{"id":"https://openalex.org/W3190416739","doi":"https://doi.org/10.1109/icme51207.2021.9428325","title":"What Matters: Attentive and Relational Feature Aggregation Network for Video-Text Retrieval","display_name":"What Matters: Attentive and Relational Feature Aggregation Network for Video-Text Retrieval","publication_year":2021,"publication_date":"2021-06-09","ids":{"openalex":"https://openalex.org/W3190416739","doi":"https://doi.org/10.1109/icme51207.2021.9428325","mag":"3190416739"},"language":"en","primary_location":{"id":"doi:10.1109/icme51207.2021.9428325","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme51207.2021.9428325","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":"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/A5037323143","display_name":"Xiaoshuai Hao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaoshuai Hao","raw_affiliation_strings":["University of Chinese Academy of Sciences,School of Cyber Security,Beijing,China,100049","Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,School of Cyber Security,Beijing,China,100049","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080811169","display_name":"Yucan Zhou","orcid":"https://orcid.org/0000-0002-1316-9118"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yucan Zhou","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China,100093"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China,100093","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002436544","display_name":"Dayan Wu","orcid":"https://orcid.org/0000-0002-8604-7226"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dayan Wu","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China,100093"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China,100093","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017704875","display_name":"Wanqian Zhang","orcid":"https://orcid.org/0000-0001-5734-4072"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wanqian Zhang","raw_affiliation_strings":["University of Chinese Academy of Sciences,School of Cyber Security,Beijing,China,100049","Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,School of Cyber Security,Beijing,China,100049","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100374360","display_name":"Bo Li","orcid":"https://orcid.org/0000-0001-6709-0942"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Li","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China,100093"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China,100093","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115591448","display_name":"Weiping Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiping Wang","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China,100093"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China,100093","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101525319","display_name":"Dan Meng","orcid":"https://orcid.org/0000-0003-1980-9283"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Meng","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China,100093"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China,100093","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5037323143"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.3843,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.60436275,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9995999932289124,"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":0.8632670640945435},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.661564826965332},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6548041701316833},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6507757306098938},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.634775698184967},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5827665328979492},{"id":"https://openalex.org/keywords/video-retrieval","display_name":"Video retrieval","score":0.5703105330467224},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5551648736000061},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5004520416259766},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.467818945646286},{"id":"https://openalex.org/keywords/attention-network","display_name":"Attention network","score":0.46552249789237976},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.44637805223464966},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4303596317768097},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.4141131043434143},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3556247651576996},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.14196205139160156},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.1302310824394226}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8632670640945435},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.661564826965332},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6548041701316833},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6507757306098938},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.634775698184967},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5827665328979492},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.5703105330467224},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5551648736000061},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5004520416259766},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.467818945646286},{"id":"https://openalex.org/C2993807640","wikidata":"https://www.wikidata.org/wiki/Q103709453","display_name":"Attention network","level":2,"score":0.46552249789237976},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.44637805223464966},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4303596317768097},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.4141131043434143},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3556247651576996},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.14196205139160156},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.1302310824394226},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme51207.2021.9428325","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme51207.2021.9428325","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":[{"display_name":"Quality Education","score":0.4399999976158142,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1527575280","https://openalex.org/W1614298861","https://openalex.org/W2021899621","https://openalex.org/W2164290393","https://openalex.org/W2396061494","https://openalex.org/W2425121537","https://openalex.org/W2490414731","https://openalex.org/W2519887557","https://openalex.org/W2558358930","https://openalex.org/W2616994964","https://openalex.org/W2753311918","https://openalex.org/W2774267535","https://openalex.org/W2796207103","https://openalex.org/W2808399042","https://openalex.org/W2951019013","https://openalex.org/W2964015378","https://openalex.org/W2965458216","https://openalex.org/W2975813532","https://openalex.org/W3035012345","https://openalex.org/W3035356601","https://openalex.org/W3102887392","https://openalex.org/W6631516269","https://openalex.org/W6636510571","https://openalex.org/W6684090549","https://openalex.org/W6730383699","https://openalex.org/W6747225742","https://openalex.org/W6750041603","https://openalex.org/W6766582784"],"related_works":["https://openalex.org/W2185469136","https://openalex.org/W2011264131","https://openalex.org/W4306353150","https://openalex.org/W2026860389","https://openalex.org/W8219677","https://openalex.org/W3216879894","https://openalex.org/W2890132085","https://openalex.org/W2168054807","https://openalex.org/W4301143707","https://openalex.org/W2952745240"],"abstract_inverted_index":{"Cross-modal":[0],"video-text":[1,54],"retrieval":[2],"has":[3],"been":[4,71],"an":[5],"emerging":[6],"task":[7],"due":[8],"to":[9,104,111,122,130],"the":[10,17,28,35,43,51,101,112,116,124,127,146],"rapid":[11],"growth":[12],"of":[13,45,53],"user-generated":[14],"videos":[15,49,106],"on":[16,23,34,141,149],"Internet.":[18],"Most":[19],"existing":[20],"approaches":[21],"focus":[22],"extracting":[24],"visual":[25],"feature":[26],"for":[27],"video,":[29],"while":[30],"audio":[31],"and":[32,63,76,92,137,151],"caption":[33],"screen":[36],"containing":[37],"rich":[38],"information":[39],"are":[40,61,77,120],"ignored.":[41],"Recently,":[42],"aggregations":[44],"multi-modal":[46,59,128],"features":[47,60,129],"in":[48,80],"boost":[50],"benchmark":[52],"retrieval.":[55],"However,":[56],"since":[57],"these":[58],"high-dimensional":[62],"heterogeneous,":[64],"their":[65],"intrinsically":[66],"structural":[67],"relations":[68,125],"have":[69],"not":[70],"attached":[72],"with":[73,145],"enough":[74],"importance":[75],"often":[78],"overlooked":[79],"previous":[81],"methods.":[82],"To":[83],"address":[84],"this":[85],"issue,":[86],"we":[87,99],"propose":[88],"a":[89],"novel":[90],"Attentive":[91],"Relational":[93],"Feature":[94],"Aggregation":[95],"Network":[96],"(ARFAN).":[97],"Specifically,":[98],"introduce":[100],"self-attention":[102],"mechanism":[103],"make":[105],"adaptively":[107],"assign":[108],"higher":[109],"weights":[110],"representative":[113],"modalities.":[114],"Then,":[115],"graph":[117],"convolutional":[118],"layers":[119],"inserted":[121],"capture":[123],"among":[126],"combine":[131],"them.":[132],"Our":[133],"method":[134,148],"achieves":[135],"15%":[136],"12.9%":[138],"relative":[139],"improvements":[140],"R@1":[142],"when":[143],"compared":[144],"state-of-the-art":[147],"MSR-VTT":[150],"MSVD":[152],"datasets,":[153],"respectively.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
