{"id":"https://openalex.org/W4402760797","doi":"https://doi.org/10.1145/3694683","title":"Improving Reference-Based Distinctive Image Captioning with Contrastive Rewards","display_name":"Improving Reference-Based Distinctive Image Captioning with Contrastive Rewards","publication_year":2024,"publication_date":"2024-09-24","ids":{"openalex":"https://openalex.org/W4402760797","doi":"https://doi.org/10.1145/3694683"},"language":"en","primary_location":{"id":"doi:10.1145/3694683","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3694683","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-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/A5105833877","display_name":"Y. Mao","orcid":"https://orcid.org/0000-0001-7759-6015"},"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","Zhejiang University, China"],"raw_orcid":"https://orcid.org/0000-0001-7759-6015","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Zhejiang University, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101485990","display_name":"Jun Xiao","orcid":"https://orcid.org/0000-0003-0303-134X"},"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","Zhejiang University, China"],"raw_orcid":"https://orcid.org/0000-0003-0303-134X","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Zhejiang University, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101818657","display_name":"Dong Zhang","orcid":"https://orcid.org/0000-0002-4543-2179"},"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":["The Hong Kong University of Science and Technology, Kowloon, Hong Kong SAR","The Hong Kong University of Science and Technology, Hong Kong SAR"],"raw_orcid":"https://orcid.org/0000-0002-4543-2179","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology, Kowloon, Hong Kong SAR","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"The Hong Kong University of Science and Technology, Hong Kong SAR","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067002890","display_name":"Meng Cao","orcid":"https://orcid.org/0000-0002-8946-4228"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210128628","display_name":"Peking University Shenzhen Hospital","ror":"https://ror.org/03kkjyb15","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210128628"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Cao","raw_affiliation_strings":["Peking University, Shenzhen, China","Peking University, China"],"raw_orcid":"https://orcid.org/0000-0002-8946-4228","affiliations":[{"raw_affiliation_string":"Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I4210128628"]},{"raw_affiliation_string":"Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"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","Zhejiang University, China"],"raw_orcid":"https://orcid.org/0000-0002-7842-7616","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Zhejiang University, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008666077","display_name":"Yueting Zhuang","orcid":"https://orcid.org/0000-0001-9017-2508"},"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":"Yueting Zhuang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China","Zhejiang University, China"],"raw_orcid":"https://orcid.org/0000-0001-9017-2508","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Zhejiang University, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100336360","display_name":"Long Chen","orcid":"https://orcid.org/0000-0001-6148-9709"},"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":"Long Chen","raw_affiliation_strings":["The Hong Kong University of Science and Technology, Kowloon, Hong Kong SAR","The Hong Kong University of Science and Technology, Hong Kong SAR"],"raw_orcid":"https://orcid.org/0000-0001-6148-9709","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology, Kowloon, Hong Kong SAR","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"The Hong Kong University of Science and Technology, Hong Kong SAR","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3124,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.81818182,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"20","issue":"12","first_page":"1","last_page":"24"},"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":0.9957000017166138,"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":0.994700014591217,"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":0.9463354349136353},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.9143497347831726},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.561461865901947},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5002572536468506},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46784958243370056},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.39061930775642395},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.37825608253479004},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.36454248428344727},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3613623380661011}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9463354349136353},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9143497347831726},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.561461865901947},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5002572536468506},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46784958243370056},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.39061930775642395},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.37825608253479004},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36454248428344727},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3613623380661011}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3694683","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3694683","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-146946","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-146946","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":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2655623952","display_name":null,"funder_award_id":"226-2024-00058","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G5540768979","display_name":null,"funder_award_id":"62337001","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"},{"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":51,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1773149199","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1955055330","https://openalex.org/W1956340063","https://openalex.org/W2506483933","https://openalex.org/W2550553598","https://openalex.org/W2574790321","https://openalex.org/W2604178507","https://openalex.org/W2745461083","https://openalex.org/W2798959609","https://openalex.org/W2890531016","https://openalex.org/W2922601488","https://openalex.org/W2949554687","https://openalex.org/W2962968835","https://openalex.org/W2963084599","https://openalex.org/W2963101956","https://openalex.org/W2963448089","https://openalex.org/W2963530300","https://openalex.org/W2963758027","https://openalex.org/W2974212192","https://openalex.org/W2987123286","https://openalex.org/W3023511145","https://openalex.org/W3035060554","https://openalex.org/W3035284526","https://openalex.org/W3035524453","https://openalex.org/W3090449556","https://openalex.org/W3155889037","https://openalex.org/W3167939936","https://openalex.org/W3176524055","https://openalex.org/W3195680250","https://openalex.org/W3204924011","https://openalex.org/W3205765769","https://openalex.org/W4213453379","https://openalex.org/W4283793362","https://openalex.org/W4285602612","https://openalex.org/W4292828275","https://openalex.org/W4318035685","https://openalex.org/W4319300753","https://openalex.org/W4324312108","https://openalex.org/W4362514016","https://openalex.org/W4377864347","https://openalex.org/W4384161812","https://openalex.org/W4388936587","https://openalex.org/W4389056806","https://openalex.org/W4391296421","https://openalex.org/W6739901393","https://openalex.org/W6743895910","https://openalex.org/W6755403031","https://openalex.org/W6840126788"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W3217388757","https://openalex.org/W3122720459","https://openalex.org/W4298897568","https://openalex.org/W4289422896","https://openalex.org/W1938708284","https://openalex.org/W4380190185"],"abstract_inverted_index":{"Distinctive":[0],"Image":[1],"Captioning":[2],"(DIC)\u2014generating":[3],"distinctive":[4,30,100,145,201,310],"captions":[5,31,54,101],"that":[6,93,304],"describe":[7],"the":[8,19,34,52,58,62,82,105,111,160,185,188,194,218,224,229,258,293,298,319],"unique":[9,161],"details":[10],"of":[11,40,247,257,297],"a":[12,38,94,131,138,141,178,205,240,282],"target":[13,35,59,83,112,150,166,189,219,230],"image\u2014has":[14],"received":[15],"considerable":[16],"attention":[17],"over":[18,323],"last":[20],"few":[21,89],"years.":[22],"A":[23,135],"recent":[24],"DIC":[25,46],"method":[26],"proposes":[27],"to":[28,50,55,75,147,199,253],"generate":[29,99,200,309],"by":[32,69],"comparing":[33],"image":[36,60,84,113,220],"with":[37,137],"set":[39],"semantic-similar":[41],"reference":[42,63,66,78,106,125,152,191,232,259],"images,":[43,167],"i.e.,":[44],"reference-Based":[45],"(Ref-DIC).":[47],"It":[48,211],"aims":[49],"force":[51],"generated":[53,299],"distinguish":[56],"between":[57,187,226],"and":[61,87,119,140,151,190,231,295],"image.":[64],"Unfortunately,":[65],"images":[67,79,126,192],"used":[68],"existing":[70],"Ref-DIC":[71,95,156,173,207,273],"works":[72],"are":[73,127],"easy":[74],"distinguish:":[76],"these":[77],"only":[80,213],"resemble":[81],"at":[85,193],"scene-level":[86],"have":[88],"common":[90],"objects,":[91],"such":[92],"model":[96],"can":[97,267,308],"trivially":[98],"even":[102],"without":[103,128],"considering":[104],"images.":[107,153,233,260],"For":[108],"example,":[109],"if":[110],"contains":[114],"objects":[115,162,227],"\u201c":[116,120,134],"towel":[117,139],"\u201d":[118,122,143],"toilet":[121,142],"while":[123],"all":[124],"them,":[129],"then":[130],"simple":[132],"caption":[133],"bathroom":[136],"is":[144,264],"enough":[146],"tell":[148],"apart":[149],"To":[154],"ensure":[155],"models":[157,317],"really":[158],"perceive":[159],"(or":[163],"attributes)":[164],"in":[165,228],"we":[168,176,203,238,280],"first":[169],"propose":[170,239,281],"two":[171,320],"new":[172,262,283,321],"benchmarks.":[174],"Specifically,":[175],"design":[177],"two-stage":[179],"matching":[180],"mechanism,":[181],"which":[182,245,266,290],"strictly":[183],"controls":[184],"similarity":[186],"object-/attribute-level":[195],"(vs.":[196],"scene-level).":[197],"Second,":[198],"captions,":[202],"develop":[204],"Transformer-based":[206],"baseline":[208],"TransDIC":[209,242,306],".":[210],"not":[212],"extracts":[214],"visual":[215],"features":[216],"from":[217],"but":[221],"also":[222],"encodes":[223],"differences":[225],"Taking":[234],"one":[235],"step":[236],"further,":[237],"stronger":[241],"\\({++}\\)":[243,307],",":[244],"consists":[246],"an":[248],"extra":[249],"contrastive":[250],"learning":[251],"module":[252,263],"make":[254],"full":[255],"use":[256],"This":[261],"model-agnostic,":[265],"be":[268],"easily":[269],"incorporated":[270],"into":[271],"various":[272],"architectures.":[274],"Finally,":[275],"for":[276,288],"more":[277],"trustworthy":[278],"benchmarking,":[279],"evaluation":[284],"metric":[285],"named":[286],"DisCIDEr":[287],"Ref-DIC,":[289],"evaluates":[291],"both":[292],"accuracy":[294],"distinctiveness":[296],"captions.":[300,311],"Experimental":[301],"results":[302],"demonstrate":[303],"our":[305],"Besides,":[312],"it":[313],"outperforms":[314],"several":[315],"state-of-the-art":[316],"on":[318],"benchmarks":[322],"different":[324],"metrics.":[325]},"counts_by_year":[{"year":2025,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}