{"id":"https://openalex.org/W4288043227","doi":"https://doi.org/10.1145/3503161.3548358","title":"Rethinking the Reference-based Distinctive Image Captioning","display_name":"Rethinking the Reference-based Distinctive Image Captioning","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4288043227","doi":"https://doi.org/10.1145/3503161.3548358"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3548358","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548358","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2207.11118","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112623313","display_name":"Yangjun Mao","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yangjun Mao","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100336360","display_name":"Long Chen","orcid":"https://orcid.org/0000-0001-6148-9709"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Long Chen","raw_affiliation_strings":["Columbia University, New York, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University, New York, NY, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102897874","display_name":"Zhihong Jiang","orcid":"https://orcid.org/0000-0001-8133-6312"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihong Jiang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100366068","display_name":"Dong Zhang","orcid":"https://orcid.org/0000-0001-6975-7851"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Dong Zhang","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101409714","display_name":"Zhimeng Zhang","orcid":"https://orcid.org/0000-0002-3695-1129"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhimeng Zhang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101687931","display_name":"Jian Shao","orcid":"https://orcid.org/0000-0002-7842-7616"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Shao","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101485989","display_name":"Jun Xiao","orcid":"https://orcid.org/0000-0002-6142-9914"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Xiao","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1208,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.85206218,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4374","last_page":"4384"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.993399977684021,"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":0.9746999740600586,"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":0.8905510306358337},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7025250792503357},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5282703638076782},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4564225673675537},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4003060460090637}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8905510306358337},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7025250792503357},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5282703638076782},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4564225673675537},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4003060460090637}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3503161.3548358","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548358","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2207.11118","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2207.11118","pdf_url":"https://arxiv.org/pdf/2207.11118","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-125237","is_oa":false,"landing_page_url":"http://lbdiscover.ust.hk/uresolver?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rfr_id=info:sid/HKUST:SPI&rft.genre=article&rft.issn=&rft.volume=&rft.issue=&rft.date=2022&rft.spage=4374&rft.aulast=Mao&rft.aufirst=&rft.atitle=Rethinking+the+Reference-based+Distinctive+Image+Captioning&rft.title=MM+2022+-+Proceedings+of+the+30th+ACM+International+Conference+on+Multimedia","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2207.11118","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2207.11118","pdf_url":"https://arxiv.org/pdf/2207.11118","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3905147744","display_name":null,"funder_award_id":"U19B2043, 61976185","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8241595156","display_name":null,"funder_award_id":"226-2022-00087","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G88417457","display_name":null,"funder_award_id":"2021ZD0110700","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1514535095","https://openalex.org/W1773149199","https://openalex.org/W1889081078","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2123301721","https://openalex.org/W2154652894","https://openalex.org/W2176263492","https://openalex.org/W2194775991","https://openalex.org/W2550553598","https://openalex.org/W2560313346","https://openalex.org/W2574790321","https://openalex.org/W2604178507","https://openalex.org/W2745461083","https://openalex.org/W2752461516","https://openalex.org/W2791445206","https://openalex.org/W2798959609","https://openalex.org/W2890531016","https://openalex.org/W2938232066","https://openalex.org/W2949376505","https://openalex.org/W2949554687","https://openalex.org/W2962968835","https://openalex.org/W2963084599","https://openalex.org/W2963101956","https://openalex.org/W2963170456","https://openalex.org/W2963448089","https://openalex.org/W2963530300","https://openalex.org/W2963758027","https://openalex.org/W2974212192","https://openalex.org/W2986670728","https://openalex.org/W2987123286","https://openalex.org/W2988981892","https://openalex.org/W2989489923","https://openalex.org/W2990818246","https://openalex.org/W3023511145","https://openalex.org/W3034655362","https://openalex.org/W3034682719","https://openalex.org/W3034984754","https://openalex.org/W3103022576","https://openalex.org/W3107015116","https://openalex.org/W3110157234","https://openalex.org/W3140300848","https://openalex.org/W3166396011","https://openalex.org/W3170494780","https://openalex.org/W3176524055","https://openalex.org/W3195680250","https://openalex.org/W3205647238","https://openalex.org/W3205765769","https://openalex.org/W4287333196","https://openalex.org/W4289542422","https://openalex.org/W4312682661","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W4298897568","https://openalex.org/W3217388757","https://openalex.org/W3122720459","https://openalex.org/W1938708284","https://openalex.org/W4380190185","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Distinctive":[0],"Image":[1],"Captioning":[2],"(DIC)":[3],"---":[4,17],"generating":[5],"distinctive":[6,34,102,141,197,266],"captions":[7,35,58,103],"that":[8,95,261],"describe":[9],"the":[10,23,38,56,62,84,107,113,156,181,184,216,222,227,250,255,275],"unique":[11,157],"details":[12],"of":[13,44,254],"a":[14,42,96,129,135,138,174,201,239],"target":[15,39,63,85,114,146,162,185,217,228],"image":[16,40,86,115],"has":[18],"received":[19],"considerable":[20],"attention":[21],"over":[22,279],"last":[24],"few":[25,91],"years.":[26],"A":[27],"recent":[28],"DIC":[29,50],"work":[30],"proposes":[31],"to":[32,54,77,143,195],"generate":[33,101,196,265],"by":[36,71],"comparing":[37],"with":[41,134],"set":[43],"semantic-similar":[45],"reference":[46,65,68,80,108,123,148,187,230],"images,":[47,163],"i.e.,":[48],"reference-based":[49],"(Ref-DIC).":[51],"It":[52,209],"aims":[53],"make":[55],"generated":[57,256],"can":[59,99,264],"tell":[60,144],"apart":[61,145],"and":[64,89,119,137,147,186,229,252],"images.":[66,109,149,231],"Unfortunately,":[67],"images":[69,81,124,188],"used":[70],"existing":[72],"Ref-DIC":[73,97,152,169,204],"works":[74],"are":[75,125],"easy":[76],"distinguish:":[78],"these":[79],"only":[82,211],"resemble":[83],"at":[87,189],"scene-level":[88],"have":[90],"common":[92],"objects,":[93],"such":[94],"model":[98],"trivially":[100],"even":[104],"without":[105,126],"considering":[106],"For":[110],"example,":[111],"if":[112],"contains":[116],"objects":[117,158,225],"\"towel''":[118],"\"toilet''":[120],"while":[121],"all":[122],"them,":[127],"then":[128],"simple":[130],"caption":[131],"\"A":[132],"bathroom":[133],"towel":[136],"toilet''":[139],"is":[140],"enough":[142],"To":[150],"ensure":[151],"models":[153,273],"really":[154],"perceive":[155],"(or":[159],"attributes)":[160],"in":[161,226],"we":[164,172,199,237],"first":[165],"propose":[166,238],"two":[167,276],"new":[168,240,277],"benchmarks.":[170],"Specifically,":[171],"design":[173],"two-stage":[175],"matching":[176],"mechanism,":[177],"which":[178,247],"strictly":[179],"controls":[180],"similarity":[182],"between":[183,224],"object-/attribute-":[190],"level":[191],"(vs.":[192],"scene-level).":[193],"Secondly,":[194],"captions,":[198],"develop":[200],"strong":[202],"Transformer-based":[203],"baseline,":[205],"dubbed":[206],"as":[207],"TransDIC.":[208],"not":[210],"extracts":[212],"visual":[213],"features":[214],"from":[215],"image,":[218],"but":[219],"also":[220],"encodes":[221],"differences":[223],"Finally,":[232],"for":[233,245],"more":[234],"trustworthy":[235],"benchmarking,":[236],"evaluation":[241],"metric":[242],"named":[243],"DisCIDEr":[244],"Ref-DIC,":[246],"evaluates":[248],"both":[249],"accuracy":[251],"distinctiveness":[253],"captions.":[257,267],"Experimental":[258],"results":[259],"demonstrate":[260],"our":[262],"TransDIC":[263],"Besides,":[268],"it":[269],"outperforms":[270],"several":[271],"state-of-the-art":[272],"on":[274],"benchmarks":[278],"different":[280],"metrics.":[281]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}