{"id":"https://openalex.org/W4293518015","doi":"https://doi.org/10.1109/icme52920.2022.9859882","title":"Dual-Scale Alignment-Based Transformer on Linguistic Skeleton Tags for Non-Autoregressive Video Captioning","display_name":"Dual-Scale Alignment-Based Transformer on Linguistic Skeleton Tags for Non-Autoregressive Video Captioning","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4293518015","doi":"https://doi.org/10.1109/icme52920.2022.9859882"},"language":"en","primary_location":{"id":"doi:10.1109/icme52920.2022.9859882","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme52920.2022.9859882","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5064738683","display_name":"Xian Zhong","orcid":"https://orcid.org/0000-0002-5242-0467"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xian Zhong","raw_affiliation_strings":["Wuhan University of Technology","Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology","institution_ids":["https://openalex.org/I196699116"]},{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100388333","display_name":"Yi Zhang","orcid":"https://orcid.org/0000-0003-4299-1511"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Zhang","raw_affiliation_strings":["Wuhan University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101736130","display_name":"Shuqin Chen","orcid":"https://orcid.org/0000-0003-3436-653X"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuqin Chen","raw_affiliation_strings":["Wuhan University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101456842","display_name":"Zhixin Sun","orcid":"https://orcid.org/0000-0001-6148-9688"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhixin Sun","raw_affiliation_strings":["Wuhan University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041872599","display_name":"Huantao Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huantao Zheng","raw_affiliation_strings":["Wuhan University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103140908","display_name":"Kui Jiang","orcid":"https://orcid.org/0000-0002-4055-7503"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kui Jiang","raw_affiliation_strings":["Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9977999925613403,"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":0.996399998664856,"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":0.8938845992088318},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.797227680683136},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7448660731315613},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6373006105422974},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5435402989387512},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.5130962133407593},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5011608600616455},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.4448885917663574},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.41237831115722656},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34073108434677124},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2166629433631897},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.14945316314697266},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08939623832702637}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8938845992088318},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.797227680683136},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7448660731315613},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6373006105422974},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5435402989387512},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.5130962133407593},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5011608600616455},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.4448885917663574},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.41237831115722656},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34073108434677124},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2166629433631897},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14945316314697266},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08939623832702637},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme52920.2022.9859882","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme52920.2022.9859882","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.550000011920929}],"awards":[{"id":"https://openalex.org/G21274074","display_name":null,"funder_award_id":"2021CFB513,2021CFB281","funder_id":"https://openalex.org/F4320326502","funder_display_name":"Department of Science and Technology, Hubei Provincial People's Government"}],"funders":[{"id":"https://openalex.org/F4320326502","display_name":"Department of Science and Technology, Hubei Provincial People's Government","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2123301721","https://openalex.org/W2142900973","https://openalex.org/W2425121537","https://openalex.org/W2895845501","https://openalex.org/W2896457183","https://openalex.org/W2951390634","https://openalex.org/W2962681491","https://openalex.org/W2962861647","https://openalex.org/W2981575209","https://openalex.org/W2996544626","https://openalex.org/W2996843693","https://openalex.org/W3039060838","https://openalex.org/W3093300941","https://openalex.org/W3101167253","https://openalex.org/W3152798676","https://openalex.org/W3168680617","https://openalex.org/W3171933509","https://openalex.org/W3174046981","https://openalex.org/W3175164646","https://openalex.org/W4205277845","https://openalex.org/W6678262379","https://openalex.org/W6755207826","https://openalex.org/W6769953141","https://openalex.org/W6780578196","https://openalex.org/W6793759846","https://openalex.org/W6797423251"],"related_works":["https://openalex.org/W3107474891","https://openalex.org/W3025136821","https://openalex.org/W3035237998","https://openalex.org/W1978971213","https://openalex.org/W159132833","https://openalex.org/W1567338489","https://openalex.org/W38394648","https://openalex.org/W1517743118","https://openalex.org/W4287888637","https://openalex.org/W4318978824"],"abstract_inverted_index":{"Due":[0],"to":[1,102,117],"the":[2,30,40,59,63,122,135],"characteristic":[3],"of":[4,8,22,65,113,121,137],"one-time":[5],"parallel":[6],"generation":[7],"a":[9,48,72,105],"caption,":[10],"non-autoregressive":[11],"video":[12,73],"captioning":[13],"lacks":[14],"strong":[15],"dependencies":[16,80],"between":[17],"words.":[18],"Although":[19],"using":[20],"guideline":[21],"scene-related":[23],"visual":[24,34,66,95,99],"words":[25,35,67,70,96,100],"can":[26],"promote":[27],"caption":[28],"generation,":[29],"semantic":[31,79],"relations":[32],"among":[33],"are":[36],"barely":[37],"explored,":[38],"limiting":[39],"accurate":[41],"representation.":[42],"To":[43],"this":[44],"end,":[45],"we":[46,108],"propose":[47],"Dual-Scale":[49],"Alignment-based":[50],"transformer":[51],"on":[52,127],"Linguistic":[53],"Skeleton":[54],"Tags":[55],"(DSA-LST),":[56],"which":[57],"alleviates":[58],"defect":[60],"above":[61],"in":[62],"form":[64],"group":[68,101],"(several":[69],"representing":[71],"frame).":[74],"Different":[75],"groups":[76],"represent":[77],"different":[78],"by":[81],"attention.":[82],"We":[83],"utilize":[84],"linguistic":[85],"skeleton":[86],"tags":[87],"(i.e.,":[88],"several":[89],"groups)":[90],"as":[91],"sentence-level":[92],"supervision":[93],"for":[94],"sequence.":[97],"For":[98],"accurately":[103],"express":[104],"specific":[106],"frame,":[107],"further":[109],"design":[110],"dual":[111],"scales":[112],"visual-language":[114],"bi-direction":[115],"alignment":[116],"achieve":[118],"internal":[119],"relevance":[120],"tags.":[123],"Extensive":[124],"experiments":[125],"conducted":[126],"widely":[128],"used":[129],"datasets:":[130],"MSVD":[131],"and":[132],"MSR-VTT":[133],"demonstrate":[134],"effectiveness":[136],"our":[138],"method":[139],"when":[140],"compared":[141],"with":[142],"existing":[143],"approaches.":[144]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}