{"id":"https://openalex.org/W3205647238","doi":"https://doi.org/10.1145/3474085.3475215","title":"Group-based Distinctive Image Captioning with Memory Attention","display_name":"Group-based Distinctive Image Captioning with Memory Attention","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3205647238","doi":"https://doi.org/10.1145/3474085.3475215","mag":"3205647238"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3475215","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475215","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5081895678","display_name":"Jiuniu Wang","orcid":"https://orcid.org/0000-0002-6113-0066"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]},{"id":"https://openalex.org/I4210137199","display_name":"Aerospace Information Research Institute","ror":"https://ror.org/0419fj215","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210137199"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Jiuniu Wang","raw_affiliation_strings":["City University of Hong Kong, Aerospace Information Research Institute, Chinese Academy of Sciences, & University of Chinese Academy of Sciences, Hong Kong SAR, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"City University of Hong Kong, Aerospace Information Research Institute, Chinese Academy of Sciences, & University of Chinese Academy of Sciences, Hong Kong SAR, Hong Kong","institution_ids":["https://openalex.org/I168719708","https://openalex.org/I4210137199","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057777785","display_name":"Wenjia Xu","orcid":"https://orcid.org/0000-0002-1425-4162"},"institutions":[{"id":"https://openalex.org/I4210137199","display_name":"Aerospace Information Research Institute","ror":"https://ror.org/0419fj215","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210137199"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjia Xu","raw_affiliation_strings":["Aerospace Information Research Institute, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aerospace Information Research Institute, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210137199","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073897483","display_name":"Qingzhong Wang","orcid":"https://orcid.org/0000-0003-1562-8098"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]},{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Qingzhong Wang","raw_affiliation_strings":["City University of Hong Kong & Baidu Research, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"City University of Hong Kong & Baidu Research, Beijing, China","institution_ids":["https://openalex.org/I168719708","https://openalex.org/I98301712"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065680386","display_name":"Antoni B. Chan","orcid":"https://orcid.org/0000-0002-2886-2513"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Antoni B. Chan","raw_affiliation_strings":["City University of Hong Kong, Hong Kong SAR, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"City University of Hong Kong, Hong Kong SAR, Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4318,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.88897052,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5020","last_page":"5028"},"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":0.9912999868392944,"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":0.9735999703407288,"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":0.9701213836669922},{"id":"https://openalex.org/keywords/optimal-distinctiveness-theory","display_name":"Optimal distinctiveness theory","score":0.9061670899391174},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7736022472381592},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6271638870239258},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6187806129455566},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.590045154094696},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5480794906616211},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5423234105110168},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5340710282325745},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.527319610118866},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.43208399415016174},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.43084245920181274},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.36270618438720703},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35044288635253906},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.16465675830841064},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07791295647621155}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9701213836669922},{"id":"https://openalex.org/C47385372","wikidata":"https://www.wikidata.org/wiki/Q7098943","display_name":"Optimal distinctiveness theory","level":2,"score":0.9061670899391174},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7736022472381592},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6271638870239258},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6187806129455566},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.590045154094696},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5480794906616211},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5423234105110168},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5340710282325745},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.527319610118866},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.43208399415016174},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.43084245920181274},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36270618438720703},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35044288635253906},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.16465675830841064},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07791295647621155},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3474085.3475215","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475215","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7200000286102295,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W2550553598","https://openalex.org/W2574790321","https://openalex.org/W2604178507","https://openalex.org/W2745461083","https://openalex.org/W2767057417","https://openalex.org/W2790600496","https://openalex.org/W2898710146","https://openalex.org/W2923793772","https://openalex.org/W2936707910","https://openalex.org/W2962968835","https://openalex.org/W2963084599","https://openalex.org/W2963170456","https://openalex.org/W2963360726","https://openalex.org/W2963594498","https://openalex.org/W2963686907","https://openalex.org/W2967834053","https://openalex.org/W2986670728","https://openalex.org/W2987118624","https://openalex.org/W2990818246","https://openalex.org/W3010593057","https://openalex.org/W3034655362","https://openalex.org/W3034682719","https://openalex.org/W3035160838","https://openalex.org/W3035284526","https://openalex.org/W3047153790","https://openalex.org/W3107015116","https://openalex.org/W6600655691"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3088136942","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W4225552138","https://openalex.org/W4290852288","https://openalex.org/W2752461516","https://openalex.org/W2963360726","https://openalex.org/W4388002133","https://openalex.org/W3009270862"],"abstract_inverted_index":{"Describing":[0],"images":[1,56,127],"using":[2,114],"natural":[3,24],"language":[4,25,196],"is":[5,57],"widely":[6],"known":[7],"as":[8],"image":[9,52,89,112,124,158],"captioning,":[10],"which":[11,74,121,149],"has":[12],"made":[13],"consistent":[14],"progress":[15],"due":[16],"to":[17,48,164,193,211],"the":[18,44,50,71,82,96,109,134,157,184,188,195,213,221,226,234,249,254,257],"development":[19],"of":[20,46,111,136,215,228,243,256],"computer":[21],"vision":[22],"and":[23,42,132,198,232,240,252],"generation":[26],"techniques.":[27],"Though":[28],"conventional":[29],"captioning":[30],"models":[31],"achieve":[32],"high":[33],"accuracy":[34,239],"based":[35],"on":[36,76,237],"popular":[37],"metrics,":[38],"i.e.,":[39],"BLEU,":[40],"CIDEr,":[41],"SPICE,":[43],"ability":[45],"captions":[47,113,190],"distinguish":[49],"target":[51],"from":[53],"other":[54,126,167],"similar":[55,88,130],"under-explored.":[58],"To":[59],"generate":[60],"distinctive":[61,181,185,207],"captions,":[62,73,177],"a":[63,87,115,143,203,244],"few":[64],"pioneers":[65],"employ":[66],"contrastive":[67],"learning":[68],"or":[69,93,99],"re-weighted":[70],"ground-truth":[72,189],"focuses":[75],"one":[77,129],"single":[78],"input":[79],"image.":[80,138],"However,":[81],"relationships":[83],"between":[84],"objects":[85,165],"in":[86,128,166,179,187],"group":[90,131,159],"(e.g.,":[91],"items":[92],"properties":[94],"within":[95],"same":[97],"album":[98],"fine-grained":[100],"events)":[101],"are":[102,154,173,191],"neglected.":[103],"In":[104,139],"this":[105],"paper,":[106],"we":[107,141,201],"improve":[108],"distinctiveness":[110,214,227],"Group-based":[116],"Distinctive":[117],"Captioning":[118],"Model":[119],"(GdisCap),":[120],"compares":[122],"each":[123,137],"with":[125,161,248],"highlights":[133],"uniqueness":[135],"particular,":[140],"propose":[142,202],"group-based":[144],"memory":[145],"attention":[146],"(GMA)":[147],"module,":[148],"stores":[150],"object":[151,171],"features":[152,172],"that":[153,220],"unique":[155,170],"among":[156],"(i.e.,":[160],"low":[162],"similarity":[163],"images).":[168],"These":[169],"highlighted":[174],"when":[175],"generating":[176],"resulting":[178],"more":[180],"captions.":[182,216],"Furthermore,":[183],"words":[186],"selected":[192],"supervise":[194],"decoder":[197],"GMA.":[199],"Finally,":[200],"new":[204,258],"evaluation":[205,251],"metric,":[206],"word":[208],"rate":[209],"(DisWordRate)":[210],"measure":[212],"Quantitative":[217],"results":[218],"indicate":[219],"proposed":[222],"method":[223],"significantly":[224],"improves":[225],"several":[229],"baseline":[230],"models,":[231],"achieves":[233],"state-of-the-art":[235],"performance":[236],"both":[238],"distinctiveness.":[241],"Results":[242],"user":[245],"study":[246],"agree":[247],"quantitative":[250],"demonstrate":[253],"rationality":[255],"metric":[259],"DisWordRate.":[260]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4}],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2025-10-10T00:00:00"}