{"id":"https://openalex.org/W4372349424","doi":"https://doi.org/10.1109/icassp49357.2023.10096391","title":"Learning To Locate Visual Answer In Video Corpus Using Question","display_name":"Learning To Locate Visual Answer In Video Corpus Using Question","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372349424","doi":"https://doi.org/10.1109/icassp49357.2023.10096391"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096391","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096391","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100365196","display_name":"Bin Li","orcid":"https://orcid.org/0000-0002-5974-1116"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Li","raw_affiliation_strings":["Hunan University,College of Electrical and Information Engineering","College of Electrical and Information Engineering, Hunan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University,College of Electrical and Information Engineering","institution_ids":["https://openalex.org/I16609230"]},{"raw_affiliation_string":"College of Electrical and Information Engineering, Hunan University","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052553582","display_name":"Yixuan Weng","orcid":"https://orcid.org/0000-0002-9720-8689"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yixuan Weng","raw_affiliation_strings":["Chinese Academy Sciences,National Laboratory of Pattern Recognition Institute of Automation","National Laboratory of Pattern Recognition Institute of Automation, Chinese Academy Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy Sciences,National Laboratory of Pattern Recognition Institute of Automation","institution_ids":["https://openalex.org/I4210112150"]},{"raw_affiliation_string":"National Laboratory of Pattern Recognition Institute of Automation, Chinese Academy Sciences","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100641761","display_name":"Bin Sun","orcid":"https://orcid.org/0000-0002-7029-8784"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Sun","raw_affiliation_strings":["Hunan University,College of Electrical and Information Engineering","College of Electrical and Information Engineering, Hunan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University,College of Electrical and Information Engineering","institution_ids":["https://openalex.org/I16609230"]},{"raw_affiliation_string":"College of Electrical and Information Engineering, Hunan University","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067097659","display_name":"Shutao Li","orcid":"https://orcid.org/0000-0002-0585-9848"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shutao Li","raw_affiliation_strings":["Hunan University,College of Electrical and Information Engineering","College of Electrical and Information Engineering, Hunan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University,College of Electrical and Information Engineering","institution_ids":["https://openalex.org/I16609230"]},{"raw_affiliation_string":"College of Electrical and Information Engineering, Hunan University","institution_ids":["https://openalex.org/I16609230"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9975000023841858,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9902999997138977,"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":0.8399758338928223},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6403508186340332},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5658725500106812},{"id":"https://openalex.org/keywords/video-retrieval","display_name":"Video retrieval","score":0.4969234764575958},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4738274812698364},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.4397229254245758},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4327213168144226},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.39553770422935486}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8399758338928223},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6403508186340332},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5658725500106812},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.4969234764575958},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4738274812698364},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.4397229254245758},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4327213168144226},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39553770422935486},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096391","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096391","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8700000047683716,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2085030399","https://openalex.org/W2787683732","https://openalex.org/W2896739098","https://openalex.org/W2915480215","https://openalex.org/W2963524571","https://openalex.org/W2963541336","https://openalex.org/W3021397474","https://openalex.org/W3034743747","https://openalex.org/W3088744711","https://openalex.org/W3099700870","https://openalex.org/W3135773387","https://openalex.org/W3155721152","https://openalex.org/W3180463990","https://openalex.org/W3195997474","https://openalex.org/W3206455169","https://openalex.org/W4221166064","https://openalex.org/W4285113287","https://openalex.org/W4285212056","https://openalex.org/W4313469377","https://openalex.org/W4360600216","https://openalex.org/W6623517193"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2387743295","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/W4212839359","https://openalex.org/W2115758952"],"abstract_inverted_index":{"We":[0,83],"introduce":[1],"a":[2,20,28,35,59,86,129],"new":[3,130],"task,":[4],"named":[5,88],"video":[6,46,71,111],"corpus":[7,72,112],"visual":[8,17,51,75,115],"answer":[9,18,52,76,116],"localization":[10,77,117],"(VCVAL),":[11],"which":[12,91,137],"aims":[13],"to":[14],"locate":[15],"the":[16,40,66,70,80,92,101,110,134],"in":[19,109,139],"large":[21],"collection":[22],"of":[23,37],"untrimmed":[24],"instructional":[25,135],"videos":[26],"using":[27],"natural":[29],"language":[30],"question.":[31],"This":[32],"task":[33,94],"requires":[34],"range":[36],"skills":[38],"-":[39],"interaction":[41],"between":[42],"vision":[43],"and":[44,50,74,114],"language,":[45],"retrieval,":[47],"passage":[48],"comprehension,":[49],"localization.":[53],"In":[54],"this":[55],"paper,":[56],"we":[57,121],"propose":[58],"cross-modal":[60],"contrastive":[61],"global-span":[62,81],"(CCGS)":[63],"method":[64,103],"for":[65,132],"VCVAL,":[67],"jointly":[68],"training":[69],"retrieval":[73,113],"subtasks":[78],"with":[79],"matrix.":[82],"have":[84],"reconstructed":[85],"dataset":[87],"MedVidCQA,":[89],"on":[90,125],"VCVAL":[93],"is":[95],"benchmarked.":[96],"Experimental":[97],"results":[98],"show":[99],"that":[100],"proposed":[102],"outperforms":[104],"other":[105],"competitive":[106],"methods":[107],"both":[108],"sub-tasks.":[118],"Most":[119],"importantly,":[120],"perform":[122],"detailed":[123],"analyses":[124],"extensive":[126],"experiments,":[127],"paving":[128],"path":[131],"understanding":[133],"videos,":[136],"ushers":[138],"further":[140],"research":[141],"<sup":[142],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[143],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[144],".":[145]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}