{"id":"https://openalex.org/W3125154076","doi":"https://doi.org/10.1109/tip.2021.3051476","title":"Vocabulary-Wide Credit Assignment for Training Image Captioning Models","display_name":"Vocabulary-Wide Credit Assignment for Training Image Captioning Models","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3125154076","doi":"https://doi.org/10.1109/tip.2021.3051476","mag":"3125154076","pmid":"https://pubmed.ncbi.nlm.nih.gov/33471759"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2021.3051476","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2021.3051476","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/A5100349041","display_name":"Han Liu","orcid":"https://orcid.org/0000-0002-3051-1990"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Han Liu","raw_affiliation_strings":["Department of Computer Science and Technology, State Key Laboratory of Intelligent Technology and Systems, Beijing National Research Center for Information Science and Technology, Institute for Artificial Intelligence, Tsinghua University, Beijing, China","State Key Laboratory of Intelligent Technology and Systems, Beijing National Research Center for Information Science and Technology, Institute for Artificial Intelligence, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, State Key Laboratory of Intelligent Technology and Systems, Beijing National Research Center for Information Science and Technology, Institute for Artificial Intelligence, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"State Key Laboratory of Intelligent Technology and Systems, Beijing National Research Center for Information Science and Technology, Institute for Artificial Intelligence, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100757125","display_name":"Shifeng Zhang","orcid":"https://orcid.org/0000-0001-8305-9566"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shifeng Zhang","raw_affiliation_strings":["Department of Computer Science and Technology, State Key Laboratory of Intelligent Technology and Systems, Beijing National Research Center for Information Science and Technology, Institute for Artificial Intelligence, Tsinghua University, Beijing, China","State Key Laboratory of Intelligent Technology and Systems, Beijing National Research Center for Information Science and Technology, Institute for Artificial Intelligence, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, State Key Laboratory of Intelligent Technology and Systems, Beijing National Research Center for Information Science and Technology, Institute for Artificial Intelligence, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"State Key Laboratory of Intelligent Technology and Systems, Beijing National Research Center for Information Science and Technology, Institute for Artificial Intelligence, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101682776","display_name":"Ke Lin","orcid":"https://orcid.org/0000-0002-4558-8771"},"institutions":[{"id":"https://openalex.org/I4210155230","display_name":"Samsung (China)","ror":"https://ror.org/04yt00889","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210155230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Lin","raw_affiliation_strings":["Samsung Research China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Samsung Research China, Beijing, China","institution_ids":["https://openalex.org/I4210155230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100715026","display_name":"Jing Wen","orcid":"https://orcid.org/0000-0001-6225-1241"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Wen","raw_affiliation_strings":["Department of Computer Science and Technology, State Key Laboratory of Intelligent Technology and Systems, Beijing National Research Center for Information Science and Technology, Institute for Artificial Intelligence, Tsinghua University, Beijing, China","State Key Laboratory of Intelligent Technology and Systems, Beijing National Research Center for Information Science and Technology, Institute for Artificial Intelligence, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, State Key Laboratory of Intelligent Technology and Systems, Beijing National Research Center for Information Science and Technology, Institute for Artificial Intelligence, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"State Key Laboratory of Intelligent Technology and Systems, Beijing National Research Center for Information Science and Technology, Institute for Artificial Intelligence, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100372739","display_name":"Jianmin Li","orcid":"https://orcid.org/0000-0002-4937-2433"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianmin Li","raw_affiliation_strings":["Department of Computer Science and Technology, State Key Laboratory of Intelligent Technology and Systems, Beijing National Research Center for Information Science and Technology, Institute for Artificial Intelligence, Tsinghua University, Beijing, China","State Key Laboratory of Intelligent Technology and Systems, Beijing National Research Center for Information Science and Technology, Institute for Artificial Intelligence, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, State Key Laboratory of Intelligent Technology and Systems, Beijing National Research Center for Information Science and Technology, Institute for Artificial Intelligence, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"State Key Laboratory of Intelligent Technology and Systems, Beijing National Research Center for Information Science and Technology, Institute for Artificial Intelligence, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004579631","display_name":"Xiaolin Hu","orcid":"https://orcid.org/0000-0002-4907-7354"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaolin Hu","raw_affiliation_strings":["Department of Computer Science and Technology, State Key Laboratory of Intelligent Technology and Systems, Beijing National Research Center for Information Science and Technology, Institute for Artificial Intelligence, Tsinghua University, Beijing, China","State Key Laboratory of Intelligent Technology and Systems, Beijing National Research Center for Information Science and Technology, Institute for Artificial Intelligence, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, State Key Laboratory of Intelligent Technology and Systems, Beijing National Research Center for Information Science and Technology, Institute for Artificial Intelligence, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"State Key Laboratory of Intelligent Technology and Systems, Beijing National Research Center for Information Science and Technology, Institute for Artificial Intelligence, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100349041"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":1.9214,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.87727124,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"30","issue":null,"first_page":"2450","last_page":"2460"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9945999979972839,"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"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9879999756813049,"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":0.9829574823379517},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8252567052841187},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.7680084705352783},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6859670877456665},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6338605284690857},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5992029905319214},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5211629867553711},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5119091272354126},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49746468663215637},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4835905432701111},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07798421382904053}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9829574823379517},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8252567052841187},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.7680084705352783},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6859670877456665},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6338605284690857},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5992029905319214},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5211629867553711},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5119091272354126},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49746468663215637},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4835905432701111},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07798421382904053},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2021.3051476","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2021.3051476","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:33471759","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33471759","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}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4699999988079071,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G4160143202","display_name":null,"funder_award_id":"61836014","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5379697419","display_name":null,"funder_award_id":"62061136001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6645987955","display_name":null,"funder_award_id":"U19B2034","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/F4320332195","display_name":"Samsung","ror":"https://ror.org/04w3jy968"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":77,"referenced_works":["https://openalex.org/W68733909","https://openalex.org/W639708223","https://openalex.org/W648786980","https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1811254738","https://openalex.org/W1861492603","https://openalex.org/W1889081078","https://openalex.org/W1905882502","https://openalex.org/W1947481528","https://openalex.org/W1956340063","https://openalex.org/W1969616664","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2108598243","https://openalex.org/W2109586012","https://openalex.org/W2119717200","https://openalex.org/W2123301721","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2154652894","https://openalex.org/W2157331557","https://openalex.org/W2176263492","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2296385829","https://openalex.org/W2302086703","https://openalex.org/W2463955103","https://openalex.org/W2506483933","https://openalex.org/W2542835211","https://openalex.org/W2550553598","https://openalex.org/W2552161745","https://openalex.org/W2575842049","https://openalex.org/W2729842244","https://openalex.org/W2745461083","https://openalex.org/W2754927243","https://openalex.org/W2887585070","https://openalex.org/W2890531016","https://openalex.org/W2949376505","https://openalex.org/W2962706528","https://openalex.org/W2962760898","https://openalex.org/W2962918138","https://openalex.org/W2963084599","https://openalex.org/W2963101956","https://openalex.org/W2963248296","https://openalex.org/W2963403868","https://openalex.org/W2964121744","https://openalex.org/W2964199361","https://openalex.org/W2964308564","https://openalex.org/W2981165461","https://openalex.org/W2986670728","https://openalex.org/W3034655362","https://openalex.org/W3035284526","https://openalex.org/W3103022576","https://openalex.org/W3105136412","https://openalex.org/W4294149591","https://openalex.org/W4385245566","https://openalex.org/W6620707391","https://openalex.org/W6621543089","https://openalex.org/W6630875275","https://openalex.org/W6631190155","https://openalex.org/W6638742206","https://openalex.org/W6639102338","https://openalex.org/W6639432524","https://openalex.org/W6676497082","https://openalex.org/W6678262379","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6682631176","https://openalex.org/W6685322675","https://openalex.org/W6694395031","https://openalex.org/W6728610325","https://openalex.org/W6739901393","https://openalex.org/W6741068176","https://openalex.org/W6744684495","https://openalex.org/W6754778999","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W3217195652","https://openalex.org/W1997182898"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"(RL)":[2],"algorithms":[3,20],"have":[4],"been":[5],"shown":[6],"to":[7,22,25,56,75,121],"be":[8,110],"efficient":[9],"in":[10,18,37,59,83],"training":[11,117],"image":[12,42,118],"captioning":[13,119],"models.":[14],"A":[15],"critical":[16],"step":[17],"RL":[19,39,114],"is":[21,73,93],"assign":[23],"credits":[24],"appropriate":[26,86],"actions.":[27],"There":[28],"are":[29],"mainly":[30],"two":[31],"classes":[32],"of":[33,134],"credit":[34,47,55,69,87,96],"assignment":[35,70],"methods":[36,40,115],"existing":[38,113],"for":[41,48,116],"captioning,":[43],"assigning":[44,53],"a":[45,54,67,103],"single":[46],"the":[49,60,76,132],"whole":[50],"sentence":[51],"and":[52],"every":[57,81],"word":[58,82],"sentence.":[61],"In":[62],"this":[63,100],"article,":[64],"we":[65,101],"propose":[66,102],"new":[68],"method":[71],"which":[72],"orthogonal":[74],"above":[77],"two.":[78],"It":[79,92],"assigns":[80],"vocabulary":[84],"an":[85],"at":[88],"each":[89],"generation":[90],"step.":[91],"called":[94],"vocabulary-wide":[95],"assignment.":[97],"Based":[98],"on":[99],"Vocabulary-Critical":[104],"Sequence":[105],"Training":[106],"(VCST).":[107],"VCST":[108],"can":[109],"incorporated":[111],"into":[112],"models":[120,130],"achieve":[122],"better":[123],"results.":[124],"Extensive":[125],"experiments":[126],"with":[127],"many":[128],"popular":[129],"validated":[131],"effectiveness":[133],"VCST.":[135]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":5}],"updated_date":"2026-02-04T23:10:29.248076","created_date":"2025-10-10T00:00:00"}