{"id":"https://openalex.org/W3196529233","doi":"https://doi.org/10.1145/3460426.3463608","title":"Multi-Feature Graph Attention Network for Cross-Modal Video-Text Retrieval","display_name":"Multi-Feature Graph Attention Network for Cross-Modal Video-Text Retrieval","publication_year":2021,"publication_date":"2021-08-24","ids":{"openalex":"https://openalex.org/W3196529233","doi":"https://doi.org/10.1145/3460426.3463608","mag":"3196529233"},"language":"en","primary_location":{"id":"doi:10.1145/3460426.3463608","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3460426.3463608","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3460426.3463608","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3460426.3463608","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037323143","display_name":"Xiaoshuai Hao","orcid":null},"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/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":true,"raw_author_name":"Xiaoshuai Hao","raw_affiliation_strings":["Institute of Information Engineering,Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering,Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]}]},{"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/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":"Yucan Zhou","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"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/A5002436544","display_name":"Dayan Wu","orcid":"https://orcid.org/0000-0002-8604-7226"},"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":"Dayan Wu","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"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/A5017704875","display_name":"Wanqian Zhang","orcid":"https://orcid.org/0000-0001-5734-4072"},"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":"Wanqian Zhang","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"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":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"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":"last","author":{"id":"https://openalex.org/A5100442321","display_name":"Weiping Wang","orcid":"https://orcid.org/0000-0002-8618-4992"},"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":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5037323143"],"corresponding_institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.5764,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.68410131,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"135","last_page":"143"},"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":0.9998000264167786,"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":0.9995999932289124,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7850955724716187},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6215523481369019},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6159439086914062},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5931594371795654},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.554203987121582},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.500424861907959},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4963536858558655},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4864766299724579},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4665966033935547},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.44561058282852173},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.44112229347229004},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.4113251566886902},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33912813663482666},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2837370038032532},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09825700521469116}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7850955724716187},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6215523481369019},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6159439086914062},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5931594371795654},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.554203987121582},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.500424861907959},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4963536858558655},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4864766299724579},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4665966033935547},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.44561058282852173},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.44112229347229004},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.4113251566886902},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33912813663482666},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2837370038032532},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09825700521469116},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3460426.3463608","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3460426.3463608","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3460426.3463608","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3460426.3463608","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3460426.3463608","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3460426.3463608","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3196529233.pdf","grobid_xml":"https://content.openalex.org/works/W3196529233.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W1527575280","https://openalex.org/W1999144079","https://openalex.org/W2012210378","https://openalex.org/W2096733369","https://openalex.org/W2104512187","https://openalex.org/W2618604876","https://openalex.org/W2964120214","https://openalex.org/W2980275434","https://openalex.org/W2981716253","https://openalex.org/W3012703918","https://openalex.org/W3012830400","https://openalex.org/W3033587904","https://openalex.org/W3046692080","https://openalex.org/W3093265782","https://openalex.org/W3099206234","https://openalex.org/W4254181784","https://openalex.org/W4300482596","https://openalex.org/W6600009415","https://openalex.org/W6600178264"],"related_works":["https://openalex.org/W2385859805","https://openalex.org/W2081900870","https://openalex.org/W2530972254","https://openalex.org/W3111219495","https://openalex.org/W2374013449","https://openalex.org/W73545470","https://openalex.org/W2183306018","https://openalex.org/W627697492","https://openalex.org/W4283320496","https://openalex.org/W4311555960"],"abstract_inverted_index":{"Cross-modal":[0],"retrieval":[1,85],"between":[2],"videos":[3,17,78,116,166],"and":[4,62,115,194,206,220],"texts":[5,114],"has":[6],"attracted":[7],"growing":[8],"attention":[9,42,156],"due":[10],"to":[11,28,34,43,199],"the":[12,19,36,44,54,60,65,72,80,83,96,108,120,160,168,190,195,202,207,211,232],"rapid":[13],"growth":[14],"of":[15,46,74,82,98,162,170],"user-generated":[16],"on":[18,64,215],"web.":[20],"To":[21],"solve":[22],"this":[23,135],"problem,":[24],"most":[25],"approaches":[26],"try":[27],"learn":[29],"a":[30,139,153,180],"joint":[31],"embedding":[32,212],"space":[33],"measure":[35],"cross-modal":[37,147,203],"similarities,":[38],"while":[39],"paying":[40],"little":[41],"representation":[45,161],"each":[47,91,163],"modality.":[48],"Video":[49],"is":[50,131],"more":[51],"complicated":[52],"than":[53],"commonly":[55],"used":[56],"visual":[57],"feature,":[58],"since":[59],"audio":[61],"caption":[63],"screen":[66],"also":[67,132],"contain":[68],"rich":[69],"information.":[70],"Recently,":[71],"aggregations":[73],"multiple":[75,104],"features":[76],"in":[77,165,210],"boost":[79],"benchmark":[81],"video-text":[84,148],"system.":[86],"However,":[87],"they":[88],"usually":[89],"handle":[90],"feature":[92,164],"independently,":[93],"which":[94,158,187],"ignores":[95],"interchange":[97,169],"high-level":[99,171],"semantic":[100,172,204],"relations":[101],"among":[102,174],"these":[103],"features.":[105],"Moreover,":[106,176],"despite":[107],"inter-modal":[109,191],"ranking":[110,192],"constraint":[111,193,198],"where":[112],"semantically-similar":[113],"should":[117,127],"stay":[118],"closer,":[119],"modality-specific":[121,208],"requirement,":[122],"i.e.":[123,218],"two":[124,216],"similar":[125,129],"videos/texts":[126],"have":[128],"representations,":[130],"significant.":[133],"In":[134],"paper,":[136],"we":[137,151,177],"propose":[138],"novel":[140,181],"Multi-Feature":[141],"Graph":[142],"ATtention":[143],"Network":[144],"(MFGATN)":[145],"for":[146],"retrieval.":[149],"Specifically,":[150],"introduce":[152],"multi-feature":[154],"graph":[155],"module,":[157],"enriches":[159],"with":[167,231],"information":[173],"them.":[175],"elaborately":[178],"design":[179],"Dual":[182],"Constraint":[183],"Ranking":[184],"Loss":[185],"(DCRL),":[186],"simultaneously":[188],"considers":[189],"intra-modal":[196],"structure":[197],"preserve":[200],"both":[201],"similarity":[205],"consistency":[209],"space.":[213],"Experiments":[214],"datasets,":[217],"MSR-VTT":[219],"MSVD,":[221],"demonstrate":[222],"that":[223],"our":[224],"method":[225],"achieves":[226],"significant":[227],"performance":[228],"gain":[229],"compared":[230],"state-of-the-arts.":[233]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}