{"id":"https://openalex.org/W2884326683","doi":"https://doi.org/10.1109/tip.2018.2855415","title":"More is Better: Precise and Detailed Image Captioning Using Online Positive Recall and Missing Concepts Mining","display_name":"More is Better: Precise and Detailed Image Captioning Using Online Positive Recall and Missing Concepts Mining","publication_year":2018,"publication_date":"2018-07-12","ids":{"openalex":"https://openalex.org/W2884326683","doi":"https://doi.org/10.1109/tip.2018.2855415","mag":"2884326683","pmid":"https://pubmed.ncbi.nlm.nih.gov/30010565"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2018.2855415","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2018.2855415","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":"https://openalex.org/A5100621291","display_name":"Mingxing Zhang","orcid":"https://orcid.org/0000-0001-8363-6968"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Mingxing Zhang","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, CN"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, CN","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100397616","display_name":"Yang Yang","orcid":"https://orcid.org/0000-0002-5070-4511"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Yang","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, CN"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, CN","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042324027","display_name":"Hanwang Zhang","orcid":"https://orcid.org/0000-0001-7374-8739"},"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":["Nanyang Technological University, Singapore, Singapore, SG"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore, SG","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068950059","display_name":"Yanli Ji","orcid":"https://orcid.org/0000-0001-9122-6141"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanli Ji","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, CN"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, CN","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052993469","display_name":"Heng Tao Shen","orcid":"https://orcid.org/0000-0002-2999-2088"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Tao Shen","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, CN"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, CN","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089404640","display_name":"Tat\u2010Seng Chua","orcid":"https://orcid.org/0000-0001-6097-7807"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Tat-Seng Chua","raw_affiliation_strings":["National University of Singapore, Singapore, SG"],"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, SG","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100621291"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":5.7452,"has_fulltext":false,"cited_by_count":91,"citation_normalized_percentile":{"value":0.97125324,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"28","issue":"1","first_page":"32","last_page":"44"},"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":0.9988999962806702,"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":0.9901000261306763,"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":0.9523420929908752},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8041073083877563},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.7078133225440979},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.609274685382843},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5956838726997375},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.5658243298530579},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.5074333548545837},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.46343594789505005},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4513567388057709},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37655484676361084},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3717460632324219},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36044397950172424}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9523420929908752},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8041073083877563},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.7078133225440979},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.609274685382843},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5956838726997375},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.5658243298530579},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.5074333548545837},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.46343594789505005},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4513567388057709},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37655484676361084},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3717460632324219},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36044397950172424},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tip.2018.2855415","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2018.2855415","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:30010565","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/30010565","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},{"id":"pmh:oai:dr.ntu.edu.sg:10356/142314","is_oa":false,"landing_page_url":"https://hdl.handle.net/10356/142314","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"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":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1816382614","display_name":null,"funder_award_id":"61572108","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3623292902","display_name":null,"funder_award_id":"61632007","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8978917354","display_name":null,"funder_award_id":"B17008","funder_id":"https://openalex.org/F4320327912","funder_display_name":"Higher Education Discipline Innovation Project"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320323292","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92"},{"id":"https://openalex.org/F4320327912","display_name":"Higher Education Discipline Innovation Project","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":84,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1527575280","https://openalex.org/W1686810756","https://openalex.org/W1811254738","https://openalex.org/W1895577753","https://openalex.org/W1903029394","https://openalex.org/W1931639407","https://openalex.org/W1947481528","https://openalex.org/W2064675550","https://openalex.org/W2127615881","https://openalex.org/W2129906471","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2143612262","https://openalex.org/W2146241755","https://openalex.org/W2154318594","https://openalex.org/W2155893237","https://openalex.org/W2157331557","https://openalex.org/W2171361956","https://openalex.org/W2194775991","https://openalex.org/W2276199106","https://openalex.org/W2302086703","https://openalex.org/W2522148122","https://openalex.org/W2550553598","https://openalex.org/W2552161745","https://openalex.org/W2556388456","https://openalex.org/W2558401060","https://openalex.org/W2558834163","https://openalex.org/W2560645892","https://openalex.org/W2565656701","https://openalex.org/W2575842049","https://openalex.org/W2578466053","https://openalex.org/W2591669147","https://openalex.org/W2604178507","https://openalex.org/W2606436201","https://openalex.org/W2607768201","https://openalex.org/W2611926148","https://openalex.org/W2614818206","https://openalex.org/W2665436006","https://openalex.org/W2678677036","https://openalex.org/W2691067844","https://openalex.org/W2753215597","https://openalex.org/W2755385356","https://openalex.org/W2755513316","https://openalex.org/W2765158981","https://openalex.org/W2766237723","https://openalex.org/W2799787995","https://openalex.org/W2803620531","https://openalex.org/W2887712318","https://openalex.org/W2949555952","https://openalex.org/W2951183276","https://openalex.org/W2962706528","https://openalex.org/W2962968835","https://openalex.org/W2963088515","https://openalex.org/W2963594498","https://openalex.org/W2963758027","https://openalex.org/W2964018924","https://openalex.org/W2964049455","https://openalex.org/W2964308564","https://openalex.org/W3105246522","https://openalex.org/W4213425930","https://openalex.org/W6630875275","https://openalex.org/W6640617836","https://openalex.org/W6679436768","https://openalex.org/W6683033130","https://openalex.org/W6685230081","https://openalex.org/W6687483927","https://openalex.org/W6698228248","https://openalex.org/W6713731963","https://openalex.org/W6719103691","https://openalex.org/W6728925852","https://openalex.org/W6729046916","https://openalex.org/W6730061300","https://openalex.org/W6730278946","https://openalex.org/W6731400982","https://openalex.org/W6732875994","https://openalex.org/W6736519844","https://openalex.org/W6740010567","https://openalex.org/W6744104549","https://openalex.org/W6744442244","https://openalex.org/W6751073220","https://openalex.org/W6752119072","https://openalex.org/W6854541590"],"related_works":["https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W3217388757","https://openalex.org/W2358294942","https://openalex.org/W3122720459","https://openalex.org/W4298897568","https://openalex.org/W4289422896","https://openalex.org/W1938708284","https://openalex.org/W4380190185"],"abstract_inverted_index":{"Recently,":[0],"a":[1,91,124,142],"great":[2],"progress":[3],"in":[4,26,74],"automatic":[5],"image":[6,191,208],"captioning":[7,192,209],"has":[8],"been":[9],"achieved":[10],"by":[11,78],"using":[12,33],"semantic":[13,136],"concepts":[14,99,130,137,165],"detected":[15,140],"from":[16,43],"the":[17,28,34,39,44,54,58,67,71,79,109,149,162,182,189,196],"image.":[18,183],"However,":[19],"we":[20,89,153],"argue":[21],"that":[22,203],"existing":[23],"concepts-to-caption":[24],"framework,":[25],"which":[27,201],"concept":[29,68],"detector":[30],"is":[31],"trained":[32],"image-caption":[35],"pairs":[36],"to":[37,101,115,159,180],"minimize":[38],"vocabulary":[40],"discrepancy,":[41],"suffers":[42],"deficiency":[45],"of":[46,60,66,84,111],"insufficient":[47],"concepts.":[48],"The":[49],"reasons":[50],"are":[51],"two-fold:":[52],"1)":[53],"extreme":[55],"imbalance":[56],"between":[57],"number":[59],"occurrence":[61],"positive":[62,95,120],"and":[63,69,82,97,122,141,177,195],"negative":[64],"samples":[65,113],"2)":[70],"incomplete":[72],"labeling":[73],"training":[75],"captions":[76],"caused":[77],"biased":[80],"annotation":[81],"usage":[83],"synonyms.":[85],"In":[86,132],"this":[87,133],"paper,":[88],"propose":[90],"method,":[92],"termed":[93],"online":[94,119,198],"recall":[96,121],"missing":[98,129],"mining,":[100],"overcome":[102],"those":[103],"problems.":[104],"Our":[105],"method":[106,172,205],"adaptively":[107],"re-weights":[108],"loss":[110],"different":[112],"according":[114],"their":[116],"predictions":[117],"for":[118,128],"uses":[123],"two-stage":[125],"optimization":[126],"strategy":[127],"mining.":[131],"way,":[134],"more":[135,175],"can":[138,173],"be":[139,146],"high":[143],"accuracy":[144],"will":[145],"expected.":[147],"On":[148],"caption":[150,179],"generation":[151],"stage,":[152],"explore":[154],"an":[155],"element-wise":[156],"selection":[157],"process":[158],"automatically":[160],"choose":[161],"most":[163],"suitable":[164],"at":[166],"each":[167],"time":[168],"step.":[169],"Thus,":[170],"our":[171,204],"generate":[174],"precise":[176],"detailed":[178],"describe":[181],"We":[184],"conduct":[185],"extensive":[186],"experiments":[187],"on":[188],"MSCOCO":[190,197],"data":[193],"set":[194],"test":[199],"server,":[200],"shows":[202],"achieves":[206],"superior":[207],"performance":[210],"compared":[211],"with":[212],"other":[213],"competitive":[214],"methods.":[215]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":20},{"year":2019,"cited_by_count":19},{"year":2018,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}