{"id":"https://openalex.org/W7137844102","doi":"https://doi.org/10.1609/aaai.v40i7.37450","title":"Explicit Temporal-Semantic Modeling for Dense Video Captioning via Context-Aware Cross-Modal Interaction","display_name":"Explicit Temporal-Semantic Modeling for Dense Video Captioning via Context-Aware Cross-Modal Interaction","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137844102","doi":"https://doi.org/10.1609/aaai.v40i7.37450"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i7.37450","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i7.37450","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37450/41412","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37450/41412","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5099478071","display_name":"Mingda Jia","orcid":null},"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":true,"raw_author_name":"Mingda Jia","raw_affiliation_strings":["MAIS, Institute of Automation, Chinese Academy of Sciences\nSchool of Artificial Intelligence, University of Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"MAIS, Institute of Automation, Chinese Academy of Sciences\nSchool of Artificial Intelligence, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129716570","display_name":"Weiliang Meng","orcid":null},"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":"Weiliang Meng","raw_affiliation_strings":["MAIS, Institute of Automation, Chinese Academy of Sciences\nSchool of Artificial Intelligence, University of Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"MAIS, Institute of Automation, Chinese Academy of Sciences\nSchool of Artificial Intelligence, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125683832","display_name":"Zenghuang Fu","orcid":null},"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":"Zenghuang Fu","raw_affiliation_strings":["MAIS, Institute of Automation, Chinese Academy of Sciences\nSchool of Artificial Intelligence, University of Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"MAIS, Institute of Automation, Chinese Academy of Sciences\nSchool of Artificial Intelligence, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129743057","display_name":"Yiheng Li","orcid":null},"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":"Yiheng Li","raw_affiliation_strings":["MAIS, Institute of Automation, Chinese Academy of Sciences\nSchool of Artificial Intelligence, University of Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"MAIS, Institute of Automation, Chinese Academy of Sciences\nSchool of Artificial Intelligence, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129738356","display_name":"Qi Zeng","orcid":null},"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":"Qi Zeng","raw_affiliation_strings":["MAIS, Institute of Automation, Chinese Academy of Sciences\nSchool of Artificial Intelligence, University of Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"MAIS, Institute of Automation, Chinese Academy of Sciences\nSchool of Artificial Intelligence, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129725849","display_name":"Yifan Zhang","orcid":null},"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":"Yifan Zhang","raw_affiliation_strings":["MAIS, Institute of Automation, Chinese Academy of Sciences\nSchool of Artificial Intelligence, University of Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"MAIS, Institute of Automation, Chinese Academy of Sciences\nSchool of Artificial Intelligence, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129715635","display_name":"Ju Xin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210161360","display_name":"Institute of Navigation","ror":"https://ror.org/05rmpy443","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210161360"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ju Xin","raw_affiliation_strings":["The Navigation Guarantee Center Of North China Sea"],"affiliations":[{"raw_affiliation_string":"The Navigation Guarantee Center Of North China Sea","institution_ids":["https://openalex.org/I4210161360"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129695553","display_name":"Rongtao Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I2800497579","display_name":"CRC for Spatial information","ror":"https://ror.org/022482e21","country_code":"AU","type":"facility","lineage":["https://openalex.org/I2800497579"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Rongtao Xu","raw_affiliation_strings":["Spatialtemporal AI"],"affiliations":[{"raw_affiliation_string":"Spatialtemporal AI","institution_ids":["https://openalex.org/I2800497579"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101620304","display_name":"Jiguang Zhang","orcid":"https://orcid.org/0000-0002-8212-1361"},"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":"Jiguang Zhang","raw_affiliation_strings":["MAIS, Institute of Automation, Chinese Academy of Sciences\nSchool of Artificial Intelligence, University of Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"MAIS, Institute of Automation, Chinese Academy of Sciences\nSchool of Artificial Intelligence, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129738862","display_name":"Xiaopeng Zhang","orcid":null},"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":"Xiaopeng Zhang","raw_affiliation_strings":["MAIS, Institute of Automation, Chinese Academy of Sciences\nSchool of Artificial Intelligence, University of Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"MAIS, Institute of Automation, Chinese Academy of Sciences\nSchool of Artificial Intelligence, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5099478071"],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06716418,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"7","first_page":"5341","last_page":"5349"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9904999732971191,"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":0.9904999732971191,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0015999999595806003,"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":0.0012000000569969416,"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":0.9483000040054321},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6913999915122986},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6556000113487244},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.6115999817848206},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5679000020027161},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5572999715805054},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4717000126838684}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9483000040054321},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8069000244140625},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6913999915122986},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6556000113487244},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.6115999817848206},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5679000020027161},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5572999715805054},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5151000022888184},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49390000104904175},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4717000126838684},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.46560001373291016},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.421099990606308},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.34450000524520874},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.32330000400543213},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2824000120162964},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.25429999828338623}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i7.37450","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i7.37450","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37450/41412","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i7.37450","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i7.37450","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37450/41412","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7137844102.pdf","grobid_xml":"https://content.openalex.org/works/W7137844102.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Dense":[0],"video":[1,41,143],"captioning":[2,144],"jointly":[3],"localizes":[4],"and":[5,21,52,81,111,131],"captions":[6],"salient":[7],"events":[8],"in":[9],"untrimmed":[10],"videos.":[11],"Recent":[12],"methods":[13],"primarily":[14],"focus":[15],"on":[16,33,127,141],"leveraging":[17],"additional":[18],"prior":[19],"knowledge":[20],"advanced":[22],"multi-task":[23],"architectures":[24],"to":[25,44,101,118],"achieve":[26],"competitive":[27],"performance.":[28],"However,":[29],"these":[30],"pipelines":[31],"rely":[32],"implicit":[34],"modeling":[35,66],"that":[36,135],"uses":[37],"frame-level":[38],"or":[39],"fragmented":[40],"features,":[42],"failing":[43],"capture":[45],"the":[46,128,138],"temporal":[47,77],"coherence":[48],"across":[49],"event":[50],"sequences":[51],"comprehensive":[53],"semantics":[54,83],"within":[55,79],"visual":[56,120],"contexts.":[57],"To":[58],"address":[59],"this,":[60],"we":[61],"propose":[62],"an":[63],"explicit":[64],"temporal-semantic":[65],"framework":[67],"called":[68],"Context-Aware":[69],"Cross-Modal":[70],"Interaction":[71],"(CACMI),":[72],"which":[73],"leverages":[74],"both":[75],"latent":[76],"characteristics":[78],"videos":[80],"linguistic":[82],"from":[84],"text":[85],"corpus.":[86],"Specifically,":[87],"our":[88],"model":[89],"consists":[90],"of":[91],"two":[92],"core":[93],"components:":[94],"Cross-modal":[95],"Frame":[96],"Aggregation":[97],"aggregates":[98],"relevant":[99],"frames":[100],"extract":[102],"temporally":[103],"coherent,":[104],"event-aligned":[105],"textual":[106],"features":[107],"through":[108],"cross-modal":[109],"retrieval;":[110],"Context-aware":[112],"Feature":[113],"Enhancement":[114],"utilizes":[115],"query-guided":[116],"attention":[117],"integrate":[119],"dynamics":[121],"with":[122],"pseudo-event":[123],"semantics.":[124],"Extensive":[125],"experiments":[126],"ActivityNet":[129],"Captions":[130],"YouCook2":[132],"datasets":[133],"demonstrate":[134],"CACMI":[136],"achieves":[137],"state-of-the-art":[139],"performance":[140],"dense":[142],"task.":[145]},"counts_by_year":[],"updated_date":"2026-03-20T20:47:17.329874","created_date":"2026-03-18T00:00:00"}