{"id":"https://openalex.org/W4226396383","doi":"https://doi.org/10.1109/tcsvt.2022.3165934","title":"Bridging Video and Text: A Two-Step Polishing Transformer for Video Captioning","display_name":"Bridging Video and Text: A Two-Step Polishing Transformer for Video Captioning","publication_year":2022,"publication_date":"2022-04-08","ids":{"openalex":"https://openalex.org/W4226396383","doi":"https://doi.org/10.1109/tcsvt.2022.3165934"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2022.3165934","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2022.3165934","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/A5071889746","display_name":"Wanru Xu","orcid":"https://orcid.org/0000-0003-2206-5051"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wanru Xu","raw_affiliation_strings":["Institute of Information Science, Beijing Jiaotong University, Beijing, China","Beijing Key Laboratory of Advanced Information Science and Network Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2206-5051","affiliations":[{"raw_affiliation_string":"Institute of Information Science, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]},{"raw_affiliation_string":"Beijing Key Laboratory of Advanced Information Science and Network Technology, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100298934","display_name":"Zhenjiang Miao","orcid":"https://orcid.org/0000-0001-8032-5769"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenjiang Miao","raw_affiliation_strings":["Institute of Information Science, Beijing Jiaotong University, Beijing, China","Beijing Key Laboratory of Advanced Information Science and Network Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]},{"raw_affiliation_string":"Beijing Key Laboratory of Advanced Information Science and Network Technology, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027501725","display_name":"Jian Yu","orcid":"https://orcid.org/0000-0002-9488-5182"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Yu","raw_affiliation_strings":["School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China","Beijing Key Laboratory of Traffic Data Analysis and Mining, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]},{"raw_affiliation_string":"Beijing Key Laboratory of Traffic Data Analysis and Mining, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100752649","display_name":"Yi Tian","orcid":"https://orcid.org/0000-0001-6054-7970"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Tian","raw_affiliation_strings":["School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China","Beijing Key Laboratory of Traffic Data Analysis and Mining, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6054-7970","affiliations":[{"raw_affiliation_string":"School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]},{"raw_affiliation_string":"Beijing Key Laboratory of Traffic Data Analysis and Mining, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011267367","display_name":"Lili Wan","orcid":"https://orcid.org/0000-0002-9520-5425"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lili Wan","raw_affiliation_strings":["Institute of Information Science, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9520-5425","affiliations":[{"raw_affiliation_string":"Institute of Information Science, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076346273","display_name":"Qiang Ji","orcid":"https://orcid.org/0000-0002-4302-2889"},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qiang Ji","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Rensselaer Polytechnic Institute, Troy, NY, USA"],"raw_orcid":"https://orcid.org/0000-0002-4302-2889","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Rensselaer Polytechnic Institute, Troy, NY, USA","institution_ids":["https://openalex.org/I165799507"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.9364,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.92383269,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"32","issue":"9","first_page":"6293","last_page":"6307"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9975000023841858,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9955999851226807,"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":0.9103705883026123},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.852982759475708},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5617321133613586},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5521989464759827},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5410060286521912},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5291723608970642},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5105482339859009},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.4529430568218231},{"id":"https://openalex.org/keywords/semantic-gap","display_name":"Semantic gap","score":0.4203135371208191}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9103705883026123},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.852982759475708},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5617321133613586},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5521989464759827},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5410060286521912},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5291723608970642},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5105482339859009},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.4529430568218231},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.4203135371208191},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2022.3165934","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2022.3165934","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":0.6700000166893005,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1594688182","display_name":"\u57fa\u4e8e\u6df1\u5ea6\u7f51\u7edc\u7684\u540c\u7c7b\u6848\u4f8b\u533b\u5b66\u56fe\u50cf\u8de8\u6a21\u6001\u591a\u6807\u7b7e\u7ba1\u7406\u548c\u591a\u6a21\u5f0f\u68c0\u7d22\u7814\u7a76","funder_award_id":"61971446","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6097791489","display_name":"\u57fa\u4e8e\u9690\u4fe1\u606f\u7684\u4eba\u4f53\u884c\u4e3a\u9884\u6d4b\u7814\u7a76","funder_award_id":"61672089","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6524102570","display_name":null,"funder_award_id":"2021RC216","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G7853727141","display_name":null,"funder_award_id":"62006015","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8749161932","display_name":null,"funder_award_id":"61906013","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8991566416","display_name":"\u56fe\u50cf\u4e0e\u4e09\u7ef4\u6a21\u578b\u7ed3\u5408\u7684\u9ad8\u5c42\u5f62\u72b6\u5206\u6790\u7814\u7a76","funder_award_id":"61572064","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/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1956340063","https://openalex.org/W2095705004","https://openalex.org/W2101105183","https://openalex.org/W2425121537","https://openalex.org/W2549139847","https://openalex.org/W2554906389","https://openalex.org/W2558834163","https://openalex.org/W2584992898","https://openalex.org/W2754927243","https://openalex.org/W2763440627","https://openalex.org/W2798725893","https://openalex.org/W2799176631","https://openalex.org/W2889418103","https://openalex.org/W2904698318","https://openalex.org/W2950579554","https://openalex.org/W2961553857","https://openalex.org/W2962861647","https://openalex.org/W2962907269","https://openalex.org/W2963504927","https://openalex.org/W2963552819","https://openalex.org/W2963971014","https://openalex.org/W2969844053","https://openalex.org/W2972281329","https://openalex.org/W2974686944","https://openalex.org/W2976669726","https://openalex.org/W2987327987","https://openalex.org/W2990964949","https://openalex.org/W3009192917","https://openalex.org/W3014545861","https://openalex.org/W3019301826","https://openalex.org/W3020826863","https://openalex.org/W3034221024","https://openalex.org/W3034316193","https://openalex.org/W3034593503","https://openalex.org/W3035365026","https://openalex.org/W3035392611","https://openalex.org/W3039060838","https://openalex.org/W3047922786","https://openalex.org/W3093309253","https://openalex.org/W3121052081","https://openalex.org/W3134875898","https://openalex.org/W3137384391","https://openalex.org/W3174441232","https://openalex.org/W3176362845","https://openalex.org/W3176425931","https://openalex.org/W3176514808","https://openalex.org/W3176689360","https://openalex.org/W3192261211","https://openalex.org/W3205898187","https://openalex.org/W3211402614","https://openalex.org/W6631190155","https://openalex.org/W6674330103","https://openalex.org/W6678262379","https://openalex.org/W6682631176","https://openalex.org/W6684090549","https://openalex.org/W6739901393","https://openalex.org/W6754653261","https://openalex.org/W6754994645","https://openalex.org/W6758859460","https://openalex.org/W6764041417","https://openalex.org/W6767736480","https://openalex.org/W6803022494"],"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/W2128807628","https://openalex.org/W4234264766","https://openalex.org/W2415426693","https://openalex.org/W3009270862"],"abstract_inverted_index":{"Video":[0],"captioning":[1],"is":[2,70,118,127,151],"a":[3,32,37,94,105,138,146,155,181],"joint":[4],"task":[5,30],"of":[6,55,113,141,192],"computer":[7],"vision":[8],"and":[9,45,92,124,166,177,190,215],"natural":[10,22,43],"language":[11,23,44],"processing,":[12],"which":[13,35],"aims":[14],"to":[15,42,63,87,119,128,158,185,206],"describe":[16],"the":[17,52,67,81,116,121,125,131,135,142,160,164,169,187,193,209,213,220,224],"video":[18,56,98],"content":[19],"using":[20],"several":[21],"sentences.":[24],"Nowadays,":[25],"most":[26],"methods":[27,222],"cast":[28],"this":[29,101],"as":[31,154],"mapping":[33,38,65],"problem,":[34],"learns":[36],"from":[39,49],"visual":[40,143],"features":[41],"generates":[46],"captions":[47],"directly":[48],"videos.":[50],"However,":[51],"underlying":[53],"challenge":[54],"captioning,":[57],"<italic":[58],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[59],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">i</i>":[60],".e.,":[61],"sequence":[62,64,198],"across":[66],"different":[68],"domains,":[69],"still":[71],"not":[72],"well":[73],"handled.":[74],"To":[75],"address":[76],"these":[77],"problems,":[78],"we":[79,103,202],"introduce":[80],"polishing":[82,90,109],"mechanism":[83,172],"in":[84,145],"an":[85],"attempt":[86],"mimic":[88],"human":[89],"process":[91],"propose":[93,104],"generate-and-polish":[95],"framework":[96],"for":[97,173,196],"captioning.":[99],"In":[100,200],"paper,":[102],"two-step":[106],"transformer":[107],"based":[108],"network":[110],"(TSTPN)":[111],"consisting":[112],"two":[114],"sub-modules:":[115],"generation-module":[117],"generate":[120],"caption":[122],"candidate":[123,136],"polishing-module":[126],"gradually":[129],"refine":[130],"generated":[132],"candidate.":[133],"Specifically,":[134],"provides":[137,180],"global":[139,182],"information":[140],"contents":[144],"semantically-meaningful":[147],"order,":[148],"where":[149],"it":[150,178],"firstly":[152],"considered":[153],"semantic":[156,161,188],"intersnubber":[157],"bridge":[159],"gap":[162],"between":[163],"text":[165],"video,":[167],"with":[168],"cross-modal":[170,175],"attention":[171],"better":[174,197,217],"modeling;":[176],"secondly":[179],"planning":[183],"ability":[184],"maintain":[186],"consistency":[189],"fluency":[191],"whole":[194],"sentence":[195],"mapping.":[199],"experiments,":[201],"present":[203],"adequate":[204],"evaluations":[205],"show":[207],"that":[208],"proposed":[210],"TSTPN":[211],"achieves":[212],"comparable":[214],"even":[216],"performance":[218],"than":[219],"state-of-the-art":[221],"on":[223],"benchmark":[225],"datasets.":[226]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}