{"id":"https://openalex.org/W4392903697","doi":"https://doi.org/10.1109/icassp48485.2024.10447469","title":"MSG-BART: Multi-Granularity Scene Graph-Enhanced Encoder-Decoder Language Model for Video-Grounded Dialogue Generation","display_name":"MSG-BART: Multi-Granularity Scene Graph-Enhanced Encoder-Decoder Language Model for Video-Grounded Dialogue Generation","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903697","doi":"https://doi.org/10.1109/icassp48485.2024.10447469"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447469","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447469","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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/A5100778701","display_name":"Hongcheng Liu","orcid":"https://orcid.org/0009-0000-3271-9544"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I4210099312","display_name":"Shandong Jiaotong University","ror":"https://ror.org/01848hk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099312"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongcheng Liu","raw_affiliation_strings":["Shanghai Jiao Tong University,Cooperative Medianet Innovation Center","Cooperative Medianet Innovation Center, Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Cooperative Medianet Innovation Center","institution_ids":["https://openalex.org/I4210099312","https://openalex.org/I183067930"]},{"raw_affiliation_string":"Cooperative Medianet Innovation Center, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I4210099312","https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100457773","display_name":"Zhe Chen","orcid":"https://orcid.org/0000-0003-4599-1170"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I4210099312","display_name":"Shandong Jiaotong University","ror":"https://ror.org/01848hk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099312"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhe Chen","raw_affiliation_strings":["Shanghai Jiao Tong University,Cooperative Medianet Innovation Center","Cooperative Medianet Innovation Center, Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Cooperative Medianet Innovation Center","institution_ids":["https://openalex.org/I4210099312","https://openalex.org/I183067930"]},{"raw_affiliation_string":"Cooperative Medianet Innovation Center, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I4210099312","https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100623330","display_name":"Hui Li","orcid":"https://orcid.org/0000-0002-7333-6942"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I4210099312","display_name":"Shandong Jiaotong University","ror":"https://ror.org/01848hk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099312"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Li","raw_affiliation_strings":["Shanghai Jiao Tong University,Cooperative Medianet Innovation Center","Cooperative Medianet Innovation Center, Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Cooperative Medianet Innovation Center","institution_ids":["https://openalex.org/I4210099312","https://openalex.org/I183067930"]},{"raw_affiliation_string":"Cooperative Medianet Innovation Center, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I4210099312","https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113123604","display_name":"Pingjie Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I4210099312","display_name":"Shandong Jiaotong University","ror":"https://ror.org/01848hk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099312"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pingjie Wang","raw_affiliation_strings":["Shanghai Jiao Tong University,Cooperative Medianet Innovation Center","Cooperative Medianet Innovation Center, Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Cooperative Medianet Innovation Center","institution_ids":["https://openalex.org/I4210099312","https://openalex.org/I183067930"]},{"raw_affiliation_string":"Cooperative Medianet Innovation Center, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I4210099312","https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100645703","display_name":"Yanfeng Wang","orcid":"https://orcid.org/0000-0001-7873-6577"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I4210099312","display_name":"Shandong Jiaotong University","ror":"https://ror.org/01848hk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099312"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanfeng Wang","raw_affiliation_strings":["Shanghai Jiao Tong University,Cooperative Medianet Innovation Center","Cooperative Medianet Innovation Center, Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Cooperative Medianet Innovation Center","institution_ids":["https://openalex.org/I4210099312","https://openalex.org/I183067930"]},{"raw_affiliation_string":"Cooperative Medianet Innovation Center, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I4210099312","https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100445125","display_name":"Yu Wang","orcid":"https://orcid.org/0000-0001-9500-081X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I4210099312","display_name":"Shandong Jiaotong University","ror":"https://ror.org/01848hk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099312"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Wang","raw_affiliation_strings":["Shanghai Jiao Tong University,Cooperative Medianet Innovation Center","Cooperative Medianet Innovation Center, Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Cooperative Medianet Innovation Center","institution_ids":["https://openalex.org/I4210099312","https://openalex.org/I183067930"]},{"raw_affiliation_string":"Cooperative Medianet Innovation Center, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I4210099312","https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6131,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.64909139,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"10516","last_page":"10520"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9919000267982483,"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":0.840095043182373},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7011614441871643},{"id":"https://openalex.org/keywords/pointer","display_name":"Pointer (user interface)","score":0.573756992816925},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.49929308891296387},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4963575005531311},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.48960715532302856},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4741605818271637},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4243495464324951},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.41679248213768005},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.35402488708496094},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34708550572395325},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.20843595266342163},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10980620980262756}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.840095043182373},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7011614441871643},{"id":"https://openalex.org/C150202949","wikidata":"https://www.wikidata.org/wiki/Q107602","display_name":"Pointer (user interface)","level":2,"score":0.573756992816925},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.49929308891296387},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4963575005531311},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.48960715532302856},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4741605818271637},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4243495464324951},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41679248213768005},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.35402488708496094},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34708550572395325},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.20843595266342163},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10980620980262756},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447469","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447469","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2751525844","https://openalex.org/W2889844776","https://openalex.org/W2902687238","https://openalex.org/W2998166190","https://openalex.org/W3008593790","https://openalex.org/W3034472388","https://openalex.org/W3034999214","https://openalex.org/W3035520612","https://openalex.org/W3137384391","https://openalex.org/W3137797626","https://openalex.org/W3168640669","https://openalex.org/W3176750236","https://openalex.org/W3186621246","https://openalex.org/W3200114289","https://openalex.org/W3205782068","https://openalex.org/W4221141684","https://openalex.org/W4284898017","https://openalex.org/W4287889327","https://openalex.org/W4364382977","https://openalex.org/W4378174011","https://openalex.org/W4380032287","https://openalex.org/W4382461806","https://openalex.org/W4389519587","https://openalex.org/W4395091069","https://openalex.org/W6774609993","https://openalex.org/W6779087587","https://openalex.org/W6801567822","https://openalex.org/W6810164656","https://openalex.org/W6851317108","https://openalex.org/W6853089504"],"related_works":["https://openalex.org/W2931688134","https://openalex.org/W2377919138","https://openalex.org/W2378857091","https://openalex.org/W103652678","https://openalex.org/W4226090359","https://openalex.org/W2059697060","https://openalex.org/W936373746","https://openalex.org/W2975817033","https://openalex.org/W4382701072","https://openalex.org/W3007164922"],"abstract_inverted_index":{"Generating":[0],"dialogue":[1,123],"grounded":[2],"in":[3,17],"videos":[4],"requires":[5],"a":[6,48,62,106,136],"high":[7],"level":[8],"of":[9,57,130,138],"understanding":[10],"and":[11,33,78,85,93,114],"reasoning":[12,95],"about":[13],"the":[14,18,55,76,83,100,127,131],"visual":[15],"scenes":[16],"videos.":[19],"However,":[20],"existing":[21],"large":[22],"visual-language":[23],"models":[24],"are":[25,118],"not":[26],"effective":[27],"due":[28],"to":[29,39,88,109,135],"their":[30],"latent":[31],"features":[32],"decoder-only":[34],"structure,":[35],"especially":[36],"with":[37],"respect":[38],"spatio-temporal":[40,64],"relationship":[41],"reasoning.":[42],"In":[43],"this":[44],"paper,":[45],"we":[46,74,104],"propose":[47,105],"novel":[49],"approach":[50],"named":[51],"MSG-BART,":[52],"which":[53,125],"enhances":[54],"integration":[56],"video":[58],"information":[59,101],"by":[60],"incorporating":[61],"multi-granularity":[63],"scene":[65,80],"graph":[66,81],"into":[67,82],"an":[68],"encoder-decoder":[69],"pre-trained":[70],"language":[71],"model.":[72],"Specifically,":[73],"integrate":[75],"global":[77],"local":[79],"encoder":[84],"decoder,":[86],"respectively,":[87],"improve":[89,99],"both":[90],"overall":[91],"perception":[92],"target":[94],"capability.":[96],"To":[97],"further":[98],"selection":[102,111],"capability,":[103],"multi-pointer":[107],"network":[108],"facilitate":[110],"between":[112],"text":[113],"video.":[115],"Extensive":[116],"experiments":[117],"conducted":[119],"on":[120],"three":[121],"video-grounded":[122],"benchmarks,":[124],"show":[126],"significant":[128],"superiority":[129],"proposed":[132],"MSG-BART":[133],"compared":[134],"range":[137],"state-of-the-art":[139],"approaches.":[140]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}