{"id":"https://openalex.org/W2981165461","doi":"https://doi.org/10.1109/tcsvt.2019.2947482","title":"Multimodal Transformer With Multi-View Visual Representation for Image Captioning","display_name":"Multimodal Transformer With Multi-View Visual Representation for Image Captioning","publication_year":2019,"publication_date":"2019-10-15","ids":{"openalex":"https://openalex.org/W2981165461","doi":"https://doi.org/10.1109/tcsvt.2019.2947482","mag":"2981165461"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2019.2947482","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2019.2947482","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","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/A5050817770","display_name":"Jun Yu","orcid":"https://orcid.org/0000-0003-1922-7283"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jun Yu","raw_affiliation_strings":["Key Laboratory of Complex Systems Modeling and Simulation, School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Complex Systems Modeling and Simulation, School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jing Li","orcid":"https://orcid.org/0000-0001-5639-4289"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Li","raw_affiliation_strings":["Key Laboratory of Complex Systems Modeling and Simulation, School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Complex Systems Modeling and Simulation, School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061025828","display_name":"Yu Zhou","orcid":"https://orcid.org/0000-0001-8407-1137"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou Yu","raw_affiliation_strings":["Key Laboratory of Complex Systems Modeling and Simulation, School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Complex Systems Modeling and Simulation, School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028597017","display_name":"Qingming Huang","orcid":"https://orcid.org/0000-0001-7542-296X"},"institutions":[{"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":"Qingming Huang","raw_affiliation_strings":["School of Computer and Control Engineering, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Control Engineering, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5050817770"],"corresponding_institution_ids":["https://openalex.org/I50760025"],"apc_list":null,"apc_paid":null,"fwci":22.783,"has_fulltext":false,"cited_by_count":452,"citation_normalized_percentile":{"value":0.99547597,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"30","issue":"12","first_page":"4467","last_page":"4480"},"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":0.9921000003814697,"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":0.9853000044822693,"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":0.9717205762863159},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8267354965209961},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5911263823509216},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5554987788200378},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.43840572237968445},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.4296562671661377},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4198017120361328},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4188675284385681},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3516438901424408},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3418229818344116},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.33254069089889526},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2829662561416626}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9717205762863159},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8267354965209961},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5911263823509216},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5554987788200378},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.43840572237968445},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.4296562671661377},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4198017120361328},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4188675284385681},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3516438901424408},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3418229818344116},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33254069089889526},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2829662561416626},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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":1,"locations":[{"id":"doi:10.1109/tcsvt.2019.2947482","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2019.2947482","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7699999809265137,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G5054529767","display_name":null,"funder_award_id":"61702143","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7528510259","display_name":null,"funder_award_id":"61836002","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":80,"referenced_works":["https://openalex.org/W8316075","https://openalex.org/W639708223","https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1536680647","https://openalex.org/W1811254738","https://openalex.org/W1858383477","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1897761818","https://openalex.org/W1905882502","https://openalex.org/W1947481528","https://openalex.org/W1956340063","https://openalex.org/W1969616664","https://openalex.org/W1996219872","https://openalex.org/W2049538695","https://openalex.org/W2064675550","https://openalex.org/W2097117768","https://openalex.org/W2101105183","https://openalex.org/W2105103432","https://openalex.org/W2112912048","https://openalex.org/W2123301721","https://openalex.org/W2130942839","https://openalex.org/W2154652894","https://openalex.org/W2185175083","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2277195237","https://openalex.org/W2463565445","https://openalex.org/W2489434015","https://openalex.org/W2546696630","https://openalex.org/W2549139847","https://openalex.org/W2550553598","https://openalex.org/W2552161745","https://openalex.org/W2560730294","https://openalex.org/W2560920409","https://openalex.org/W2575842049","https://openalex.org/W2613718673","https://openalex.org/W2735680049","https://openalex.org/W2745461083","https://openalex.org/W2747623286","https://openalex.org/W2885013662","https://openalex.org/W2889418103","https://openalex.org/W2890531016","https://openalex.org/W2908056713","https://openalex.org/W2943070176","https://openalex.org/W2962706528","https://openalex.org/W2962918138","https://openalex.org/W2962938439","https://openalex.org/W2963037989","https://openalex.org/W2963084599","https://openalex.org/W2963150162","https://openalex.org/W2963176022","https://openalex.org/W2963351448","https://openalex.org/W2963383024","https://openalex.org/W2963403868","https://openalex.org/W2963521239","https://openalex.org/W2963656855","https://openalex.org/W2963668159","https://openalex.org/W2964022527","https://openalex.org/W2964121744","https://openalex.org/W2964345792","https://openalex.org/W2966683369","https://openalex.org/W4385245566","https://openalex.org/W6600334730","https://openalex.org/W6620707391","https://openalex.org/W6630875275","https://openalex.org/W6631190155","https://openalex.org/W6638742206","https://openalex.org/W6639102338","https://openalex.org/W6639118148","https://openalex.org/W6676647902","https://openalex.org/W6678262379","https://openalex.org/W6679436768","https://openalex.org/W6682631176","https://openalex.org/W6719057275","https://openalex.org/W6739901393","https://openalex.org/W6752083267","https://openalex.org/W6780226713","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W4290852288","https://openalex.org/W3088136942","https://openalex.org/W4310447809","https://openalex.org/W4200243030","https://openalex.org/W2800782462","https://openalex.org/W4323777661","https://openalex.org/W3209117276"],"abstract_inverted_index":{"Image":[0],"captioning":[1,121,165,189,236],"aims":[2],"to":[3,108,118,138,160,196],"automatically":[4],"generate":[5],"a":[6,11,27,109,133],"natural":[7],"language":[8],"description":[9],"of":[10,26,70,97,143,219,232,241,244],"given":[12],"image,":[13,42],"and":[14,43,129,155,179,191],"most":[15],"state-of-the-art":[16,214],"models":[17],"have":[18],"adopted":[19],"an":[20,44,217],"encoder-decoder":[21],"framework.":[22],"The":[23,203],"framework":[24],"consists":[25],"convolution":[28],"neural":[29,46],"network":[30,47],"(CNN)-based":[31],"image":[32,115,120,164,188,235],"encoder":[33],"that":[34,52,79,88,207],"extracts":[35],"region-based":[36],"visual":[37,61,168],"features":[38,62,169],"from":[39],"the":[40,54,60,64,68,77,81,86,90,95,98,123,139,147,163,174,185,198,212,225,229,233,239,242],"input":[41],"recurrent":[45],"(RNN)":[48],"based":[49,58],"caption":[50,56],"decoder":[51],"generates":[53],"output":[55,156],"words":[57],"on":[59,228],"with":[63],"attention":[65,135,145],"mechanism.":[66],"Despite":[67],"success":[69,96],"existing":[71,119],"studies,":[72],"current":[73],"methods":[74],"only":[75],"model":[76,100,113,125,149],"co-attention":[78],"characterizes":[80,89],"inter-modal":[82,130],"interactions":[83,131],"while":[84],"neglecting":[85],"self-attention":[87],"intra-modal":[91],"interactions.":[92],"Inspired":[93],"by":[94],"Transformer":[99,111],"in":[101,132],"machine":[102],"translation,":[103],"here":[104],"we":[105],"extend":[106],"it":[107],"Multimodal":[110],"(MT)":[112],"for":[114],"captioning.":[116],"Compared":[117],"approaches,":[122],"MT":[124,148,175],"simultaneously":[126],"captures":[127],"intra-":[128],"unified":[134],"block.":[136],"Due":[137],"in-depth":[140],"modular":[141],"composition":[142],"such":[144],"blocks,":[146],"can":[150],"perform":[151],"complex":[152],"multimodal":[153],"reasoning":[154],"accurate":[157],"captions.":[158],"Moreover,":[159],"further":[161],"improve":[162],"performance,":[166],"multi-view":[167],"are":[170],"seamlessly":[171],"introduced":[172],"into":[173],"model.":[176],"We":[177],"quantitatively":[178],"qualitatively":[180],"evaluate":[181],"our":[182,208,222],"approach":[183],"using":[184],"benchmark":[186],"MSCOCO":[187,234],"dataset":[190],"conduct":[192],"extensive":[193],"ablation":[194],"studies":[195],"investigate":[197],"reasons":[199],"behind":[200],"its":[201],"effectiveness.":[202],"experimental":[204],"results":[205],"show":[206],"method":[209],"significantly":[210],"outperforms":[211],"previous":[213],"methods.":[215],"With":[216],"ensemble":[218],"seven":[220],"models,":[221],"solution":[223],"ranks":[224],"1st":[226],"place":[227],"real-time":[230],"leaderboard":[231],"challenge":[237],"at":[238],"time":[240],"writing":[243],"this":[245],"paper.":[246]},"counts_by_year":[{"year":2026,"cited_by_count":11},{"year":2025,"cited_by_count":56},{"year":2024,"cited_by_count":69},{"year":2023,"cited_by_count":93},{"year":2022,"cited_by_count":88},{"year":2021,"cited_by_count":48},{"year":2020,"cited_by_count":83},{"year":2019,"cited_by_count":4}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}