{"id":"https://openalex.org/W3172352865","doi":"https://doi.org/10.1109/icme51207.2021.9428225","title":"Fusing Temporally Distributed Multi-Modal Semantic Clues for Video Question Answering","display_name":"Fusing Temporally Distributed Multi-Modal Semantic Clues for Video Question Answering","publication_year":2021,"publication_date":"2021-06-09","ids":{"openalex":"https://openalex.org/W3172352865","doi":"https://doi.org/10.1109/icme51207.2021.9428225","mag":"3172352865"},"language":"en","primary_location":{"id":"doi:10.1109/icme51207.2021.9428225","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme51207.2021.9428225","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Multimedia and Expo (ICME)","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/A5072166761","display_name":"Fuwei Zhang","orcid":"https://orcid.org/0000-0002-7711-866X"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuwei Zhang","raw_affiliation_strings":["Sun Yat-sen University,School of Computer Science and Engineering, National Engineering Research Center of Digital Life,Guangzhou,China","School of Computer Science and Engineering, National Engineering Research Center of Digital Life, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University,School of Computer Science and Engineering, National Engineering Research Center of Digital Life,Guangzhou,China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"School of Computer Science and Engineering, National Engineering Research Center of Digital Life, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000079751","display_name":"Ruomei Wang","orcid":"https://orcid.org/0000-0002-2712-4412"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruomei Wang","raw_affiliation_strings":["Sun Yat-sen University,School of Computer Science and Engineering, National Engineering Research Center of Digital Life,Guangzhou,China","School of Computer Science and Engineering, National Engineering Research Center of Digital Life, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University,School of Computer Science and Engineering, National Engineering Research Center of Digital Life,Guangzhou,China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"School of Computer Science and Engineering, National Engineering Research Center of Digital Life, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046202286","display_name":"Songhua Xu","orcid":"https://orcid.org/0000-0002-2276-2538"},"institutions":[{"id":"https://openalex.org/I155781252","display_name":"University of South Carolina","ror":"https://ror.org/02b6qw903","country_code":"US","type":"education","lineage":["https://openalex.org/I155781252"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Songhua Xu","raw_affiliation_strings":["University of South Carolina,College of Engineering and Computing,Columbia,SC,USA","College of Engineering and Computing, University of South Carolina, Columbia, SC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of South Carolina,College of Engineering and Computing,Columbia,SC,USA","institution_ids":["https://openalex.org/I155781252"]},{"raw_affiliation_string":"College of Engineering and Computing, University of South Carolina, Columbia, SC, USA","institution_ids":["https://openalex.org/I155781252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077610457","display_name":"Fan Zhou","orcid":"https://orcid.org/0000-0003-1736-2641"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Zhou","raw_affiliation_strings":["Sun Yat-sen University,School of Computer Science and Engineering, National Engineering Research Center of Digital Life,Guangzhou,China","School of Computer Science and Engineering, National Engineering Research Center of Digital Life, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University,School of Computer Science and Engineering, National Engineering Research Center of Digital Life,Guangzhou,China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"School of Computer Science and Engineering, National Engineering Research Center of Digital Life, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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":0.9980000257492065,"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":0.9979000091552734,"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":0.8690739870071411},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6753965616226196},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6014772057533264},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5816236138343811},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5634407997131348},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5432760119438171},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.5280706882476807},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5003998279571533},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4925876259803772},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.48907405138015747},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4389183521270752},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42279016971588135},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3345833122730255},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.15640917420387268},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10450559854507446}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8690739870071411},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6753965616226196},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6014772057533264},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5816236138343811},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5634407997131348},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5432760119438171},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.5280706882476807},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5003998279571533},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4925876259803772},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.48907405138015747},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4389183521270752},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42279016971588135},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3345833122730255},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.15640917420387268},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10450559854507446},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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/icme51207.2021.9428225","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme51207.2021.9428225","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1686810756","https://openalex.org/W2606982687","https://openalex.org/W2806331055","https://openalex.org/W2896457183","https://openalex.org/W2904452845","https://openalex.org/W2954199749","https://openalex.org/W2963541336","https://openalex.org/W2974161034","https://openalex.org/W2997344006","https://openalex.org/W3003991937","https://openalex.org/W3016658915","https://openalex.org/W3020743079","https://openalex.org/W3023993913","https://openalex.org/W3035419698","https://openalex.org/W3116312348","https://openalex.org/W3128726204","https://openalex.org/W6637373629","https://openalex.org/W6730666313","https://openalex.org/W6736741030","https://openalex.org/W6751936687","https://openalex.org/W6755207826","https://openalex.org/W6767958706","https://openalex.org/W6776111039"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W203959209","https://openalex.org/W2110287964","https://openalex.org/W2167701463","https://openalex.org/W4307407935"],"abstract_inverted_index":{"Video":[0],"Question":[1],"Answering":[2],"(VideoQA)":[3],"is":[4,18,110],"an":[5],"intriguing":[6],"topic,":[7],"attracting":[8],"increasing":[9],"interest":[10],"among":[11],"the":[12,83,87,96,102,142,162,180,184],"broad":[13],"AI":[14],"community.":[15],"Yet":[16],"videoQA":[17],"a":[19,43,62,105,117,125,136,148,155],"difficult":[20],"task.":[21,98],"An":[22],"algorithm":[23],"competently":[24],"tackle":[25],"this":[26,113],"task":[27],"that":[28],"needs":[29],"to":[30,85,101,132,140,160,176],"be":[31,69],"able":[32],"to:":[33],"1)":[34],"extract":[35],"rich":[36],"semantics":[37,57],"supplied":[38],"in":[39,112,183],"each":[40,130],"modality":[41,138],"of":[42,61,82,127,135,179],"video":[44],"and":[45,50,53,90,147],"incorporate":[46],"them":[47],"across":[48],"modalities,":[49],"2)":[51],"identify":[52],"integrate":[54],"such":[55],"multimodal":[56],"from":[58],"pertinent":[59],"moments":[60],"video,":[63,84],"which":[64,115],"may":[65,67],"or":[66,72,78],"not":[68],"temporally":[70],"adjacent":[71],"nearby,":[73],"while":[74],"filtering":[75],"away":[76],"irrelevant":[77],"even":[79],"detractive":[80],"portions":[81],"yield":[86],"most":[88],"precise":[89],"sensible":[91],"semantic":[92,119],"context":[93],"for":[94],"executing":[95],"QA":[97,145,151,165],"In":[99],"response":[100],"above":[103],"requirements,":[104],"novel":[106],"deep":[107,128,156],"VideoQA":[108],"solution":[109,182],"proposed":[111],"paper,":[114],"comprises":[116],"multi-modal":[118,149],"clue":[120],"extraction":[121],"module,":[122],"driven":[123],"by":[124,154],"series":[126],"networks,":[129],"dedicated":[131],"digesting":[133],"signals":[134],"distinct":[137],"type,":[139],"develop":[141],"first":[143],"algorithmic":[144,164],"capability,":[146],"temporal":[150],"module":[152],"empowered":[153],"graph":[157],"attention":[158],"network":[159],"build":[161],"second":[163],"capability.":[166],"Comprehensive":[167],"experiments":[168],"are":[169],"conducted":[170],"on":[171],"publicly":[172],"available":[173],"benchmark":[174],"data":[175],"validate":[177],"advantages":[178],"new":[181],"end.":[185]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
