{"id":"https://openalex.org/W4392909573","doi":"https://doi.org/10.1109/icassp48485.2024.10447275","title":"Semantic Enrichment for Video Question Answering with Gated Graph Neural Networks","display_name":"Semantic Enrichment for Video Question Answering with Gated Graph Neural Networks","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392909573","doi":"https://doi.org/10.1109/icassp48485.2024.10447275"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447275","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447275","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/A5043763521","display_name":"Chenyang Lyu","orcid":"https://orcid.org/0000-0002-3403-7050"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]},{"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":["AE","IE"],"is_corresponding":false,"raw_author_name":"Chenyang Lyu","raw_affiliation_strings":["Dublin City University,Dublin,Ireland","Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE","Dublin City University, Dublin, Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dublin City University,Dublin,Ireland","institution_ids":["https://openalex.org/I42934936"]},{"raw_affiliation_string":"Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE","institution_ids":["https://openalex.org/I4210113480"]},{"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","Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"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","Nantong University, Nantong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nantong University,Nantong,China","institution_ids":["https://openalex.org/I199305430"]},{"raw_affiliation_string":"Nantong University, Nantong, China","institution_ids":["https://openalex.org/I199305430"]}]},{"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","National Institute of Informatics, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics,Tokyo,Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"last","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","Tencent AI Lab, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab,Shenzhen,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2187,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.44271899,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"11616","last_page":"11620"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9908000230789185,"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/T10028","display_name":"Topic Modeling","score":0.9901999831199646,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.7724196910858154},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.6849075555801392},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48317399621009827},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4450339078903198},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.44189032912254333},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.41052526235580444},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.15598082542419434}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7724196910858154},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6849075555801392},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48317399621009827},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4450339078903198},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.44189032912254333},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.41052526235580444},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.15598082542419434}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447275","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447275","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":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2250378130","https://openalex.org/W2463565445","https://openalex.org/W2562439797","https://openalex.org/W2740765036","https://openalex.org/W2904452845","https://openalex.org/W2954199749","https://openalex.org/W2964213933","https://openalex.org/W2966683369","https://openalex.org/W2981582341","https://openalex.org/W2998166190","https://openalex.org/W3034730770","https://openalex.org/W3044495139","https://openalex.org/W3094502228","https://openalex.org/W3119243803","https://openalex.org/W4214604251","https://openalex.org/W4304098310","https://openalex.org/W4311000453","https://openalex.org/W4312380001","https://openalex.org/W4318815354","https://openalex.org/W6719057275","https://openalex.org/W6757817989","https://openalex.org/W6791353385","https://openalex.org/W6811013733","https://openalex.org/W6857732338"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W2115758952","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2366230879","https://openalex.org/W3208425359","https://openalex.org/W2349927912","https://openalex.org/W3159777597","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Video":[0],"Question":[1],"Answering":[2],"(VideoQA)":[3],"is":[4],"a":[5,10,14,51,101],"complex":[6],"task":[7],"that":[8,145],"requires":[9],"deep":[11],"understanding":[12,38],"of":[13,39,61],"video":[15,40,62,71],"to":[16,24,35,57,112,120],"accurately":[17],"answer":[18,66,108],"questions.":[19],"Existing":[20],"methods":[21],"often":[22],"struggle":[23],"effectively":[25],"integrate":[26],"the":[27,47,59],"visual":[28,79,127],"and":[29,42,65,73,82,93,128,140],"language-based":[30],"semantic":[31,76,80,84,124],"information,":[32],"subsequently":[33],"leading":[34],"an":[36],"incomplete":[37],"content":[41],"sub-optimal":[43],"performance.":[44],"To":[45],"address":[46],"challenge,":[48],"we":[49,69,110],"introduce":[50],"novel":[52],"approach":[53,134,147],"in":[54],"this":[55],"paper":[56],"enrich":[58],"semantics":[60],"frames,":[63],"questions,":[64],"candidates.":[67],"Specifically,":[68],"parse":[70],"frames":[72],"questions":[74],"into":[75],"graphs":[77,96],"-":[78],"graph":[81],"question":[83,157],"graph,":[85],"which":[86],"captures":[87],"information":[88,125],"about":[89],"objects,":[90],"their":[91],"attributes,":[92],"relationships.":[94],"These":[95],"are":[97],"then":[98],"encoded":[99],"using":[100,115],"Gated":[102],"Graph":[103],"Neural":[104],"Network":[105],"(GGNN).":[106],"For":[107],"candidates,":[109],"propose":[111],"verbalize":[113],"them":[114],"Large":[116],"Language":[117],"Models":[118],"(LLMs)":[119],"further":[121],"inject":[122],"more":[123],"from":[126],"acoustic":[129],"aspects.":[130],"We":[131],"evaluate":[132],"our":[133,146],"on":[135,155],"benchmark":[136],"VideoQA":[137],"datasets:":[138],"AVQA":[139],"Music-AVQA.":[141],"Experimental":[142],"results":[143],"show":[144],"outperforms":[148],"competitive":[149],"baseline":[150],"models,":[151],"achieving":[152],"state-of-the-art":[153],"performance":[154],"various":[156],"types.":[158]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}