{"id":"https://openalex.org/W3110761028","doi":"https://doi.org/10.1109/tip.2020.3042086","title":"Cross-Domain Image Captioning via Cross-Modal Retrieval and Model Adaptation","display_name":"Cross-Domain Image Captioning via Cross-Modal Retrieval and Model Adaptation","publication_year":2020,"publication_date":"2020-12-11","ids":{"openalex":"https://openalex.org/W3110761028","doi":"https://doi.org/10.1109/tip.2020.3042086","mag":"3110761028","pmid":"https://pubmed.ncbi.nlm.nih.gov/33306468"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2020.3042086","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2020.3042086","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5029157617","display_name":"Wentian Zhao","orcid":"https://orcid.org/0009-0006-7645-8263"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wentian Zhao","raw_affiliation_strings":["Media Computing and Intelligent Systems Laboratory, Beijing Institute of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Media Computing and Intelligent Systems Laboratory, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011070646","display_name":"Xinxiao Wu","orcid":"https://orcid.org/0000-0002-2056-6947"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinxiao Wu","raw_affiliation_strings":["Media Computing and Intelligent Systems Laboratory, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2056-6947","affiliations":[{"raw_affiliation_string":"Media Computing and Intelligent Systems Laboratory, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055469774","display_name":"Jiebo Luo","orcid":"https://orcid.org/0000-0002-4516-9729"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiebo Luo","raw_affiliation_strings":["Department of Computer Science, University of Rochester, Rochester, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Rochester, Rochester, NY, USA","institution_ids":["https://openalex.org/I5388228"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.2583,"has_fulltext":false,"cited_by_count":64,"citation_normalized_percentile":{"value":0.93652419,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"30","issue":null,"first_page":"1180","last_page":"1192"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9936000108718872,"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":0.9926999807357788,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.8740471601486206},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7760123610496521},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6681786179542542},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6603417992591858},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6478613018989563},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.49842047691345215},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4971669018268585},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.43715205788612366},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43358302116394043},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3814425468444824},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34520789980888367},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3444805145263672},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09957298636436462}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8740471601486206},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7760123610496521},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6681786179542542},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6603417992591858},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6478613018989563},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.49842047691345215},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4971669018268585},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.43715205788612366},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43358302116394043},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3814425468444824},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34520789980888367},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3444805145263672},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09957298636436462},{"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/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2020.3042086","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2020.3042086","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:33306468","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33306468","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","score":0.5,"display_name":"Decent work and economic growth"}],"awards":[{"id":"https://openalex.org/G4454715294","display_name":null,"funder_award_id":"61673062","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G816247876","display_name":null,"funder_award_id":"62072041","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":98,"referenced_works":["https://openalex.org/W68733909","https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1523385540","https://openalex.org/W1527575280","https://openalex.org/W1687846465","https://openalex.org/W1797268635","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1897761818","https://openalex.org/W1905882502","https://openalex.org/W1949478088","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2123301721","https://openalex.org/W2154652894","https://openalex.org/W2159243025","https://openalex.org/W2163605009","https://openalex.org/W2164290393","https://openalex.org/W2164530430","https://openalex.org/W2173180041","https://openalex.org/W2176263492","https://openalex.org/W2185175083","https://openalex.org/W2194775991","https://openalex.org/W2274287116","https://openalex.org/W2302086703","https://openalex.org/W2337252826","https://openalex.org/W2345649690","https://openalex.org/W2398118205","https://openalex.org/W2425121537","https://openalex.org/W2533598788","https://openalex.org/W2560920409","https://openalex.org/W2745461083","https://openalex.org/W2767577934","https://openalex.org/W2774267535","https://openalex.org/W2795832645","https://openalex.org/W2807717070","https://openalex.org/W2886641317","https://openalex.org/W2890718122","https://openalex.org/W2913618459","https://openalex.org/W2918888132","https://openalex.org/W2945223572","https://openalex.org/W2948958195","https://openalex.org/W2950096400","https://openalex.org/W2953016680","https://openalex.org/W2962869524","https://openalex.org/W2962918138","https://openalex.org/W2963017553","https://openalex.org/W2963084599","https://openalex.org/W2963088515","https://openalex.org/W2963101956","https://openalex.org/W2963187862","https://openalex.org/W2963248296","https://openalex.org/W2963293463","https://openalex.org/W2963403868","https://openalex.org/W2963499204","https://openalex.org/W2963743213","https://openalex.org/W2963992143","https://openalex.org/W2964065333","https://openalex.org/W2964121744","https://openalex.org/W2964303913","https://openalex.org/W2964350391","https://openalex.org/W2966005000","https://openalex.org/W2972113750","https://openalex.org/W2974161034","https://openalex.org/W2979933490","https://openalex.org/W2981352610","https://openalex.org/W2990307191","https://openalex.org/W2990818246","https://openalex.org/W2992478697","https://openalex.org/W2998355566","https://openalex.org/W2998841681","https://openalex.org/W3003991937","https://openalex.org/W3034493371","https://openalex.org/W3034655362","https://openalex.org/W3035167603","https://openalex.org/W3035356601","https://openalex.org/W3101429639","https://openalex.org/W3105758476","https://openalex.org/W4385245566","https://openalex.org/W6630875275","https://openalex.org/W6631190155","https://openalex.org/W6631216910","https://openalex.org/W6631516269","https://openalex.org/W6637306801","https://openalex.org/W6638319203","https://openalex.org/W6639102338","https://openalex.org/W6639694449","https://openalex.org/W6678262379","https://openalex.org/W6682631176","https://openalex.org/W6683512859","https://openalex.org/W6684090549","https://openalex.org/W6684191040","https://openalex.org/W6685322675","https://openalex.org/W6694260854","https://openalex.org/W6739901393","https://openalex.org/W6747225742","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W2767577934","https://openalex.org/W2903179935","https://openalex.org/W159132833","https://openalex.org/W3209355071","https://openalex.org/W3216250699","https://openalex.org/W2560207749","https://openalex.org/W4297080010","https://openalex.org/W2161229648","https://openalex.org/W2993674027","https://openalex.org/W2130228941"],"abstract_inverted_index":{"In":[0,79],"recent":[1],"years,":[2],"large":[3],"scale":[4],"datasets":[5,249,296],"of":[6,36,61,103,115,164,201,312],"paired":[7,37],"images":[8,38,62,104,124],"and":[9,29,39,63,105,125,151,186,246,254,293,298],"sentences":[10,40,64,106,126,203],"have":[11],"enabled":[12],"the":[13,50,108,113,116,121,128,147,155,178,182,188,193,198,202,206,212,228,243,259,273,290,304,310],"remarkable":[14],"success":[15],"in":[16,41,55,107,127,205],"automatically":[17],"generating":[18],"descriptions":[19],"for":[20],"images,":[21],"namely":[22],"image":[23,51,91,219],"captioning.":[24],"However,":[25],"it":[26],"is":[27,143,240,287],"labour-intensive":[28],"time-consuming":[30],"to":[31,48,68,89,99,111,154,159,211,281,307],"collect":[32],"a":[33,69,84,95,139,223],"sufficient":[34],"number":[35],"each":[42],"domain.":[43],"It":[44],"may":[45],"be":[46],"beneficial":[47],"transfer":[49],"captioning":[52,92,117,220,284],"model":[53,98,142,180,221],"trained":[54],"an":[56,133,161,217],"existing":[57],"domain":[58,71,110,149,157,208,245,292],"with":[59,72,181,222],"pairs":[60,102,171,185,191],"(i.e.,":[65,76],"source":[66,148,207,244,291],"domain)":[67],"new":[70],"only":[73],"unpaired":[74],"data":[75,150,158],"target":[77,109,129,156,213,260,305],"domain).":[78],"this":[80],"paper,":[81],"we":[82,131,215],"propose":[83,132,216],"cross-modal":[85,96,135,140],"retrieval":[86,97,136,141,179,194],"aided":[87],"approach":[88],"cross-domain":[90,282],"that":[93,263],"leverages":[94],"generate":[100],"pseudo":[101,165,169,183,189,230],"facilitate":[112],"adaptation":[114],"model.":[118,195],"To":[119,196],"learn":[120],"correlation":[122],"between":[123],"domain,":[130,214],"iterative":[134],"process":[137],"where":[138,238,285],"first":[144],"pre-trained":[145],"using":[146,192,227],"then":[152],"applied":[153],"acquire":[160],"initial":[162],"set":[163],"image-sentence":[166,170,184,190,231],"pairs.":[167,232],"The":[168],"are":[172,256,301],"further":[173,308],"refined":[174,229],"by":[175],"iteratively":[176],"fine-tuning":[177],"updating":[187],"make":[197],"linguistic":[199],"patterns":[200],"learned":[204],"adapt":[209],"well":[210],"adaptive":[218],"self-attention":[224],"mechanism":[225],"fine-tuned":[226],"Experimental":[233],"results":[234],"on":[235],"several":[236],"settings":[237],"MSCOCO":[239],"used":[241,257,288,302],"as":[242,258,289,303],"five":[247],"different":[248],"(Flickr30k,":[250],"TGIF,":[251],"CUB-200,":[252],"Oxford-102":[253],"Conceptual)":[255],"domains":[261,306],"demonstrate":[262,309],"our":[264,279,313],"method":[265,280],"achieves":[266],"mostly":[267],"better":[268],"or":[269],"comparable":[270],"performance":[271],"against":[272],"state-of-the-art":[274],"methods.":[275],"We":[276],"also":[277],"extend":[278],"video":[283],"MSR-VTT":[286],"two":[294],"other":[295],"(MSVD":[297],"Charades":[299],"Captions)":[300],"effectiveness":[311],"method.":[314]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}