{"id":"https://openalex.org/W4220798700","doi":"https://doi.org/10.1109/tpami.2022.3159811","title":"On Distinctive Image Captioning via Comparing and Reweighting","display_name":"On Distinctive Image Captioning via Comparing and Reweighting","publication_year":2022,"publication_date":"2022-03-16","ids":{"openalex":"https://openalex.org/W4220798700","doi":"https://doi.org/10.1109/tpami.2022.3159811","pmid":"https://pubmed.ncbi.nlm.nih.gov/35294345"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2022.3159811","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2022.3159811","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2204.03938","any_repository_has_fulltext":true},"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/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"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":true,"raw_author_name":"Jiuniu Wang","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Hong Kong","University of Chinese Academy of Sciences, Beijing, China","Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I168719708"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210137199","https://openalex.org/I19820366"]}]},{"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/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"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":["Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, Beijing, China","University of Chinese Academy of Sciences, Beijing, China","Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210137199","https://openalex.org/I19820366"]}]},{"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":["Department of Computer Science, City University of Hong Kong, Hong Kong","Baidu Research, Baidu Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I168719708"]},{"raw_affiliation_string":"Baidu Research, Baidu Inc., Beijing, China","institution_ids":["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":["Department of Computer Science, City University of Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5081895678"],"corresponding_institution_ids":["https://openalex.org/I168719708","https://openalex.org/I19820366","https://openalex.org/I4210137199","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":2.7584,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.91613505,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"45","issue":"2","first_page":"2088","last_page":"2103"},"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":0.998199999332428,"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":0.9957000017166138,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.9595028162002563},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8525596857070923},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.6330702304840088},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4147000014781952},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3664991855621338},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.36019450426101685},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.35686418414115906}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9595028162002563},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8525596857070923},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6330702304840088},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4147000014781952},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3664991855621338},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.36019450426101685},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35686418414115906}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/tpami.2022.3159811","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2022.3159811","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:35294345","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35294345","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 pattern analysis and machine intelligence","raw_type":null},{"id":"pmh:oai:arXiv.org:2204.03938","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2204.03938","pdf_url":"https://arxiv.org/pdf/2204.03938","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:pure.atira.dk:publications/c621469f-0019-45ee-be2f-7e0cb1a51de2","is_oa":true,"landing_page_url":"https://hdl.handle.net/2031/c621469f-0019-45ee-be2f-7e0cb1a51de2","pdf_url":null,"source":{"id":"https://openalex.org/S7407055387","display_name":"CityU Scholars","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":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Wang, J, Xu, W, Wang, Q & Chan, A B 2023, 'On Distinctive Image Captioning via Comparing and Reweighting', IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 45, no. 2, pp. 2088-2103. https://doi.org/10.1109/TPAMI.2022.3159811","raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2204.03938","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2204.03938","pdf_url":"https://arxiv.org/pdf/2204.03938","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":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":89,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1686810756","https://openalex.org/W1811254738","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1897761818","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2133459682","https://openalex.org/W2148143831","https://openalex.org/W2154652894","https://openalex.org/W2194775991","https://openalex.org/W2506483933","https://openalex.org/W2552161745","https://openalex.org/W2574790321","https://openalex.org/W2604178507","https://openalex.org/W2607579284","https://openalex.org/W2745461083","https://openalex.org/W2752461516","https://openalex.org/W2754927243","https://openalex.org/W2774267535","https://openalex.org/W2791445206","https://openalex.org/W2795601629","https://openalex.org/W2797029597","https://openalex.org/W2798959609","https://openalex.org/W2803206166","https://openalex.org/W2803525166","https://openalex.org/W2850386316","https://openalex.org/W2884561390","https://openalex.org/W2885013662","https://openalex.org/W2885822952","https://openalex.org/W2889543827","https://openalex.org/W2892153332","https://openalex.org/W2896457183","https://openalex.org/W2947380870","https://openalex.org/W2954841306","https://openalex.org/W2962964995","https://openalex.org/W2962968835","https://openalex.org/W2963084599","https://openalex.org/W2963101956","https://openalex.org/W2963150697","https://openalex.org/W2963170456","https://openalex.org/W2963351448","https://openalex.org/W2963448089","https://openalex.org/W2963467339","https://openalex.org/W2963686907","https://openalex.org/W2963691377","https://openalex.org/W2966715458","https://openalex.org/W2973826744","https://openalex.org/W2978725006","https://openalex.org/W2982553922","https://openalex.org/W2983141445","https://openalex.org/W2986670728","https://openalex.org/W2987118624","https://openalex.org/W2988793532","https://openalex.org/W2989489923","https://openalex.org/W3034316193","https://openalex.org/W3034682719","https://openalex.org/W3035552357","https://openalex.org/W3047153790","https://openalex.org/W3095707208","https://openalex.org/W3097062010","https://openalex.org/W3101313921","https://openalex.org/W3102138045","https://openalex.org/W3107015116","https://openalex.org/W3166396011","https://openalex.org/W3203770998","https://openalex.org/W4288263322","https://openalex.org/W4385245566","https://openalex.org/W6620707391","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6638742206","https://openalex.org/W6682631176","https://openalex.org/W6739901393","https://openalex.org/W6743895910","https://openalex.org/W6747225742","https://openalex.org/W6750238580","https://openalex.org/W6752113587","https://openalex.org/W6755207826","https://openalex.org/W6763430915","https://openalex.org/W6766438439","https://openalex.org/W6766904570","https://openalex.org/W6785276314","https://openalex.org/W6791353385"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3088136942","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"],"abstract_inverted_index":{"Recent":[0],"image":[1,65,108,174,222],"captioning":[2,223],"models":[3],"are":[4,113,176,192,227],"achieving":[5],"impressive":[6],"results":[7,226],"based":[8,116],"on":[9,19,117],"popular":[10,22],"metrics,":[11],"i.e.,":[12,47],"BLEU,":[13],"CIDEr,":[14],"and":[15,33,42,69,169,207,210],"SPICE.":[16],"However,":[17],"focusing":[18],"the":[20,27,30,52,62,87,103,110,124,162,172,183],"most":[21],"metrics":[23],"that":[24,102,165,195],"only":[25],"consider":[26],"overlap":[28],"between":[29],"generated":[31,184],"captions":[32,66,170],"human":[34,104,125],"annotation":[35],"could":[36,131],"result":[37],"in":[38,109],"using":[39],"common":[40],"words":[41,164],"phrases,":[43],"which":[44,130],"lacks":[45],"distinctiveness,":[46],"many":[48],"similar":[49,75,97,173],"images":[50],"have":[51],"same":[53],"caption.":[54],"In":[55,140],"this":[56],"paper,":[57],"we":[58,78,142],"aim":[59],"to":[60,85,94,148,160,181,186],"improve":[61],"distinctiveness":[63,81,88,150,202],"of":[64,74,89,96,106,221],"via":[67],"comparing":[68],"reweighting":[70],"with":[71,92],"a":[72,80,90,133,156,218,231],"set":[73,175],"images.":[76,98],"First,":[77],"propose":[79],"metric-between-set":[82],"CIDEr":[83],"(CIDErBtw)":[84],"evaluate":[86],"caption":[91,146],"respect":[93],"those":[95],"Our":[99],"metric":[100],"reveals":[101],"annotations":[105,126],"each":[107,144],"MSCOCO":[111],"dataset":[112],"not":[114],"equivalent":[115],"distinctiveness;":[118],"however,":[119],"previous":[120],"works":[121],"normally":[122],"treat":[123],"equally":[127],"during":[128,151],"training,":[129],"be":[132,187],"reason":[134],"for":[135,217],"generating":[136],"less":[137],"distinctive":[138],"captions.":[139],"contrast,":[141],"reweight":[143],"ground-truth":[145],"according":[147],"its":[149],"training.":[152],"We":[153],"further":[154,228],"integrate":[155],"long-tailed":[157],"weight":[158],"strategy":[159],"highlight":[161],"rare":[163],"contain":[166],"more":[167],"information,":[168],"from":[171],"sampled":[177],"as":[178,213],"negative":[179],"examples":[180],"encourage":[182],"sentence":[185],"unique.":[188],"Finally,":[189],"extensive":[190],"experiments":[191],"conducted,":[193],"showing":[194],"our":[196],"proposed":[197],"approach":[198],"significantly":[199],"improves":[200],"both":[201],"(as":[203],"measured":[204,214],"by":[205,215],"CIDErBtw":[206],"retrieval":[208],"metrics)":[209],"accuracy":[211],"(e.g.,":[212],"CIDEr)":[216],"wide":[219],"variety":[220],"baselines.":[224],"These":[225],"confirmed":[229],"through":[230],"user":[232],"study.":[233]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":4}],"updated_date":"2026-04-01T17:29:45.350535","created_date":"2022-05-05T00:00:00"}