{"id":"https://openalex.org/W4283394402","doi":"https://doi.org/10.1145/3512527.3531358","title":"Learning Hierarchical Semantic Correspondences for Cross-Modal Image-Text Retrieval","display_name":"Learning Hierarchical Semantic Correspondences for Cross-Modal Image-Text Retrieval","publication_year":2022,"publication_date":"2022-06-23","ids":{"openalex":"https://openalex.org/W4283394402","doi":"https://doi.org/10.1145/3512527.3531358"},"language":"en","primary_location":{"id":"doi:10.1145/3512527.3531358","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3512527.3531358","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/10072/417962","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100394035","display_name":"Sheng Zeng","orcid":"https://orcid.org/0000-0003-0159-3808"},"institutions":[{"id":"https://openalex.org/I53592917","display_name":"Jiangxi Normal University","ror":"https://ror.org/05nkgk822","country_code":"CN","type":"education","lineage":["https://openalex.org/I53592917"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Sheng Zeng","raw_affiliation_strings":["Jiangxi Normal University, Nanchang, China"],"affiliations":[{"raw_affiliation_string":"Jiangxi Normal University, Nanchang, China","institution_ids":["https://openalex.org/I53592917"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101859009","display_name":"Changhong Liu","orcid":"https://orcid.org/0000-0003-4673-5806"},"institutions":[{"id":"https://openalex.org/I53592917","display_name":"Jiangxi Normal University","ror":"https://ror.org/05nkgk822","country_code":"CN","type":"education","lineage":["https://openalex.org/I53592917"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changhong Liu","raw_affiliation_strings":["Jiangxi Normal University, Nanchang, China"],"affiliations":[{"raw_affiliation_string":"Jiangxi Normal University, Nanchang, China","institution_ids":["https://openalex.org/I53592917"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100781212","display_name":"Jun Zhou","orcid":"https://orcid.org/0000-0001-5822-8233"},"institutions":[{"id":"https://openalex.org/I11701301","display_name":"Griffith University","ror":"https://ror.org/02sc3r913","country_code":"AU","type":"education","lineage":["https://openalex.org/I11701301"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jun Zhou","raw_affiliation_strings":["Griffith University, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"Griffith University, Brisbane, Australia","institution_ids":["https://openalex.org/I11701301"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100679260","display_name":"Yong Chen","orcid":"https://orcid.org/0000-0002-0649-0763"},"institutions":[{"id":"https://openalex.org/I141103825","display_name":"Nanchang Institute of Technology","ror":"https://ror.org/00avfj807","country_code":"CN","type":"education","lineage":["https://openalex.org/I141103825"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Chen","raw_affiliation_strings":["Nanchang Institute of Technology, Nanchang, China"],"affiliations":[{"raw_affiliation_string":"Nanchang Institute of Technology, Nanchang, China","institution_ids":["https://openalex.org/I141103825"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034126758","display_name":"Aiwen Jiang","orcid":"https://orcid.org/0000-0002-5979-7590"},"institutions":[{"id":"https://openalex.org/I53592917","display_name":"Jiangxi Normal University","ror":"https://ror.org/05nkgk822","country_code":"CN","type":"education","lineage":["https://openalex.org/I53592917"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Aiwen Jiang","raw_affiliation_strings":["Jiangxi Normal University, Nanchang, China"],"affiliations":[{"raw_affiliation_string":"Jiangxi Normal University, Nanchang, China","institution_ids":["https://openalex.org/I53592917"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101418342","display_name":"Hanxi Li","orcid":"https://orcid.org/0000-0002-9433-1833"},"institutions":[{"id":"https://openalex.org/I53592917","display_name":"Jiangxi Normal University","ror":"https://ror.org/05nkgk822","country_code":"CN","type":"education","lineage":["https://openalex.org/I53592917"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanxi Li","raw_affiliation_strings":["Jiangxi Normal University, Nanchang, China"],"affiliations":[{"raw_affiliation_string":"Jiangxi Normal University, Nanchang, China","institution_ids":["https://openalex.org/I53592917"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100394035"],"corresponding_institution_ids":["https://openalex.org/I53592917"],"apc_list":null,"apc_paid":null,"fwci":1.0066,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.76537021,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"239","last_page":"248"},"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":0.9988999962806702,"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":0.9973000288009644,"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":0.8010451197624207},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6569001078605652},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5096511840820312},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4736579358577728},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4699307382106781},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.4584817886352539},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4373123347759247},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4310861825942993},{"id":"https://openalex.org/keywords/visual-word","display_name":"Visual Word","score":0.4198368191719055},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.38475796580314636},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3842165172100067},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.346223920583725}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8010451197624207},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6569001078605652},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5096511840820312},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4736579358577728},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4699307382106781},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.4584817886352539},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4373123347759247},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4310861825942993},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.4198368191719055},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.38475796580314636},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3842165172100067},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.346223920583725},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3512527.3531358","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3512527.3531358","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:research-repository.griffith.edu.au:10072/417962","is_oa":true,"landing_page_url":"http://hdl.handle.net/10072/417962","pdf_url":null,"source":{"id":"https://openalex.org/S4306402548","display_name":"Griffith Research Online (Griffith University, Queensland, Australia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I11701301","host_organization_name":"Griffith University","host_organization_lineage":["https://openalex.org/I11701301"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference output"}],"best_oa_location":{"id":"pmh:oai:research-repository.griffith.edu.au:10072/417962","is_oa":true,"landing_page_url":"http://hdl.handle.net/10072/417962","pdf_url":null,"source":{"id":"https://openalex.org/S4306402548","display_name":"Griffith Research Online (Griffith University, Queensland, Australia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I11701301","host_organization_name":"Griffith University","host_organization_lineage":["https://openalex.org/I11701301"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference output"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.699999988079071}],"awards":[{"id":"https://openalex.org/G7152999925","display_name":null,"funder_award_id":"62067004, 61966018, 61962027","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1861492603","https://openalex.org/W1902237438","https://openalex.org/W1949478088","https://openalex.org/W1957706851","https://openalex.org/W1964073652","https://openalex.org/W2064675550","https://openalex.org/W2147800946","https://openalex.org/W2185175083","https://openalex.org/W2302086703","https://openalex.org/W2342543219","https://openalex.org/W2481240925","https://openalex.org/W2596164567","https://openalex.org/W2602856279","https://openalex.org/W2737725206","https://openalex.org/W2745461083","https://openalex.org/W2750779823","https://openalex.org/W2778100917","https://openalex.org/W2884585870","https://openalex.org/W2962964995","https://openalex.org/W2962965405","https://openalex.org/W2963389687","https://openalex.org/W2963467339","https://openalex.org/W2964022527","https://openalex.org/W2964120214","https://openalex.org/W2965848243","https://openalex.org/W2982078236","https://openalex.org/W2988823324","https://openalex.org/W2994818707","https://openalex.org/W2998215884","https://openalex.org/W3010277541","https://openalex.org/W3035454331","https://openalex.org/W3035552787","https://openalex.org/W3035588244","https://openalex.org/W3035605030","https://openalex.org/W3094172275","https://openalex.org/W3110042533","https://openalex.org/W3118694826","https://openalex.org/W3154430790","https://openalex.org/W3155230099","https://openalex.org/W3190055600","https://openalex.org/W3197809352","https://openalex.org/W3198064418"],"related_works":["https://openalex.org/W2063218608","https://openalex.org/W4386105885","https://openalex.org/W2184288218","https://openalex.org/W2947282851","https://openalex.org/W2374066281","https://openalex.org/W4387423606","https://openalex.org/W2071180033","https://openalex.org/W2036058638","https://openalex.org/W2528082075","https://openalex.org/W155590726"],"abstract_inverted_index":{"Cross-modal":[0],"image-text":[1],"retrieval":[2,76],"is":[3,15],"a":[4,92,102,129,144],"fundamental":[5],"task":[6,14],"in":[7,140],"information":[8,51],"retrieval.":[9],"The":[10],"key":[11],"to":[12,16,136,147],"this":[13],"address":[17],"both":[18,121],"heterogeneity":[19],"and":[20,40,71,87,110,123,143,158,164],"cross-modal":[21],"semantic":[22,36,59,82,94,118],"correlation":[23,95],"between":[24,38,68,84,96],"data":[25],"of":[26,151,166],"different":[27,97],"modalities.":[28],"Fine-grained":[29],"matching":[30,67],"methods":[31],"can":[32],"nicely":[33],"model":[34],"local":[35,66,122],"correlations":[37],"image":[39,72,85,152],"text":[41,53],"but":[42,90],"face":[43],"two":[44],"challenges.":[45],"First,":[46],"images":[47],"may":[48],"contain":[49,56],"redundant":[50],"while":[52],"sentences":[54],"often":[55],"words":[57,70,89,139],"without":[58],"meaning.":[60],"Such":[61],"redundancy":[62],"interferes":[63],"with":[64,107],"the":[65,75,133,141,149,162],"textual":[69,88],"regions.":[73],"Furthermore,":[74],"shall":[77],"consider":[78],"not":[79],"only":[80],"low-level":[81],"correspondence":[83],"regions":[86],"also":[91],"higher":[93],"intra-modal":[98],"relationships.":[99],"We":[100,126],"propose":[101],"multi-layer":[103],"graph":[104],"convolutional":[105],"network":[106],"object-level,":[108],"object-relational-level,":[109],"higher-level":[111],"learning":[112,150],"sub-networks.":[113],"Our":[114],"method":[115],"learns":[116],"hierarchical":[117],"correspondences":[119],"by":[120],"global":[124],"alignment.":[125],"further":[127],"introduce":[128],"self-attention":[130],"mechanism":[131,146],"after":[132],"word":[134],"embedding":[135],"weaken":[137],"insignificant":[138],"sentence":[142],"cross-attention":[145],"guide":[148],"features.":[153],"Extensive":[154],"experiments":[155],"on":[156],"Flickr30K":[157],"MS-COCO":[159],"datasets":[160],"demonstrate":[161],"effectiveness":[163],"superiority":[165],"our":[167],"proposed":[168],"method.":[169]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}