{"id":"https://openalex.org/W4387969760","doi":"https://doi.org/10.1145/3581783.3612863","title":"Deep Video Understanding with Video-Language Model","display_name":"Deep Video Understanding with Video-Language Model","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387969760","doi":"https://doi.org/10.1145/3581783.3612863"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612863","doi":"https://doi.org/10.1145/3581783.3612863","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612863","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612863","source":{"id":"https://openalex.org/S4363608757","display_name":"ACM International Conference on Multimedia (ACM MM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612863","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101743925","display_name":"Runze Liu","orcid":"https://orcid.org/0009-0000-9993-9576","observed_orcids":["https://orcid.org/0009-0000-9993-9576"]},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Runze Liu","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0000-9993-9576","affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001427581","display_name":"Yaqun Fang","orcid":"https://orcid.org/0009-0001-9065-968X","observed_orcids":["https://orcid.org/0009-0001-9065-968X"]},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaqun Fang","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0001-9065-968X","affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101824411","display_name":"Fan Yu","orcid":"https://orcid.org/0000-0003-2789-0325","observed_orcids":["https://orcid.org/0000-0003-2789-0325"]},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Yu","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-2789-0325","affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049195096","display_name":"Ruiming Tian","orcid":"https://orcid.org/0009-0000-7840-7159","observed_orcids":["https://orcid.org/0009-0000-7840-7159"]},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ruiqi Tian","raw_affiliation_strings":["University of British Columbia, Vancouver, Canada"],"raw_orcid":"https://orcid.org/0009-0000-7840-7159","affiliations":[{"raw_affiliation_string":"University of British Columbia, Vancouver, Canada","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084591510","display_name":"Tongwei Ren","orcid":"https://orcid.org/0000-0003-3092-424X","observed_orcids":["https://orcid.org/0000-0003-3092-424X"]},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tongwei Ren","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-3092-424X","affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101546753","display_name":"Gangshan Wu","orcid":"https://orcid.org/0000-0003-1391-1762","observed_orcids":["https://orcid.org/0000-0003-1391-1762"]},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gangshan Wu","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-1391-1762","affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1759,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.46741103,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"9551","last_page":"9555"},"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":0.0,"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/T11439","display_name":"Video Analysis and Summarization","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/video-language-models","display_name":"video-language models","score":0.9269999861717224},{"id":"https://openalex.org/keywords/multimodal-question-answering","display_name":"multimodal question answering","score":0.9380000233650208},{"id":"https://openalex.org/keywords/long-form-video","display_name":"long-form video","score":0.7960000038146973},{"id":"https://openalex.org/keywords/knowledge-graphs","display_name":"knowledge graphs","score":0.8809999823570251},{"id":"https://openalex.org/keywords/multimodal-fusion","display_name":"multimodal fusion","score":0.8859999775886536},{"id":"https://openalex.org/keywords/video-summarization","display_name":"video summarization","score":0.765999972820282},{"id":"https://openalex.org/keywords/scene-description","display_name":"scene description","score":0.6819999814033508}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8803389072418213},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5804054737091064},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5167128443717957},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5130195021629333},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5116851329803467},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4897937774658203},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.43471765518188477},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.4199722409248352},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3425498604774475},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3404616415500641},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3385026156902313},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.323359876871109},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.14059990644454956},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0855749249458313},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612863","doi":"https://doi.org/10.1145/3581783.3612863","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612863","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612863","source":{"id":"https://openalex.org/S4363608757","display_name":"ACM International Conference on Multimedia (ACM MM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3581783.3612863","doi":"https://doi.org/10.1145/3581783.3612863","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612863","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612863","source":{"id":"https://openalex.org/S4363608757","display_name":"ACM International Conference on Multimedia (ACM MM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G4388298099","display_name":null,"funder_award_id":"021714380026","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G6005646369","display_name":null,"funder_award_id":"62072232","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G7458595415","display_name":"\u9762\u5411\u590d\u6742\u573a\u666f\u89c6\u9891\u7684\u89c6\u89c9\u5173\u7cfb\u68c0\u6d4b\u65b9\u6cd5\u7814\u7a76","funder_award_id":"62072232","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387969760.pdf","grobid_xml":"https://content.openalex.org/works/W4387969760.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W3021553284","https://openalex.org/W3034364644","https://openalex.org/W3165766112","https://openalex.org/W4205645931","https://openalex.org/W4285606530","https://openalex.org/W4304013709","https://openalex.org/W4304087177","https://openalex.org/W4304092154","https://openalex.org/W4304097992","https://openalex.org/W4312614039","https://openalex.org/W7133182950"],"related_works":["https://openalex.org/W4304014186","https://openalex.org/W4304013709","https://openalex.org/W4393213853","https://openalex.org/W7129109165","https://openalex.org/W4387969536","https://openalex.org/W7123307713","https://openalex.org/W4416281167","https://openalex.org/W4403725941","https://openalex.org/W7221366401","https://openalex.org/W4393148256"],"abstract_inverted_index":{"Pre-trained":[0],"video-language":[1],"models":[2],"(VLMs)":[3],"have":[4],"shown":[5],"superior":[6],"performance":[7],"in":[8,31],"high-level":[9],"video":[10],"understanding":[11],"tasks,":[12],"analyzing":[13],"multi-modal":[14],"information,":[15],"aligning":[16],"with":[17,76],"Deep":[18],"Video":[19,45],"Understanding":[20],"Challenge":[21],"(DVUC)":[22],"requirements.In":[23],"this":[24],"paper,":[25],"we":[26],"explore":[27],"pre-trained":[28],"VLMs'":[29],"potential":[30],"multimodal":[32,68],"question":[33],"answering":[34],"for":[35],"long-form":[36],"videos.":[37],"We":[38],"propose":[39],"a":[40,87,98],"solution":[41],"called":[42],"Dual":[43],"Branches":[44],"Modeling":[46],"(DBVM),":[47],"which":[48],"combines":[49],"knowledge":[50],"graph":[51],"(KG)":[52],"and":[53,58,64,73,80,97],"VLMs,":[54],"leveraging":[55],"their":[56],"strengths":[57],"addressing":[59],"shortcomings.The":[60],"KG":[61],"branch":[62,85],"recognizes":[63],"localizes":[65],"entities,":[66],"fuses":[67],"features":[69],"at":[70],"different":[71],"levels,":[72],"constructs":[74],"KGs":[75],"entities":[77],"as":[78,82],"nodes":[79],"relationships":[81],"edges.The":[83],"VLM":[84],"applies":[86],"selection":[88],"strategy":[89,100],"to":[90,101],"adapt":[91],"input":[92],"movies":[93],"into":[94],"acceptable":[95],"length":[96],"cross-matching":[99],"post-process":[102],"results":[103],"providing":[104],"accurate":[105],"scene":[106],"descriptions.Experiments":[107],"conducted":[108],"on":[109],"the":[110,114],"DVUC":[111],"dataset":[112],"validate":[113],"effectiveness":[115],"of":[116],"our":[117],"DBVM.":[118]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2023-10-28T00:00:00"}