{"id":"https://openalex.org/W4210668396","doi":"https://doi.org/10.1109/tmm.2022.3146005","title":"Dense Video Captioning With Early Linguistic Information Fusion","display_name":"Dense Video Captioning With Early Linguistic Information Fusion","publication_year":2022,"publication_date":"2022-01-25","ids":{"openalex":"https://openalex.org/W4210668396","doi":"https://doi.org/10.1109/tmm.2022.3146005"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2022.3146005","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3146005","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://api.research-repository.uwa.edu.au/ws/files/492632218/Dense_Video_Captioning_With_Early_Linguistic_Information_Fusion.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003668441","display_name":"Nayyer Aafaq","orcid":"https://orcid.org/0000-0003-2763-2094"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Nayyer Aafaq","raw_affiliation_strings":["Department of Computer Science and Software Engineering, The University of Western Australia, Perth, WA, Australia"],"raw_orcid":"https://orcid.org/0000-0003-2763-2094","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Software Engineering, The University of Western Australia, Perth, WA, Australia","institution_ids":["https://openalex.org/I177877127"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089986388","display_name":"Ajmal Mian","orcid":"https://orcid.org/0000-0002-5206-3842"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ajmal Mian","raw_affiliation_strings":["Department of Computer Science and Software Engineering, The University of Western Australia, Perth, WA, Australia"],"raw_orcid":"https://orcid.org/0000-0002-5206-3842","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Software Engineering, The University of Western Australia, Perth, WA, Australia","institution_ids":["https://openalex.org/I177877127"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069697936","display_name":"Naveed Akhtar","orcid":"https://orcid.org/0000-0003-3406-673X"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Naveed Akhtar","raw_affiliation_strings":["Department of Computer Science and Software Engineering, The University of Western Australia, Perth, WA, Australia"],"raw_orcid":"https://orcid.org/0000-0003-3406-673X","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Software Engineering, The University of Western Australia, Perth, WA, Australia","institution_ids":["https://openalex.org/I177877127"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100641142","display_name":"Wei Liu","orcid":"https://orcid.org/0000-0002-7409-0948"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Wei Liu","raw_affiliation_strings":["Department of Computer Science and Software Engineering, The University of Western Australia, Perth, WA, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Software Engineering, The University of Western Australia, Perth, WA, Australia","institution_ids":["https://openalex.org/I177877127"]}]},{"author_position":"last","author":{"id":null,"display_name":"Mubarak Shah","orcid":"https://orcid.org/0000-0002-8216-1128"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mubarak Shah","raw_affiliation_strings":["University of Central Florida, Orlando, FL, USA"],"raw_orcid":"https://orcid.org/0000-0002-8216-1128","affiliations":[{"raw_affiliation_string":"University of Central Florida, Orlando, FL, USA","institution_ids":["https://openalex.org/I106165777"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.7194,"has_fulltext":true,"cited_by_count":40,"citation_normalized_percentile":{"value":0.94488788,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"25","issue":null,"first_page":"2309","last_page":"2322"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9966999888420105,"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":0.9944999814033508,"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/computer-science","display_name":"Computer science","score":0.721798300743103},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.6499538421630859},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6067392230033875},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6033910512924194},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5620734691619873},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.38985615968704224},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1686888039112091}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.721798300743103},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.6499538421630859},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6067392230033875},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6033910512924194},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5620734691619873},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38985615968704224},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1686888039112091},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tmm.2022.3146005","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3146005","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"},{"id":"pmh:oai:pure.atira.dk:publications/2d14ec38-c76a-4224-9c0e-aa633e4b5d0d","is_oa":true,"landing_page_url":"https://research-repository.uwa.edu.au/en/publications/2d14ec38-c76a-4224-9c0e-aa633e4b5d0d","pdf_url":"https://api.research-repository.uwa.edu.au/ws/files/492632218/Dense_Video_Captioning_With_Early_Linguistic_Information_Fusion.pdf","source":{"id":"https://openalex.org/S4306402492","display_name":"UWA Profiles and Research Repository (UWA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177877127","host_organization_name":"The University of Western Australia","host_organization_lineage":["https://openalex.org/I177877127"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Aafaq, N, Mian, A S, Akhtar, N, Liu, W & Shah, M 2023, 'Dense Video Captioning with Early Linguistic Information Fusion', IEEE Transactions on Multimedia, vol. 25, pp. 2309-2322. https://doi.org/10.1109/TMM.2022.3146005","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:publications/2d14ec38-c76a-4224-9c0e-aa633e4b5d0d","is_oa":true,"landing_page_url":"https://research-repository.uwa.edu.au/en/publications/2d14ec38-c76a-4224-9c0e-aa633e4b5d0d","pdf_url":"https://api.research-repository.uwa.edu.au/ws/files/492632218/Dense_Video_Captioning_With_Early_Linguistic_Information_Fusion.pdf","source":{"id":"https://openalex.org/S4306402492","display_name":"UWA Profiles and Research Repository (UWA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177877127","host_organization_name":"The University of Western Australia","host_organization_lineage":["https://openalex.org/I177877127"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Aafaq, N, Mian, A S, Akhtar, N, Liu, W & Shah, M 2023, 'Dense Video Captioning with Early Linguistic Information Fusion', IEEE Transactions on Multimedia, vol. 25, pp. 2309-2322. https://doi.org/10.1109/TMM.2022.3146005","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7799999713897705,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G3406409465","display_name":null,"funder_award_id":"NIPG-2021-001","funder_id":"https://openalex.org/F4320315885","funder_display_name":"Australian Government"},{"id":"https://openalex.org/G7966873392","display_name":null,"funder_award_id":"NIPG-2021-001","funder_id":"https://openalex.org/F4320337300","funder_display_name":"Office of National Intelligence"}],"funders":[{"id":"https://openalex.org/F4320315885","display_name":"Australian Government","ror":"https://ror.org/0314h5y94"},{"id":"https://openalex.org/F4320337300","display_name":"Office of National Intelligence","ror":null},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4210668396.pdf","grobid_xml":"https://content.openalex.org/works/W4210668396.grobid-xml"},"referenced_works_count":106,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1522734439","https://openalex.org/W1586939924","https://openalex.org/W1601567445","https://openalex.org/W1662133657","https://openalex.org/W1797109199","https://openalex.org/W1923332106","https://openalex.org/W1927052826","https://openalex.org/W1945129080","https://openalex.org/W1956340063","https://openalex.org/W1995820507","https://openalex.org/W2084341401","https://openalex.org/W2095661305","https://openalex.org/W2095705004","https://openalex.org/W2101105183","https://openalex.org/W2110933980","https://openalex.org/W2123301721","https://openalex.org/W2139501017","https://openalex.org/W2152984213","https://openalex.org/W2154652894","https://openalex.org/W2159637323","https://openalex.org/W2194775991","https://openalex.org/W2461621749","https://openalex.org/W2471143248","https://openalex.org/W2472970127","https://openalex.org/W2478884216","https://openalex.org/W2493916176","https://openalex.org/W2508191294","https://openalex.org/W2519328139","https://openalex.org/W2552161745","https://openalex.org/W2554906389","https://openalex.org/W2556388456","https://openalex.org/W2557264465","https://openalex.org/W2558834163","https://openalex.org/W2584992898","https://openalex.org/W2597958930","https://openalex.org/W2605035112","https://openalex.org/W2607119937","https://openalex.org/W2607768201","https://openalex.org/W2739107216","https://openalex.org/W2755876276","https://openalex.org/W2766375149","https://openalex.org/W2798725893","https://openalex.org/W2882319491","https://openalex.org/W2883910824","https://openalex.org/W2890718122","https://openalex.org/W2891939431","https://openalex.org/W2896457183","https://openalex.org/W2919115771","https://openalex.org/W2936695845","https://openalex.org/W2949789546","https://openalex.org/W2951183276","https://openalex.org/W2951390634","https://openalex.org/W2952132648","https://openalex.org/W2953461088","https://openalex.org/W2962790054","https://openalex.org/W2962799512","https://openalex.org/W2962990649","https://openalex.org/W2963017553","https://openalex.org/W2963101956","https://openalex.org/W2963177403","https://openalex.org/W2963321993","https://openalex.org/W2963351113","https://openalex.org/W2963504927","https://openalex.org/W2963576560","https://openalex.org/W2963613897","https://openalex.org/W2963699792","https://openalex.org/W2963743213","https://openalex.org/W2963753226","https://openalex.org/W2963758027","https://openalex.org/W2963916161","https://openalex.org/W2964089981","https://openalex.org/W2964214371","https://openalex.org/W2964216549","https://openalex.org/W2964241990","https://openalex.org/W2968101724","https://openalex.org/W2968104955","https://openalex.org/W2970597249","https://openalex.org/W2979401726","https://openalex.org/W2985144848","https://openalex.org/W3009192917","https://openalex.org/W3019301826","https://openalex.org/W3034221024","https://openalex.org/W3034815696","https://openalex.org/W3035365026","https://openalex.org/W3035392611","https://openalex.org/W3096935578","https://openalex.org/W3097607319","https://openalex.org/W3098682680","https://openalex.org/W3109395208","https://openalex.org/W4288083805","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6674330103","https://openalex.org/W6678262379","https://openalex.org/W6682631176","https://openalex.org/W6724997344","https://openalex.org/W6739901393","https://openalex.org/W6748524686","https://openalex.org/W6754478056","https://openalex.org/W6755207826","https://openalex.org/W6761205521","https://openalex.org/W6763701032","https://openalex.org/W6769430610","https://openalex.org/W6775036685","https://openalex.org/W6780226713"],"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/W2949522393","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Dense":[0],"captioning":[1],"methods":[2,44],"generally":[3],"detect":[4],"events":[5],"in":[6,105,130],"videos":[7],"first":[8],"and":[9,32,77,125,187],"then":[10,151],"generate":[11],"captions":[12,112],"for":[13,80,104],"the":[14,23,28,49,68,73,82,93,111,120,126,173,182,191],"individual":[15],"events.":[16],"Events":[17],"are":[18,90,102,150],"localized":[19],"solely":[20],"based":[21],"on":[22,181],"visual":[24,123],"cues":[25],"while":[26],"ignoring":[27],"associated":[29],"linguistic":[30],"information":[31,124],"context.":[33],"Whereas":[34],"end-to-end":[35],"learning":[36,106],"may":[37],"implicitly":[38],"take":[39],"guidance":[40],"from":[41],"language,":[42],"these":[43],"still":[45],"fall":[46],"short":[47],"of":[48,51,109,122,193],"power":[50],"explicit":[52],"modeling.":[53],"In":[54],"this":[55],"paper,":[56],"we":[57,134,166],"propose":[58],"a":[59,115,131,155,168],"<italic":[60,83,96,136,146,156],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[61,84,97,137,147,157],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Visual-Semantic":[62,138],"Embedding":[63],"(ViSE)":[64],"Framework</i>":[65],"that":[66,87],"models":[67],"word(s)-context":[69],"distributional":[70],"properties":[71],"over":[72],"entire":[74],"semantic":[75,116,128],"space":[76,129],"computes":[78],"weights":[79,89,101],"all":[81,110],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">n-grams</i>":[85,98],"such":[86],"higher":[88],"assigned":[91],"to":[92,113,171],"more":[94],"informative":[95],".":[99,143,162],"The":[100,144],"accounted":[103],"distributed":[107],"representations":[108],"construct":[114],"space.":[117],"To":[118],"perform":[119],"contextualization":[121],"constructed":[127],"supervised":[132],"manner,":[133],"design":[135],"Joint":[139],"Modeling":[140],"Network":[141],"(VSJM-Net)</i>":[142],"learned":[145],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">ViSE</i>":[148],"embeddings":[149,175],"temporally":[152],"encoded":[153],"with":[154],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Hierarchical":[158],"Descriptor":[159],"Transformer":[160],"(HDT)</i>":[161],"For":[163],"caption":[164],"generation,":[165],"exploit":[167],"transformer":[169],"architecture":[170],"decode":[172],"input":[174],"into":[176],"natural":[177],"language":[178],"descriptions.":[179],"Experiments":[180],"large-scale":[183],"ActivityNet":[184],"Captions":[185],"dataset":[186,189],"YouCook-II":[188],"demonstrate":[190],"efficacy":[192],"our":[194],"method.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":4}],"updated_date":"2026-07-14T08:27:34.040176","created_date":"2025-10-10T00:00:00"}