999857902527,"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":0.9508000016212463,"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"}},{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9409000277519226,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.8338156938552856},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8253072500228882},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6547770500183105},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.618144690990448},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5667679905891418},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5582002401351929},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5515576601028442},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.507335364818573},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4761738181114197},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.4739111661911011},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.43043583631515503},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3828539252281189}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8338156938552856},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8253072500228882},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6547770500183105},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.618144690990448},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5667679905891418},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5582002401351929},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5515576601028442},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.507335364818573},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4761738181114197},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.4739111661911011},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.43043583631515503},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3828539252281189},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v36i11.21705","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v36i11.21705","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/21705/21454","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v36i11.21705","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v36i11.21705","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/21705/21454","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4283809957.pdf","grobid_xml":"https://content.openalex.org/works/W4283809957.grobid-xml"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W2789636240","https://openalex.org/W2982834534","https://openalex.org/W3013137071","https://openalex.org/W3034336960","https://openalex.org/W3106859150"],"related_works":["https://openalex.org/W2547835662","https://openalex.org/W2971688299","https://openalex.org/W3020826863","https://openalex.org/W4284710034","https://openalex.org/W3041777105","https://openalex.org/W4368754908","https://openalex.org/W4221152473","https://openalex.org/W2359001871","https://openalex.org/W2951916837","https://openalex.org/W4312438583"],"abstract_inverted_index":{"While":[0],"text":[1,29,38,141],"generated":[2,48,140],"by":[3,142],"current":[4],"vision-language":[5,53],"models":[6,54,124],"may":[7],"be":[8],"accurate":[9],"and":[10,45,92,107],"syntactically":[11],"correct,":[12],"it":[13],"is":[14],"often":[15],"general.":[16],"Recent":[17],"work":[18],"has":[19],"used":[20],"optical":[21],"character":[22],"recognition":[23,137],"to":[24,69,98],"supplement":[25],"visual":[26],"information":[27,59,72],"with":[28,101,125],"extracted":[30,60],"from":[31,57,61,73],"an":[32,62,87],"image.":[33,63],"In":[34,79],"many":[35],"cases,":[36],"using":[37],"in":[39,109,119],"the":[40,43],"image":[41],"improves":[42],"specificity":[44],"usefulness":[46],"of":[47,76,90,113,116],"text.":[49],"We":[50,64],"contend":[51],"that":[52,132],"can":[55,133],"benefit":[56],"additional":[58,88],"modify":[65],"previous":[66],"multimodal":[67],"frameworks":[68],"accept":[70],"relevant":[71],"a":[74,94,130],"number":[75],"auxiliary":[77],"classifiers.":[78],"particular,":[80],"we":[81,128],"focus":[82],"on":[83,144],"person":[84,102],"names":[85],"as":[86],"set":[89],"tokens":[91,138],"create":[93],"novel":[95],"image-caption":[96],"dataset":[97],"facilitate":[99],"captioning":[100],"names.":[103],"The":[104],"dataset,":[105,127],"Politicians":[106],"Athletes":[108],"Captions":[110],"(PAC),":[111],"consists":[112],"captioned":[114],"images":[115],"well-known":[117],"people":[118],"context.":[120],"By":[121],"fine-tuning":[122],"pretrained":[123],"this":[126],"demonstrate":[129],"model":[131],"naturally":[134],"integrate":[135],"facial":[136],"into":[139],"training":[143],"limited":[145],"data.":[146]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}