{"id":"https://openalex.org/W4372265847","doi":"https://doi.org/10.1109/icassp49357.2023.10095026","title":"Visual Answer Localization with Cross-Modal Mutual Knowledge Transfer","display_name":"Visual Answer Localization with Cross-Modal Mutual Knowledge Transfer","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372265847","doi":"https://doi.org/10.1109/icassp49357.2023.10095026"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095026","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095026","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/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":"last","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"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0635,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.91442904,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"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":0.9994000196456909,"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":0.9977999925613403,"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":0.7731997966766357},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6256429553031921},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6230286359786987},{"id":"https://openalex.org/keywords/knowledge-transfer","display_name":"Knowledge transfer","score":0.5699475407600403},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5454862117767334},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.48689785599708557},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.457394003868103},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.4476161599159241},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4268838167190552},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3805820047855377}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7731997966766357},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6256429553031921},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6230286359786987},{"id":"https://openalex.org/C2776960227","wikidata":"https://www.wikidata.org/wiki/Q2586354","display_name":"Knowledge transfer","level":2,"score":0.5699475407600403},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5454862117767334},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.48689785599708557},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.457394003868103},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.4476161599159241},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4268838167190552},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3805820047855377},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge 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},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095026","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095026","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7599999904632568}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2798354744","https://openalex.org/W2896739098","https://openalex.org/W2908510526","https://openalex.org/W2963393391","https://openalex.org/W2963524571","https://openalex.org/W2968538719","https://openalex.org/W2973164670","https://openalex.org/W3025323587","https://openalex.org/W3034743747","https://openalex.org/W3088744711","https://openalex.org/W3135773387","https://openalex.org/W3209859545","https://openalex.org/W3211686893","https://openalex.org/W3211953751","https://openalex.org/W4221166064","https://openalex.org/W4285212056","https://openalex.org/W4285290969","https://openalex.org/W4288000169","https://openalex.org/W4295253143","https://openalex.org/W4360600216","https://openalex.org/W6751097180","https://openalex.org/W6755852683","https://openalex.org/W6757817989","https://openalex.org/W6770906865","https://openalex.org/W6803557570","https://openalex.org/W6809659084","https://openalex.org/W6809894078"],"related_works":["https://openalex.org/W2185469136","https://openalex.org/W2466816617","https://openalex.org/W2011264131","https://openalex.org/W1970834875","https://openalex.org/W842936808","https://openalex.org/W2068608913","https://openalex.org/W3174028392","https://openalex.org/W4306353150","https://openalex.org/W4301143707","https://openalex.org/W2952745240"],"abstract_inverted_index":{"The":[0,159],"goal":[1],"of":[2,115,145],"visual":[3,46,50,77,104],"answering":[4],"localization":[5,93],"(VAL)":[6],"in":[7],"the":[8,23,26,36,45,49,54,60,98,112,143],"video":[9,21,40],"is":[10],"to":[11,25,43,63,96,118,123,140],"obtain":[12],"a":[13,20,87,135],"relevant":[14],"and":[15,41,106],"concise":[16],"time":[17],"clip":[18],"from":[19,76],"as":[22,122],"answer":[24,47],"given":[27],"natural":[28],"language":[29],"question.":[30],"Early":[31],"methods":[32,70],"are":[33],"based":[34],"on":[35,153],"interaction":[37],"modelling":[38],"between":[39,128],"text":[42],"predict":[44],"by":[48],"predictor.":[51],"Later,":[52],"using":[53],"textual":[55,80,107],"predictor":[56,105],"with":[57],"subtitles":[58],"for":[59,157],"VAL":[61],"proves":[62],"be":[64,119],"more":[65],"precise.":[66],"However,":[67],"these":[68,116],"existing":[69],"still":[71],"have":[72,149],"cross-modal":[73,88],"knowledge":[74,90,99,126,146],"deviations":[75],"frames":[78],"or":[79],"subtitles.":[81],"In":[82],"this":[83,131],"paper,":[84],"we":[85,110,133],"propose":[86],"mutual":[89],"transfer":[91],"span":[92],"(MutualSL)":[94],"method":[95,165],"reduce":[97],"deviation.":[100],"MutualSL":[101],"has":[102],"both":[103,117],"predictor,":[108],"where":[109],"expect":[111],"prediction":[113],"results":[114,161],"consistent,":[120],"so":[121],"promote":[124],"semantic":[125],"understanding":[127],"cross-modalities.":[129],"On":[130],"basis,":[132],"design":[134],"one-way":[136],"dynamic":[137],"loss":[138],"function":[139],"dynamically":[141],"adjust":[142],"proportion":[144],"transfer.":[147],"We":[148],"conducted":[150],"extensive":[151],"experiments":[152],"three":[154],"public":[155],"datasets":[156],"evaluation.":[158],"experimental":[160],"show":[162],"that":[163],"our":[164],"outperforms":[166],"other":[167],"competitive":[168],"state-of-the-art":[169],"(SOTA)":[170],"methods,":[171],"demonstrating":[172],"its":[173],"effectiveness1.":[174]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":5}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}