{"id":"https://openalex.org/W4304014186","doi":"https://doi.org/10.1145/3503161.3551600","title":"Multimodal Analysis for Deep Video Understanding with Video Language Transformer","display_name":"Multimodal Analysis for Deep Video Understanding with Video Language Transformer","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304014186","doi":"https://doi.org/10.1145/3503161.3551600"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3551600","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3551600","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":"Proceedings of the 30th ACM International Conference on Multimedia","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/A5100441018","display_name":"Beibei Zhang","orcid":"https://orcid.org/0009-0005-2301-8160"},"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":true,"raw_author_name":"Beibei Zhang","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109589641","display_name":"Yaqun Fang","orcid":null},"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":null,"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084591510","display_name":"Tongwei Ren","orcid":"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":null,"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"},"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":null,"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100441018"],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":0.2386,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.58219761,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7165","last_page":"7169"},"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":0.9998999834060669,"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":0.9976000189781189,"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":0.8406761884689331},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7308053374290466},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5049465298652649},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49872446060180664},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.45406976342201233},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.44797956943511963},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43789368867874146},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.34982529282569885},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3359905481338501},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.33168458938598633}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8406761884689331},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7308053374290466},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5049465298652649},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49872446060180664},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.45406976342201233},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.44797956943511963},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43789368867874146},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.34982529282569885},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3359905481338501},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33168458938598633},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3551600","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3551600","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6200000047683716}],"awards":[{"id":"https://openalex.org/G5028012422","display_name":null,"funder_award_id":"BK20191248","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"}],"funders":[{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2080873731","https://openalex.org/W2157982431","https://openalex.org/W2243279568","https://openalex.org/W2765137706","https://openalex.org/W2788865504","https://openalex.org/W2883429621","https://openalex.org/W2949178656","https://openalex.org/W2963524571","https://openalex.org/W3021553284","https://openalex.org/W3034364644","https://openalex.org/W3035124602","https://openalex.org/W3035265375","https://openalex.org/W3105473141","https://openalex.org/W3168640669","https://openalex.org/W4205645931"],"related_works":["https://openalex.org/W3107474891","https://openalex.org/W3114564740","https://openalex.org/W2115485936","https://openalex.org/W4312298165","https://openalex.org/W3173727152","https://openalex.org/W4312635861","https://openalex.org/W1539663307","https://openalex.org/W1578250328","https://openalex.org/W1964409860","https://openalex.org/W1986230959"],"abstract_inverted_index":{"The":[0,77],"Deep":[1],"Video":[2],"Understanding":[3],"Challenge":[4],"(DVUC)":[5],"is":[6],"aimed":[7],"to":[8,13,37,51],"use":[9,32,63],"multiple":[10,40,59],"modality":[11],"information":[12,70],"build":[14],"high-level":[15],"understanding":[16],"of":[17,55,90,98,104],"video,":[18],"involving":[19],"tasks":[20,41],"such":[21],"as":[22],"relationship":[23],"recognition":[24],"and":[25,46,62,93,101],"interaction":[26],"detection.":[27],"In":[28,49],"this":[29],"paper,":[30],"we":[31,57],"a":[33],"joint":[34],"learning":[35],"framework":[36],"simultaneously":[38],"predict":[39],"with":[42,74],"visual,":[43],"text,":[44],"audio":[45],"pose":[47],"features.":[48],"addition,":[50],"answer":[52],"the":[53],"queries":[54],"DVUC,":[56],"design":[58],"answering":[60],"strategies":[61],"video":[64],"language":[65],"transformer":[66],"which":[67],"learns":[68],"cross-modal":[69],"for":[71,87,96],"matching":[72],"videos":[73],"text":[75],"choices.":[76],"final":[78],"DVUC":[79],"result":[80],"shows":[81],"that":[82],"our":[83],"method":[84],"ranks":[85,94],"first":[86],"group":[88,99,102],"one":[89,100],"movie-level":[91],"queries,":[92],"third":[95],"both":[97],"two":[103],"scene-level":[105],"queries.":[106]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3}],"updated_date":"2026-04-28T14:05:53.105641","created_date":"2025-10-10T00:00:00"}