{"id":"https://openalex.org/W4386076444","doi":"https://doi.org/10.1109/cvpr52729.2023.00670","title":"Cross-Domain Image Captioning with Discriminative Finetuning","display_name":"Cross-Domain Image Captioning with Discriminative Finetuning","publication_year":2023,"publication_date":"2023-06-01","ids":{"openalex":"https://openalex.org/W4386076444","doi":"https://doi.org/10.1109/cvpr52729.2023.00670"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52729.2023.00670","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52729.2023.00670","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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/A5081298299","display_name":"Roberto Dess\u00ec","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Roberto Dess\u00ec","raw_affiliation_strings":["Meta AI / UPF"],"affiliations":[{"raw_affiliation_string":"Meta AI / UPF","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036241567","display_name":"Michele Bevilacqua","orcid":"https://orcid.org/0000-0001-7955-0117"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michele Bevilacqua","raw_affiliation_strings":["Samaya AI"],"affiliations":[{"raw_affiliation_string":"Samaya AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031674195","display_name":"Eleonora Gualdoni","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090448","display_name":"University Press of Florida","ror":"https://ror.org/017j15308","country_code":"US","type":"education","lineage":["https://openalex.org/I4210090448"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eleonora Gualdoni","raw_affiliation_strings":["UPF"],"affiliations":[{"raw_affiliation_string":"UPF","institution_ids":["https://openalex.org/I4210090448"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034208113","display_name":"Nathana\u00ebl Carraz Rakotonirina","orcid":"https://orcid.org/0000-0003-0181-2644"},"institutions":[{"id":"https://openalex.org/I4210090448","display_name":"University Press of Florida","ror":"https://ror.org/017j15308","country_code":"US","type":"education","lineage":["https://openalex.org/I4210090448"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nathana\u00ebl Carraz Rakotonirina","raw_affiliation_strings":["UPF"],"affiliations":[{"raw_affiliation_string":"UPF","institution_ids":["https://openalex.org/I4210090448"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045137998","display_name":"Francesca Franzon","orcid":"https://orcid.org/0000-0003-0503-2792"},"institutions":[{"id":"https://openalex.org/I4210090448","display_name":"University Press of Florida","ror":"https://ror.org/017j15308","country_code":"US","type":"education","lineage":["https://openalex.org/I4210090448"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Francesca Franzon","raw_affiliation_strings":["UPF"],"affiliations":[{"raw_affiliation_string":"UPF","institution_ids":["https://openalex.org/I4210090448"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038612405","display_name":"Marco Baroni","orcid":"https://orcid.org/0000-0001-5066-3580"},"institutions":[{"id":"https://openalex.org/I11932220","display_name":"Instituci\u00f3 Catalana de Recerca i Estudis Avan\u00e7ats","ror":"https://ror.org/0371hy230","country_code":"ES","type":"nonprofit","lineage":["https://openalex.org/I11932220"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Marco Baroni","raw_affiliation_strings":["UPF / ICREA"],"affiliations":[{"raw_affiliation_string":"UPF / ICREA","institution_ids":["https://openalex.org/I11932220"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5081298299"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.5792,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.9162591,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6935","last_page":"6944"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9955000281333923,"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":0.8889937996864319},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.8832341432571411},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.8271104097366333},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6467725038528442},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6078693866729736},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5829188823699951},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.5650903582572937},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5134438276290894},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5056226253509521},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4387549161911011},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3853774070739746},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.36757639050483704},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3430887460708618}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8889937996864319},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8832341432571411},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8271104097366333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6467725038528442},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6078693866729736},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5829188823699951},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.5650903582572937},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5134438276290894},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5056226253509521},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4387549161911011},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3853774070739746},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36757639050483704},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3430887460708618},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52729.2023.00670","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52729.2023.00670","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7200000286102295,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320338335","display_name":"H2020 European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":64,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1732736211","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2119717200","https://openalex.org/W2121863487","https://openalex.org/W2133459682","https://openalex.org/W2176263492","https://openalex.org/W2185175083","https://openalex.org/W2251512949","https://openalex.org/W2282219577","https://openalex.org/W2506483933","https://openalex.org/W2508429489","https://openalex.org/W2745461083","https://openalex.org/W2752461516","https://openalex.org/W2886641317","https://openalex.org/W2890718122","https://openalex.org/W2904565150","https://openalex.org/W2963084599","https://openalex.org/W2963170456","https://openalex.org/W2963448089","https://openalex.org/W2963992143","https://openalex.org/W2970443036","https://openalex.org/W3104279398","https://openalex.org/W3106477503","https://openalex.org/W3110761028","https://openalex.org/W3153469116","https://openalex.org/W3166396011","https://openalex.org/W3216130706","https://openalex.org/W4206256378","https://openalex.org/W4226182655","https://openalex.org/W4226278401","https://openalex.org/W4255012397","https://openalex.org/W4281686064","https://openalex.org/W4281699561","https://openalex.org/W4287674181","https://openalex.org/W4296566403","https://openalex.org/W4307106676","https://openalex.org/W4307207885","https://openalex.org/W4309088836","https://openalex.org/W4312712450","https://openalex.org/W4321337690","https://openalex.org/W4385245566","https://openalex.org/W4385573818","https://openalex.org/W4385573941","https://openalex.org/W6630875275","https://openalex.org/W6631190155","https://openalex.org/W6639102338","https://openalex.org/W6639657675","https://openalex.org/W6685322675","https://openalex.org/W6691231616","https://openalex.org/W6739901393","https://openalex.org/W6743895910","https://openalex.org/W6782465632","https://openalex.org/W6782529094","https://openalex.org/W6785833691","https://openalex.org/W6791353385","https://openalex.org/W6804709890","https://openalex.org/W6810932996","https://openalex.org/W6849821914","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W3122720459","https://openalex.org/W4298897568","https://openalex.org/W3217388757","https://openalex.org/W1938708284","https://openalex.org/W4380190185","https://openalex.org/W3093339210","https://openalex.org/W3015037427"],"abstract_inverted_index":{"Neural":[0],"captioners":[1],"are":[2,181],"typically":[3],"trained":[4,127],"to":[5,17,44,66,77,104,144],"mimic":[6],"human-generated":[7],"references":[8],"without":[9,141],"optimizing":[10],"for":[11,147,192],"any":[12],"specific":[13],"communication":[14,41],"goal,":[15],"leading":[16],"problems":[18],"such":[19,79],"as":[20],"the":[21,62,89,95,108,120,124,131,137,164,174],"generation":[22],"of":[23,84,102],"vague":[24],"captions.":[25],"In":[26,100],"this":[27],"paper,":[28],"we":[29],"show":[30,171],"that":[31,51,70,155],"fine-tuning":[32],"an":[33,72,197],"out-of-the-box":[34,73],"neural":[35],"captioner":[36,152,166],"with":[37,88,98,196],"a":[38,46,59,68,82],"self-supervised":[39],"discriminative":[40],"objective":[42],"helps":[43],"recover":[45],"plain,":[47],"visually":[48],"descriptive":[49],"language":[50],"is":[52,126,139,209],"more":[53,159,182],"informative":[54],"about":[55],"image":[56,75,80,198],"contents.":[57],"Given":[58],"target":[60],"image,":[61],"system":[63],"must":[64],"learn":[65],"produce":[67],"description":[69],"enables":[71],"text-conditioned":[74],"retriever":[76],"iden-tify":[78],"among":[81],"set":[83],"candidates.":[85],"We":[86,169],"experiment":[87],"popular":[90],"ClipCap":[91,187],"captioner;":[92],"also":[93],"replicating":[94],"main":[96],"results":[97],"BLIP.":[99],"terms":[101],"similarity":[103],"ground-truth":[105,190],"human":[106,157,193],"descriptions,":[107],"captions":[109,146,180,188,191],"emerging":[110],"from":[111],"dis-criminative":[112],"finetuning":[113],"lag":[114],"slightly":[115],"behind":[116],"those":[117,161],"generated":[118],"by":[119,163],"non-finetuned":[121],"model,":[122],"when":[123,136],"latter":[125],"and":[128],"tested":[129],"on":[130,173],"same":[132,165],"caption":[133],"dataset.":[134],"However,":[135],"model":[138],"used":[140],"further":[142,170],"tuning":[143],"generate":[145],"out-of-domain":[148],"datasets,":[149],"our":[150],"discriminatively-finetuned":[151],"generates":[153],"descriptions":[154],"resemble":[156],"ref-erences":[158],"than":[160,184],"produced":[162],"wihtout":[167],"finetuning.":[168],"that,":[172],"Concep-tual":[175],"Captions":[176],"dataset,":[177],"discriminatively":[178],"finetuned":[179],"helpful":[183],"either":[185],"vanilla":[186],"or":[189],"annotators":[194],"tasked":[195],"discrimination":[199],"task.":[200],"<sup":[201,204],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[202,205],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[203,206],"Our":[207],"code":[208],"available":[210],"at":[211],"https://github.com/facebookresearch/EGG/tree/main/egg/zoo/discriminative_captioner.":[212]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}