{"id":"https://openalex.org/W4405778998","doi":"https://doi.org/10.1109/tmm.2024.3521736","title":"Dual Stream Relation Learning Network for Image-Text Retrieval","display_name":"Dual Stream Relation Learning Network for Image-Text Retrieval","publication_year":2024,"publication_date":"2024-12-25","ids":{"openalex":"https://openalex.org/W4405778998","doi":"https://doi.org/10.1109/tmm.2024.3521736"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2024.3521736","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3521736","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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/A5083360832","display_name":"Dongqing Wu","orcid":"https://orcid.org/0000-0003-0749-4050"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Dongqing Wu","raw_affiliation_strings":["School of Automation, Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"School of Automation, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088848549","display_name":"Huihui Li","orcid":"https://orcid.org/0009-0000-0875-2125"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huihui Li","raw_affiliation_strings":["School of Automation, Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"School of Automation, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042976220","display_name":"Cang Gu","orcid":"https://orcid.org/0000-0003-4427-3652"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cang Gu","raw_affiliation_strings":["School of Automation, Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"School of Automation, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100657946","display_name":"Lei Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Guo","raw_affiliation_strings":["School of Automation, Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"School of Automation, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100338895","display_name":"Hang Liu","orcid":"https://orcid.org/0000-0001-7948-4236"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hang Liu","raw_affiliation_strings":["School of Cybersecurity, Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"School of Cybersecurity, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5083360832"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":1.0497,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.79317517,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"27","issue":null,"first_page":"1551","last_page":"1565"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9140999913215637,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9140999913215637,"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":0.8593312501907349},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.636768102645874},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.6326248645782471},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.5260132551193237},{"id":"https://openalex.org/keywords/automatic-image-annotation","display_name":"Automatic image annotation","score":0.4989137649536133},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.49829888343811035},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4205872714519501},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4131110906600952},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2396526336669922}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8593312501907349},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.636768102645874},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.6326248645782471},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.5260132551193237},{"id":"https://openalex.org/C199579030","wikidata":"https://www.wikidata.org/wiki/Q2851778","display_name":"Automatic image annotation","level":4,"score":0.4989137649536133},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.49829888343811035},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4205872714519501},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4131110906600952},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2396526336669922},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2024.3521736","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3521736","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W2064675550","https://openalex.org/W2117539524","https://openalex.org/W2185175083","https://openalex.org/W2549139847","https://openalex.org/W2745461083","https://openalex.org/W2778100917","https://openalex.org/W2883311563","https://openalex.org/W2953037339","https://openalex.org/W2962964995","https://openalex.org/W2963467339","https://openalex.org/W2963882743","https://openalex.org/W2964120214","https://openalex.org/W2968374502","https://openalex.org/W2974592692","https://openalex.org/W2981586349","https://openalex.org/W2988823324","https://openalex.org/W2994818707","https://openalex.org/W2996478685","https://openalex.org/W2997525715","https://openalex.org/W2998215884","https://openalex.org/W3003460937","https://openalex.org/W3009270862","https://openalex.org/W3034305926","https://openalex.org/W3035160838","https://openalex.org/W3035454331","https://openalex.org/W3035497460","https://openalex.org/W3035552787","https://openalex.org/W3035588244","https://openalex.org/W3035605030","https://openalex.org/W3047381720","https://openalex.org/W3092820619","https://openalex.org/W3094172275","https://openalex.org/W3106925514","https://openalex.org/W3118694826","https://openalex.org/W3155230099","https://openalex.org/W3167939936","https://openalex.org/W3174377922","https://openalex.org/W3175888430","https://openalex.org/W3189718596","https://openalex.org/W3190055600","https://openalex.org/W3198064418","https://openalex.org/W4206314411","https://openalex.org/W4210894218","https://openalex.org/W4213348104","https://openalex.org/W4214819138","https://openalex.org/W4224952037","https://openalex.org/W4283394402","https://openalex.org/W4283805294","https://openalex.org/W4283812943","https://openalex.org/W4285118104","https://openalex.org/W4312761738","https://openalex.org/W4312941295","https://openalex.org/W4313429809","https://openalex.org/W4366241040","https://openalex.org/W4385245566","https://openalex.org/W4386071498","https://openalex.org/W4386075677","https://openalex.org/W6631516269","https://openalex.org/W6678470764","https://openalex.org/W6747225742"],"related_works":["https://openalex.org/W3177930984","https://openalex.org/W2052697133","https://openalex.org/W2076896210","https://openalex.org/W2384288472","https://openalex.org/W1539573266","https://openalex.org/W2093596879","https://openalex.org/W2376984068","https://openalex.org/W2201969175","https://openalex.org/W2017257332","https://openalex.org/W2747088704"],"abstract_inverted_index":{"Image-text":[0],"retrieval":[1],"has":[2],"made":[3],"remarkable":[4],"achievements":[5],"through":[6,159,196],"the":[7,39,115,125,154,213],"development":[8],"of":[9,157,217],"feature":[10,36,40],"extraction":[11,41],"networks":[12],"and":[13,63,105,147,150,164,194,198,209,215],"model":[14,124],"architectures.":[15],"However,":[16],"almost":[17],"all":[18],"region":[19,31,56],"feature-based":[20],"methods":[21],"face":[22],"two":[23,96,120,155,204],"serious":[24],"problems":[25],"when":[26],"modeling":[27],"modality":[28],"interactions.":[29],"First,":[30],"features":[32,57,140,158],"are":[33],"prone":[34],"to":[35,46,69,90,122,176],"entanglement":[37],"in":[38],"stage,":[42],"making":[43,66],"it":[44,67],"difficult":[45,68],"accurately":[47],"reason":[48],"complex":[49,151],"intra-model":[50],"relations":[51],"between":[52,128,153,192],"visual":[53,144,174],"objects.":[54],"Second,":[55],"lack":[58],"rich":[59],"contextual":[60],"information,":[61],"background,":[62],"object":[64],"details,":[65],"achieve":[70],"precise":[71,179],"inter-modal":[72,180],"alignment":[73],"with":[74,95],"textual":[75],"information.":[76],"In":[77],"this":[78],"paper,":[79],"we":[80],"propose":[81],"a":[82,99,106,160,187],"novel":[83],"Dual":[84,107],"Stream":[85],"Relation":[86],"Learning":[87],"Network":[88],"(DSRLN)":[89],"jointly":[91],"solve":[92],"these":[93],"issues":[94],"key":[97],"components:":[98],"Geometry-sensitive":[100],"Interactive":[101],"Self-Attention":[102],"(GISA)":[103],"module":[104,163],"Information":[108],"Fusion":[109],"(DIF)":[110],"module.":[111],"Specifically,":[112],"GISA":[113],"extends":[114],"vanilla":[116],"self-attention":[117],"network":[118],"from":[119],"aspects":[121],"better":[123],"intrinsic":[126],"relationships":[127],"different":[129],"regions,":[130],"thereby":[131],"improving":[132],"high-level":[133],"visual-semantic":[134],"reasoning":[135],"ability.":[136],"DIF":[137],"uses":[138],"grid":[139],"as":[141],"an":[142,165],"additional":[143],"information":[145,175],"source,":[146],"achieves":[148],"deeper":[149],"fusion":[152,168],"types":[156],"masked":[161],"cross-attention":[162],"adaptive":[166],"gate":[167],"module,":[169],"which":[170],"can":[171],"capture":[172],"comprehensive":[173,189],"learn":[177],"more":[178,188],"alignment.":[181,200],"Besides,":[182],"our":[183,218],"method":[184],"also":[185],"learns":[186],"hierarchical":[190],"correspondence":[191],"images":[193],"sentences":[195],"local":[197],"global":[199],"Experimental":[201],"results":[202],"on":[203],"public":[205],"datasets,":[206],"i.e.,":[207],"Flickr30K":[208],"MS-COCO,":[210],"fully":[211],"demonstrate":[212],"superiority":[214],"effectiveness":[216],"model.":[219]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}