{"id":"https://openalex.org/W4210649510","doi":"https://doi.org/10.1109/tip.2022.3145158","title":"Discriminative Style Learning for Cross-Domain Image Captioning","display_name":"Discriminative Style Learning for Cross-Domain Image Captioning","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4210649510","doi":"https://doi.org/10.1109/tip.2022.3145158","pmid":"https://pubmed.ncbi.nlm.nih.gov/35085078"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2022.3145158","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2022.3145158","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":null,"display_name":"Jin Yuan","orcid":"https://orcid.org/0000-0002-9600-7789"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Yuan","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-9600-7789","affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shuai Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Zhu","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shuyin Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuyin Huang","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hanwang Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hanwang Zhang","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yaoqiang Xiao","orcid":"https://orcid.org/0000-0003-3162-3086"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaoqiang Xiao","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0003-3162-3086","affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhiyong Li","orcid":"https://orcid.org/0000-0001-9720-5915"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Li","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0001-9720-5915","affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"last","author":{"id":null,"display_name":"Meng Wang","orcid":"https://orcid.org/0000-0002-3094-7735"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Wang","raw_affiliation_strings":["School of Computer Science, Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-3094-7735","affiliations":[{"raw_affiliation_string":"School of Computer Science, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.523,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.83272277,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"31","issue":null,"first_page":"1723","last_page":"1736"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9243000149726868,"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":0.9243000149726868,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.04050000011920929,"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":0.00559999980032444,"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":0.9142000079154968},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.743399977684021},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6699000000953674},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6172999739646912},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5891000032424927},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.45829999446868896},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.42289999127388},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.3779999911785126}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9142000079154968},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7876999974250793},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.743399977684021},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6699000000953674},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6553999781608582},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6172999739646912},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5891000032424927},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5720000267028809},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.45829999446868896},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.42289999127388},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.3779999911785126},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.3416000008583069},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.33399999141693115},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3244999945163727},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.31189998984336853},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.31150001287460327},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.30160000920295715},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.30140000581741333},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.28119999170303345},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2635999917984009},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2596000134944916}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2022.3145158","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2022.3145158","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:35085078","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35085078","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":[],"awards":[{"id":"https://openalex.org/G2781639450","display_name":null,"funder_award_id":"61976086","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6151690139","display_name":null,"funder_award_id":"62020106007","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":56,"referenced_works":["https://openalex.org/W92662927","https://openalex.org/W1587871245","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1902237438","https://openalex.org/W1931639407","https://openalex.org/W1947481528","https://openalex.org/W2173180041","https://openalex.org/W2185175083","https://openalex.org/W2194775991","https://openalex.org/W2220981600","https://openalex.org/W2277195237","https://openalex.org/W2296385829","https://openalex.org/W2398118205","https://openalex.org/W2481240925","https://openalex.org/W2533598788","https://openalex.org/W2550553598","https://openalex.org/W2552161745","https://openalex.org/W2558834163","https://openalex.org/W2575842049","https://openalex.org/W2625940279","https://openalex.org/W2745461083","https://openalex.org/W2766261529","https://openalex.org/W2767577934","https://openalex.org/W2788710361","https://openalex.org/W2797733588","https://openalex.org/W2808071176","https://openalex.org/W2822349497","https://openalex.org/W2890718122","https://openalex.org/W2913618459","https://openalex.org/W2955956881","https://openalex.org/W2963084599","https://openalex.org/W2963201326","https://openalex.org/W2963992143","https://openalex.org/W2964018924","https://openalex.org/W2965697393","https://openalex.org/W2970768710","https://openalex.org/W2982553922","https://openalex.org/W2983537698","https://openalex.org/W2984862483","https://openalex.org/W2997248215","https://openalex.org/W3003478339","https://openalex.org/W3010356384","https://openalex.org/W3034984754","https://openalex.org/W3035160838","https://openalex.org/W3035284526","https://openalex.org/W3035323998","https://openalex.org/W3038593179","https://openalex.org/W3110761028","https://openalex.org/W6600334730","https://openalex.org/W6631190155","https://openalex.org/W6679434410","https://openalex.org/W6681184217","https://openalex.org/W6685145238","https://openalex.org/W6748197246","https://openalex.org/W6762718338"],"related_works":[],"abstract_inverted_index":{"The":[0],"cross-domain":[1],"image":[2,69,107,154,174],"captioning,":[3],"which":[4,94,124],"is":[5,43,164],"trained":[6],"on":[7,232],"a":[8,88,109,120,131,137],"source":[9,32,194],"domain":[10,20],"and":[11,33,104,134,156,196,215],"generalized":[12],"to":[13,28,37,66,113,129,141,148,166],"other":[14],"domains,":[15,59],"usually":[16],"faces":[17],"the":[18,41,51,96,101,126,162,169,176,183,187,193,201,212,216,224],"large":[19,52],"shift":[21],"problem.":[22],"Although":[23],"prior":[24],"work":[25],"has":[26],"attempted":[27],"leverage":[29],"both":[30],"paired":[31],"unpaired":[34],"target":[35,202],"data":[36],"minimize":[38],"this":[39,83,85],"shift,":[40],"performance":[42],"still":[44],"unsatisfactory.":[45],"One":[46],"main":[47],"reason":[48],"lies":[49],"in":[50,54,74],"discrepancy":[53],"language":[55,62],"expression":[56],"between":[57],"two":[58],"where":[60],"diverse":[61],"styles":[63],"are":[64,146],"adopted":[65],"describe":[67],"an":[68,79,106,173],"from":[70],"different":[71,75],"views,":[72],"resulting":[73],"semantic":[76,170],"descriptions":[77,155],"for":[78],"image.":[80],"To":[81],"tackle":[82],"problem,":[84],"paper":[86],"proposes":[87],"Style-based":[89],"Cross-domain":[90],"Image":[91],"Captioner":[92],"(SCIC)":[93],"incorporates":[95],"discriminative":[97],"style":[98,115,132,217],"information":[99,218],"into":[100],"encoder-decoder":[102],"framework,":[103],"interprets":[105],"as":[108,179,181,192,200],"special":[110,177],"sentence":[111],"according":[112,140],"external":[114],"instructions.":[116],"Technically,":[117],"we":[118],"design":[119],"novel":[121],"\"Instruction-based":[122],"LSTM\",":[123],"adds":[125],"instruct":[127],"gate":[128],"collect":[130],"instruction,":[133],"then":[135],"outputs":[136],"specified":[138],"format":[139],"that":[142,207],"instruction.":[143],"Two":[144],"objectives":[145],"designed":[147],"train":[149],"I-LSTM:":[150],"1)":[151],"generating":[152,158],"correct":[153,159],"2)":[157],"styles,":[160],"thus":[161],"model":[163,209],"expected":[165],"accurately":[167],"capture":[168],"meanings":[171],"of":[172,186],"by":[175],"caption":[178],"well":[180],"understand":[182],"syntactic":[184],"structure":[185],"caption.":[188],"We":[189],"use":[190],"MS-COCO":[191],"domain,":[195],"Oxford-102,":[197],"CUB-200,":[198],"Flickr30k":[199],"domains.":[203],"Experimental":[204],"results":[205],"demonstrate":[206],"our":[208],"consistently":[210],"outperforms":[211],"previous":[213],"methods,":[214],"incorporating":[219],"with":[220,226],"I-LSTM":[221],"significantly":[222],"improves":[223],"performance,":[225],"5%":[227],"CIDEr":[228],"improvements":[229],"at":[230],"least":[231],"all":[233],"datasets.":[234]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2022-02-08T00:00:00"}