{"id":"https://openalex.org/W4408177927","doi":"https://doi.org/10.1587/transinf.2024edp7126","title":"Empowering Vision-Language Tuning with Machine Translation for Driving Scene Caption Generation","display_name":"Empowering Vision-Language Tuning with Machine Translation for Driving Scene Caption Generation","publication_year":2025,"publication_date":"2025-03-06","ids":{"openalex":"https://openalex.org/W4408177927","doi":"https://doi.org/10.1587/transinf.2024edp7126"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2024edp7126","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2024edp7126","pdf_url":null,"source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1587/transinf.2024edp7126","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091690989","display_name":"Lei Zhou","orcid":"https://orcid.org/0000-0002-3443-7396"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Lei ZHOU","raw_affiliation_strings":["Graduate School of Informatics, Nagoya University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Nagoya University","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049498516","display_name":"Ryohei Sasano","orcid":null},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryohei SASANO","raw_affiliation_strings":["Graduate School of Informatics, Nagoya University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Nagoya University","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000123568","display_name":"Koichi Takeda","orcid":"https://orcid.org/0000-0001-7545-4101"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Koichi TAKEDA","raw_affiliation_strings":["Research and Development Center for Large Language Models, National Institute of Informatics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research and Development Center for Large Language Models, National Institute of Informatics","institution_ids":["https://openalex.org/I184597095"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02688207,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"E108.D","issue":"9","first_page":"1082","last_page":"1094"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9976999759674072,"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":0.9976999759674072,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9283000230789185,"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":0.9150000214576721,"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/computer-science","display_name":"Computer science","score":0.8728331327438354},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5844867825508118},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.563819408416748},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5343149900436401},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.42708680033683777},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3767223358154297}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8728331327438354},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5844867825508118},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.563819408416748},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5343149900436401},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42708680033683777},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3767223358154297},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1587/transinf.2024edp7126","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2024edp7126","pdf_url":null,"source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1587/transinf.2024edp7126","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2024edp7126","pdf_url":null,"source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2194775991","https://openalex.org/W2506483933","https://openalex.org/W2933138175","https://openalex.org/W2962784628","https://openalex.org/W2971296908","https://openalex.org/W2979826702","https://openalex.org/W2989322838","https://openalex.org/W3006961192","https://openalex.org/W3035564946","https://openalex.org/W3036411379","https://openalex.org/W3091588028","https://openalex.org/W3168477526","https://openalex.org/W3174010726","https://openalex.org/W3177654849","https://openalex.org/W3203711169","https://openalex.org/W4205979075","https://openalex.org/W4214612132","https://openalex.org/W4285813146","https://openalex.org/W4312560592","https://openalex.org/W4312810944","https://openalex.org/W4312922092","https://openalex.org/W4323357858","https://openalex.org/W4383097607","https://openalex.org/W4385569837","https://openalex.org/W4385569915","https://openalex.org/W4386072117","https://openalex.org/W4386076444","https://openalex.org/W4389520022"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"In":[0,128],"the":[1,12,16,21,29,53,76,94,105,113,121,199,242],"Autonomous":[2],"Driving":[3],"(AD)":[4],"scenario,":[5],"accurate,":[6],"informative,":[7],"and":[8,15,112,169,213],"understandable":[9],"descriptions":[10],"of":[11,23,55,124],"traffic":[13],"conditions":[14],"ego-vehicle":[17],"motions":[18],"can":[19],"increase":[20],"interpretability":[22],"an":[24],"autonomous":[25,97],"driving":[26,48,115,160,219],"system":[27,158],"to":[28,41,133,154,197],"vehicle":[30,228],"user.":[31],"End-to-end":[32],"free-form":[33],"video":[34],"captioning":[35,117,157],"is":[36],"a":[37,59,86,138,156,167,238],"straightforward":[38],"vision-to-text":[39],"task":[40],"address":[42],"such":[43],"needs.":[44],"However,":[45,92],"insufficient":[46],"real-world":[47,114,218],"scene":[49,116,161],"descriptive":[50],"data":[51,107],"hinders":[52],"performance":[54,233],"caption":[56,90,162,223,231],"generation":[57,163,232],"under":[58],"simple":[60],"supervised":[61],"training":[62,106],"paradigm.":[63],"Recently,":[64],"large-scale":[65],"Vision-Language":[66],"Pre-training":[67],"(VLP)":[68],"foundation":[69,80,110,126],"models":[70,81,111],"have":[71],"attracted":[72],"much":[73],"attention":[74],"from":[75,166],"community.":[77],"Tuning":[78],"large":[79,102],"on":[82,207,217],"task-specific":[83],"datasets":[84],"becomes":[85],"prevailing":[87],"paradigm":[88],"for":[89,93,108,141,159,189],"generation.":[91],"application":[95],"in":[96,164],"driving,":[98],"we":[99,131,193,209],"often":[100],"encounter":[101],"gaps":[103],"between":[104],"VLP":[109,125,171],"data,":[118],"which":[119],"impedes":[120],"immense":[122],"potential":[123],"models.":[127],"this":[129,135],"paper,":[130],"present":[132],"tackle":[134],"problem":[136],"via":[137],"unified":[139],"framework":[140,174,212,236],"cross-lingual":[142,190],"cross-domain":[143],"vision-language":[144,200],"tuning":[145,201],"empowered":[146],"by":[147,183,226],"Machine":[148],"Translation":[149],"(MT)":[150],"techniques.":[151],"We":[152],"aim":[153],"obtain":[155],"Japanese":[165],"domain-general":[168],"English-centric":[170],"model.":[172],"The":[173,230],"comprises":[175],"two":[176],"core":[177],"components:":[178],"(i)":[179],"bidirectional":[180],"knowledge":[181],"distillation":[182],"MT":[184],"teachers;":[185],"(ii)":[186],"fusing":[187,204],"objectives":[188],"fine-tuning.":[191],"Moreover,":[192],"introduce":[194],"three":[195],"schedulers":[196],"operate":[198],"process":[202],"with":[203,221,234],"objectives.":[205],"Based":[206],"GIT,":[208],"implement":[210],"our":[211,235],"verify":[214],"its":[215],"effectiveness":[216],"scenes":[220],"natural":[222],"texts":[224],"annotated":[225],"experienced":[227],"users.":[229],"reveals":[237],"significant":[239],"advantage":[240],"over":[241],"baseline":[243],"settings.":[244]},"counts_by_year":[],"updated_date":"2025-12-19T19:40:27.379048","created_date":"2025-10-10T00:00:00"}
