{"id":"https://openalex.org/W4387969090","doi":"https://doi.org/10.1145/3581783.3612132","title":"Graph-Based Video-Language Learning with Multi-Grained Audio-Visual Alignment","display_name":"Graph-Based Video-Language Learning with Multi-Grained Audio-Visual Alignment","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387969090","doi":"https://doi.org/10.1145/3581783.3612132"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612132","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612132","pdf_url":null,"source":null,"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"},"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/A5093130749","display_name":"Chenyang Lyu","orcid":"https://orcid.org/0009-0002-6733-5879"},"institutions":[{"id":"https://openalex.org/I42934936","display_name":"Dublin City University","ror":"https://ror.org/04a1a1e81","country_code":"IE","type":"education","lineage":["https://openalex.org/I42934936"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Chenyang Lyu","raw_affiliation_strings":["Dublin City University, Dublin, Ireland"],"raw_orcid":"https://orcid.org/0009-0002-6733-5879","affiliations":[{"raw_affiliation_string":"Dublin City University, Dublin, Ireland","institution_ids":["https://openalex.org/I42934936"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052375254","display_name":"Wenxi Li","orcid":"https://orcid.org/0000-0001-8449-0489"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenxi Li","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-8449-0489","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071808662","display_name":"Tianbo Ji","orcid":"https://orcid.org/0000-0003-0143-6220"},"institutions":[{"id":"https://openalex.org/I199305430","display_name":"Nantong University","ror":"https://ror.org/02afcvw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I199305430"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianbo Ji","raw_affiliation_strings":["Nantong University, Nantong, China"],"raw_orcid":"https://orcid.org/0000-0003-0143-6220","affiliations":[{"raw_affiliation_string":"Nantong University, Nantong, China","institution_ids":["https://openalex.org/I199305430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088191810","display_name":"Longyue Wang","orcid":"https://orcid.org/0000-0002-9062-6183"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longyue Wang","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-9062-6183","affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071890018","display_name":"Liting Zhou","orcid":"https://orcid.org/0000-0002-7778-8743"},"institutions":[{"id":"https://openalex.org/I42934936","display_name":"Dublin City University","ror":"https://ror.org/04a1a1e81","country_code":"IE","type":"education","lineage":["https://openalex.org/I42934936"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Liting Zhou","raw_affiliation_strings":["Dublin City University, Dublin, Ireland"],"raw_orcid":"https://orcid.org/0000-0002-7778-8743","affiliations":[{"raw_affiliation_string":"Dublin City University, Dublin, Ireland","institution_ids":["https://openalex.org/I42934936"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014224452","display_name":"Cathal Gurrin","orcid":"https://orcid.org/0000-0003-2903-3968"},"institutions":[{"id":"https://openalex.org/I42934936","display_name":"Dublin City University","ror":"https://ror.org/04a1a1e81","country_code":"IE","type":"education","lineage":["https://openalex.org/I42934936"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Cathal Gurrin","raw_affiliation_strings":["Dublin City University, Dublin, Ireland"],"raw_orcid":"https://orcid.org/0000-0003-2903-3968","affiliations":[{"raw_affiliation_string":"Dublin City University, Dublin, Ireland","institution_ids":["https://openalex.org/I42934936"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035082722","display_name":"Linyi Yang","orcid":"https://orcid.org/0000-0003-0667-7349"},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linyi Yang","raw_affiliation_strings":["Westlake University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-0667-7349","affiliations":[{"raw_affiliation_string":"Westlake University, Hangzhou, China","institution_ids":["https://openalex.org/I3133055985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100745222","display_name":"Yi Yu","orcid":"https://orcid.org/0000-0002-0294-6620"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yi Yu","raw_affiliation_strings":["National Institute of Informatics, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0002-0294-6620","affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020500064","display_name":"Yvette Graham","orcid":"https://orcid.org/0000-0001-6741-4855"},"institutions":[{"id":"https://openalex.org/I205274468","display_name":"Trinity College Dublin","ror":"https://ror.org/02tyrky19","country_code":"IE","type":"education","lineage":["https://openalex.org/I205274468"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Yvette Graham","raw_affiliation_strings":["Trinity College Dublin, Dublin, Ireland"],"raw_orcid":"https://orcid.org/0000-0001-6741-4855","affiliations":[{"raw_affiliation_string":"Trinity College Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I205274468"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066497689","display_name":"Jennifer Foster","orcid":"https://orcid.org/0000-0002-7789-4853"},"institutions":[{"id":"https://openalex.org/I42934936","display_name":"Dublin City University","ror":"https://ror.org/04a1a1e81","country_code":"IE","type":"education","lineage":["https://openalex.org/I42934936"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Jennifer Foster","raw_affiliation_strings":["Dublin City University, Dublin, Ireland"],"raw_orcid":"https://orcid.org/0000-0002-7789-4853","affiliations":[{"raw_affiliation_string":"Dublin City University, Dublin, Ireland","institution_ids":["https://openalex.org/I42934936"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":10,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6737,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.71909732,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3975","last_page":"3984"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9979000091552734,"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":0.9972000122070312,"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":0.893695592880249},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6189050674438477},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5229552388191223},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4807395935058594},{"id":"https://openalex.org/keywords/scene-graph","display_name":"Scene graph","score":0.47284749150276184},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4593750238418579},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.4422800838947296},{"id":"https://openalex.org/keywords/semantic-matching","display_name":"Semantic matching","score":0.41275596618652344},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3774026334285736},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.3330859839916229},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.1764880120754242}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.893695592880249},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6189050674438477},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5229552388191223},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4807395935058594},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.47284749150276184},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4593750238418579},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.4422800838947296},{"id":"https://openalex.org/C2778493491","wikidata":"https://www.wikidata.org/wiki/Q7449072","display_name":"Semantic matching","level":3,"score":0.41275596618652344},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3774026334285736},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3330859839916229},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.1764880120754242},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"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:10.1145/3581783.3612132","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612132","pdf_url":null,"source":null,"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":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7900000214576721,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1978620866","https://openalex.org/W2517194566","https://openalex.org/W2963691697","https://openalex.org/W2964109005","https://openalex.org/W2964187781","https://openalex.org/W2964213933","https://openalex.org/W2989812581","https://openalex.org/W2998166190","https://openalex.org/W3035309251","https://openalex.org/W3035356601","https://openalex.org/W3036007088","https://openalex.org/W3043840704","https://openalex.org/W3099700870","https://openalex.org/W3102887392","https://openalex.org/W3119243803","https://openalex.org/W3130796238","https://openalex.org/W3166016508","https://openalex.org/W3168640669","https://openalex.org/W3169472988","https://openalex.org/W3174873881","https://openalex.org/W3204588463","https://openalex.org/W4200631219","https://openalex.org/W4210257598","https://openalex.org/W4210352519","https://openalex.org/W4280651853","https://openalex.org/W4288020443","https://openalex.org/W4306809100","https://openalex.org/W4307928257","https://openalex.org/W4312810944","https://openalex.org/W4317931697","https://openalex.org/W6600103761","https://openalex.org/W6600234944","https://openalex.org/W6790241037","https://openalex.org/W6807384801"],"related_works":["https://openalex.org/W2068608913","https://openalex.org/W3124914020","https://openalex.org/W2141033859","https://openalex.org/W579810227","https://openalex.org/W2952780262","https://openalex.org/W2077542787","https://openalex.org/W2754155766","https://openalex.org/W4287854977","https://openalex.org/W2963192850","https://openalex.org/W2769151336"],"abstract_inverted_index":{"Video-language":[0],"learning":[1],"has":[2],"attracted":[3],"significant":[4],"attention":[5],"in":[6,17,25,157],"the":[7,22,111,115,138,152,164,169,191,201],"fields":[8],"of":[9,21,114,122,125,203],"multimedia,":[10],"computer":[11],"vision":[12],"and":[13,34,44,54,69,75,83,101,127,140,154,181,206],"natural":[14],"language":[15],"processing":[16],"recent":[18],"years.":[19],"One":[20],"key":[23],"challenges":[24],"this":[26,48,60],"area":[27],"is":[28,161],"how":[29],"to":[30,37,40,58,97,103,118,149],"effectively":[31,150],"integrate":[32],"visual":[33,128,141,155],"linguistic":[35],"information":[36,156,166],"enable":[38],"machines":[39],"understand":[41],"video":[42,68],"content":[43],"query":[45,70],"information.":[46],"In":[47],"work,":[49],"we":[50,130],"leverage":[51],"graph-based":[52,170,204],"representations":[53,100],"multi-grained":[55,133,207],"audio-visual":[56,208],"alignment":[57,134],"address":[59],"challenge.":[61],"First,":[62],"our":[63,188],"approach":[64,189],"starts":[65],"by":[66,168],"transforming":[67],"inputs":[71],"into":[72],"visual-scene":[73,81],"graphs":[74,78,89],"semantic":[76,84,112],"role":[77,85],"using":[79,93],"a":[80,105,132,158],"parser":[82],"labeler":[86],"respectively.":[87],"These":[88],"are":[90],"then":[91],"encoded":[92],"graph":[94],"neural":[95],"networks":[96],"obtain":[98,104],"enriched":[99],"combined":[102],"video-query":[106],"joint":[107],"representation":[108,205],"that":[109,136,160,187],"enhances":[110],"expressivity":[113],"inputs.":[116],"Second,":[117],"achieve":[119],"accurate":[120],"matching":[121],"relevant":[123],"parts":[124],"audio":[126,139,153],"features,":[129],"propose":[131],"module":[135],"aligns":[137],"features":[142],"at":[143],"multiple":[144],"scales.":[145],"This":[146],"enables":[147],"us":[148],"fuse":[151],"way":[159],"consistent":[162],"with":[163],"semantic-level":[165],"captured":[167],"representations.":[171],"Experiments":[172],"on":[173,193],"five":[174],"representative":[175],"datasets":[176],"collected":[177],"for":[178],"Video":[179,182],"Retrieval":[180],"Question":[183],"Answering":[184],"tasks":[185],"show":[186],"outperforms":[190],"literature":[192],"several":[194],"metrics.":[195],"Our":[196],"extensive":[197],"ablation":[198],"studies":[199],"demonstrate":[200],"effectiveness":[202],"alignment.":[209]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}