{"id":"https://openalex.org/W4229444697","doi":"https://doi.org/10.1145/3512527.3531380","title":"Dual-Level Decoupled Transformer for Video Captioning","display_name":"Dual-Level Decoupled Transformer for Video Captioning","publication_year":2022,"publication_date":"2022-06-23","ids":{"openalex":"https://openalex.org/W4229444697","doi":"https://doi.org/10.1145/3512527.3531380"},"language":"en","primary_location":{"id":"doi:10.1145/3512527.3531380","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3512527.3531380","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"preprint","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/A5044936257","display_name":"Yiqi Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yiqi Gao","raw_affiliation_strings":["Northwestern Polytechnical University & National Engineering Lab for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University & National Engineering Lab for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103210333","display_name":"Xinglin Hou","orcid":"https://orcid.org/0000-0002-8642-0772"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinglin Hou","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077386763","display_name":"Wei Suo","orcid":"https://orcid.org/0000-0002-8283-8637"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Suo","raw_affiliation_strings":["Northwestern Polytechnical University & National Engineering Lab for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University & National Engineering Lab for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055917672","display_name":"Mengyang Sun","orcid":"https://orcid.org/0000-0003-0638-3295"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengyang Sun","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University;National Engineering Lab for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, Xi'an, China","School of Computer Science, Northwestern Polytechnical University"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University;National Engineering Lab for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027308029","display_name":"Tiezheng Ge","orcid":"https://orcid.org/0000-0003-1381-2692"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tiezheng Ge","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074655314","display_name":"Yuning Jiang","orcid":"https://orcid.org/0000-0002-7145-0995"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuning Jiang","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100396097","display_name":"Peng Wang","orcid":"https://orcid.org/0000-0002-9218-9132"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Wang","raw_affiliation_strings":["Northwestern Polytechnical University & National Engineering Lab for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University & National Engineering Lab for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5044936257"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":1.36170981,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.78296724,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"219","last_page":"228"},"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":0.9991000294685364,"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":0.9882000088691711,"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":0.8886234760284424},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8545387983322144},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6645887494087219},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5802193880081177},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5469622015953064},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.4750630557537079},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.45913487672805786},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4331142008304596},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41346514225006104},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.41070735454559326},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.410099059343338},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.21057680249214172},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.12561959028244019},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.07730346918106079}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8886234760284424},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8545387983322144},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6645887494087219},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5802193880081177},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5469622015953064},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.4750630557537079},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.45913487672805786},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4331142008304596},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41346514225006104},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.41070735454559326},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.410099059343338},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.21057680249214172},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.12561959028244019},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.07730346918106079},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3512527.3531380","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3512527.3531380","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6299999952316284}],"awards":[{"id":"https://openalex.org/G4888510474","display_name":null,"funder_award_id":"No. U19B2037, No. 61876152","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5353464696","display_name":null,"funder_award_id":"No. 2021JCW-03","funder_id":"https://openalex.org/F4320336567","funder_display_name":"Natural Science Basic Research Program of Shaanxi Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320336567","display_name":"Natural Science Basic Research Program of Shaanxi Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1586939924","https://openalex.org/W1601567445","https://openalex.org/W2194775991","https://openalex.org/W2425121537","https://openalex.org/W2584992898","https://openalex.org/W2739107216","https://openalex.org/W2740388348","https://openalex.org/W2755876276","https://openalex.org/W2765658575","https://openalex.org/W2896878184","https://openalex.org/W2905145027","https://openalex.org/W2948358897","https://openalex.org/W2951390634","https://openalex.org/W2962681491","https://openalex.org/W2962990649","https://openalex.org/W2963084599","https://openalex.org/W2963524571","https://openalex.org/W2979826702","https://openalex.org/W2984862483","https://openalex.org/W2988753485","https://openalex.org/W2989322838","https://openalex.org/W3034221024","https://openalex.org/W3034655362","https://openalex.org/W3035160838","https://openalex.org/W3035365026","https://openalex.org/W3035392611","https://openalex.org/W3035635319","https://openalex.org/W3039060838","https://openalex.org/W3096935578","https://openalex.org/W3121523901","https://openalex.org/W3131500599","https://openalex.org/W3176425931","https://openalex.org/W3176689360"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3088136942","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W4290852288","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W3161079477"],"abstract_inverted_index":{"Video":[0],"captioning":[1],"aims":[2],"to":[3,19,26,109,137,159],"understand":[4],"the":[5,10,44,57,69,83,88,111,121,129,139,146,162,185,190,198],"spatio-temporal":[6,51,62,117],"semantic":[7,92,166],"concept":[8],"of":[9,90,123,131,164,184,200],"video":[11,50,116,201],"and":[12,53,76,93,141,144,167,178,188],"generate":[13],"descriptive":[14],"sentences.":[15],"The":[16],"de-facto":[17],"approach":[18],"this":[20,98],"task":[21,199],"dictates":[22],"a":[23,65,104,194],"text":[24],"generator":[25],"learn":[27],"from":[28,34,43],"offline-extracted":[29],"motion":[30],"or":[31],"appearance":[32],"features":[33],"pre-trained":[35],"vision":[36],"models.":[37],"However,":[38],"these":[39],"methods":[40,192],"may":[41],"suffer":[42],"so-called":[45],"\"couple\"":[46,59,85],"drawbacks":[47],"on":[48,172],"both":[49],"representation":[52,63],"sentence":[54,153],"generation.":[55],"For":[56],"former,":[58],"means":[60,86],"learning":[61],"in":[64,73,197],"single":[66],"model(3DCNN),":[67],"resulting":[68],"problems":[70],"named":[71],"disconnection":[72],"task/pre-train":[74],"domain":[75],"hard":[77],"for":[78,82,115,152],"end-to-end":[79,149],"training.":[80],"As":[81],"latter,":[84],"treating":[87],"generation":[89],"visual":[91,165],"syntax-related":[94,168],"words":[95],"equally.":[96],"To":[97],"end,":[99],"we":[100,119,155],"present":[101],"D2":[102,187],"-":[103],"dual-level":[105],"decoupled":[106],"transformer":[107],"pipeline":[108],"solve":[110],"above":[112],"drawbacks:":[113],"(i)":[114],"representation,":[118],"decouple":[120],"process":[122],"it":[124],"into":[125],"\"first-spatial-then-temporal\"":[126],"paradigm,":[127],"releasing":[128],"potential":[130,183],"using":[132],"dedicated":[133],"model(e.g.":[134],"image-text":[135],"pre-training)":[136],"connect":[138],"pre-training":[140],"downstream":[142],"tasks,":[143],"makes":[145],"entire":[147],"model":[148],"trainable.":[150],"(ii)":[151],"generation,":[154],"propose":[156],"Syntax-Aware":[157],"Decoder":[158],"dynamically":[160],"measure":[161],"contribution":[163],"words.":[169],"Extensive":[170],"experiments":[171],"three":[173],"widely-used":[174],"benchmarks":[175],"(MSVD,":[176],"MSR-VTT":[177],"VATEX)":[179],"have":[180],"shown":[181],"great":[182],"proposed":[186],"surpassed":[189],"previous":[191],"by":[193],"large":[195],"margin":[196],"captioning.":[202]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}