{"id":"https://openalex.org/W3213351830","doi":"https://doi.org/10.1109/iccse51940.2021.9569264","title":"Visual Relationship Learning for Cross-Modal Retrieval","display_name":"Visual Relationship Learning for Cross-Modal Retrieval","publication_year":2021,"publication_date":"2021-08-17","ids":{"openalex":"https://openalex.org/W3213351830","doi":"https://doi.org/10.1109/iccse51940.2021.9569264","mag":"3213351830"},"language":"en","primary_location":{"id":"doi:10.1109/iccse51940.2021.9569264","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccse51940.2021.9569264","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 16th International Conference on Computer Science & Education (ICCSE)","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/A5064738683","display_name":"Xian Zhong","orcid":"https://orcid.org/0000-0002-5242-0467"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xian Zhong","raw_affiliation_strings":["Hubei Key Laboratory of Transportation Internet of Things, Wuhan University of Technology, Wuhan, China","School of Computer Science and Technology, Wuhan University of Technology, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hubei Key Laboratory of Transportation Internet of Things, Wuhan University of Technology, Wuhan, China","institution_ids":["https://openalex.org/I196699116"]},{"raw_affiliation_string":"School of Computer Science and Technology, Wuhan University of Technology, Wuhan, China","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039388570","display_name":"Tianyou Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyou Lu","raw_affiliation_strings":["School of Computer Science and Technology, Wuhan University of Technology, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Wuhan University of Technology, Wuhan, China","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101564555","display_name":"Wenxuan Liu","orcid":"https://orcid.org/0000-0002-4417-6628"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenxuan Liu","raw_affiliation_strings":["School of Computer Science and Technology, Wuhan University of Technology, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Wuhan University of Technology, Wuhan, China","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112704975","display_name":"Duxiu Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Duxiu Feng","raw_affiliation_strings":["ZhongQianLiYuan Engineering Consulting Co., Ltd, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ZhongQianLiYuan Engineering Consulting Co., Ltd, Wuhan, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011131365","display_name":"Qi Cui","orcid":"https://orcid.org/0000-0002-0282-9758"},"institutions":[{"id":"https://openalex.org/I4210148225","display_name":"China State Construction Engineering (China)","ror":"https://ror.org/03kgcsq08","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210148225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Cui","raw_affiliation_strings":["China Construction Third Engineering Bureau Group Co., Ltd, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Construction Third Engineering Bureau Group Co., Ltd, Wuhan, China","institution_ids":["https://openalex.org/I4210148225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037897744","display_name":"Luo Zhong","orcid":"https://orcid.org/0000-0002-2346-9659"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Luo Zhong","raw_affiliation_strings":["Hubei Key Laboratory of Transportation Internet of Things, Wuhan University of Technology, Wuhan, China","School of Computer Science and Technology, Wuhan University of Technology, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hubei Key Laboratory of Transportation Internet of Things, Wuhan University of Technology, Wuhan, China","institution_ids":["https://openalex.org/I196699116"]},{"raw_affiliation_string":"School of Computer Science and Technology, Wuhan University of Technology, Wuhan, China","institution_ids":["https://openalex.org/I196699116"]}]}],"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":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"828","last_page":"832"},"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":0.9954000115394592,"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":0.8805491328239441},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6352568864822388},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6192536354064941},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5989505648612976},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5881457328796387},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.5641038417816162},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5414845943450928},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5187111496925354},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.501497745513916},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4918251037597656},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.449025958776474},{"id":"https://openalex.org/keywords/visual-word","display_name":"Visual Word","score":0.4489608407020569},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.44590580463409424},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4225155711174011},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4137420058250427},{"id":"https://openalex.org/keywords/multimedia-information-retrieval","display_name":"Multimedia information retrieval","score":0.4133458137512207},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35404473543167114},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34700533747673035},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.27925556898117065},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.1010410487651825}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8805491328239441},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6352568864822388},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6192536354064941},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5989505648612976},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5881457328796387},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.5641038417816162},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5414845943450928},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5187111496925354},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.501497745513916},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4918251037597656},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.449025958776474},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.4489608407020569},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.44590580463409424},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4225155711174011},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4137420058250427},{"id":"https://openalex.org/C2776318140","wikidata":"https://www.wikidata.org/wiki/Q6934776","display_name":"Multimedia information retrieval","level":2,"score":0.4133458137512207},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35404473543167114},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34700533747673035},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.27925556898117065},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.1010410487651825},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccse51940.2021.9569264","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccse51940.2021.9569264","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 16th International Conference on Computer Science & Education (ICCSE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W637153065","https://openalex.org/W1522301498","https://openalex.org/W1527575280","https://openalex.org/W1686810756","https://openalex.org/W1905882502","https://openalex.org/W2077069816","https://openalex.org/W2194775991","https://openalex.org/W2250378130","https://openalex.org/W2552579943","https://openalex.org/W2561196672","https://openalex.org/W2774267535","https://openalex.org/W2778940641","https://openalex.org/W2883311563","https://openalex.org/W2962835968","https://openalex.org/W2962964995","https://openalex.org/W2963040148","https://openalex.org/W2963467339","https://openalex.org/W2963499204","https://openalex.org/W2963899908","https://openalex.org/W2964120214","https://openalex.org/W2964121744","https://openalex.org/W2982078236","https://openalex.org/W2988823324","https://openalex.org/W3029678209","https://openalex.org/W3035454331","https://openalex.org/W3035552787","https://openalex.org/W3168680617","https://openalex.org/W4299801216","https://openalex.org/W6620673361","https://openalex.org/W6631190155","https://openalex.org/W6631516269","https://openalex.org/W6637373629","https://openalex.org/W6685183736","https://openalex.org/W6747225742","https://openalex.org/W6747457746","https://openalex.org/W6749537441","https://openalex.org/W6775142011","https://openalex.org/W6796275203"],"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/W1981548447"],"abstract_inverted_index":{"With":[0],"the":[1,15,91,95,113,134,137],"rapid":[2],"development":[3],"of":[4,26,94,115,136],"deep":[5,103],"neural":[6,104],"networks,":[7],"multimedia":[8,21],"data":[9,22],"has":[10,31],"been":[11],"greatly":[12],"enriched":[13],"during":[14],"past":[16],"few":[17],"years.":[18],"Searching":[19],"among":[20],"with":[23,64],"a":[24,33,78,102],"variety":[25],"modalities":[27],"(i.e.,":[28],"cross-modal":[29],"retrieval)":[30],"become":[32],"central":[34],"research":[35],"topic":[36],"due":[37],"to":[38,41,46,62,84],"its":[39],"ability":[40],"better":[42],"express":[43],"semantics":[44],"compared":[45],"simple":[47],"uni-modal":[48],"search.":[49],"These":[50],"methods":[51],"give":[52],"amazing":[53],"results":[54],"in":[55,118],"many":[56,65],"areas,":[57],"but":[58],"it":[59,100],"is":[60],"difficult":[61],"deal":[63],"objects":[66],"and":[67,98,120],"relationships":[68],"faithfully":[69],"reproducing":[70],"complex":[71],"sentences.":[72],"In":[73],"this":[74,86,116],"paper,":[75],"we":[76],"propose":[77],"novel":[79],"approach":[80,89,117],"for":[81,107],"image-sentence":[82,138],"retrieval":[83,139],"overcome":[85],"limitation.":[87],"Our":[88],"leverages":[90],"semantic":[92],"expressiveness":[93],"scene":[96],"graph":[97],"incorporates":[99],"into":[101],"network":[105],"model":[106],"more":[108],"efficient":[109],"retrieval.":[110],"We":[111],"demonstrate":[112],"effectiveness":[114],"real-world":[119],"simulated":[121],"computer":[122],"vision":[123],"tasks.":[124],"Extensive":[125],"experiments":[126],"show":[127],"that":[128],"our":[129],"method":[130],"can":[131],"significantly":[132],"improve":[133],"accuracy":[135],"task.":[140]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}