{"id":"https://openalex.org/W4411215554","doi":"https://doi.org/10.1007/s40747-025-01946-1","title":"Progressive multi-subspace fusion for text-image matching","display_name":"Progressive multi-subspace fusion for text-image matching","publication_year":2025,"publication_date":"2025-06-11","ids":{"openalex":"https://openalex.org/W4411215554","doi":"https://doi.org/10.1007/s40747-025-01946-1"},"language":"en","primary_location":{"id":"doi:10.1007/s40747-025-01946-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-025-01946-1","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-025-01946-1.pdf","source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex & Intelligent Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://link.springer.com/content/pdf/10.1007/s40747-025-01946-1.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019253498","display_name":"Haoming Wang","orcid":"https://orcid.org/0000-0002-4824-6662"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]},{"id":"https://openalex.org/I4210134428","display_name":"Chinese People's Armed Police Force Engineering University","ror":"https://ror.org/031jzbb03","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210134428"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoming Wang","raw_affiliation_strings":["Engineering University of People\u2019s Armed Police, 710078, Shaanxi, Xi\u2019an, China","School of Electronic & Information Engineering, Xi\u2019an Jiaotong University, Xi\u2019an, 710049, Shaanxi, China","Engineering University of People's Armed Police, 710078, Shaanxi, Xi'an, China","School of Electronic & Information Engineering, Xi'an Jiaotong University, Xi'an, 710049, Shaanxi, China"],"affiliations":[{"raw_affiliation_string":"Engineering University of People\u2019s Armed Police, 710078, Shaanxi, Xi\u2019an, China","institution_ids":["https://openalex.org/I4210134428"]},{"raw_affiliation_string":"School of Electronic & Information Engineering, Xi\u2019an Jiaotong University, Xi\u2019an, 710049, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"Engineering University of People's Armed Police, 710078, Shaanxi, Xi'an, China","institution_ids":[]},{"raw_affiliation_string":"School of Electronic & Information Engineering, Xi'an Jiaotong University, Xi'an, 710049, Shaanxi, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100635247","display_name":"Li Zhu","orcid":"https://orcid.org/0000-0002-4586-1192"},"institutions":[{"id":"https://openalex.org/I4210134428","display_name":"Chinese People's Armed Police Force Engineering University","ror":"https://ror.org/031jzbb03","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210134428"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Zhu","raw_affiliation_strings":["Engineering University of People\u2019s Armed Police, 710078, Shaanxi, Xi\u2019an, China","Engineering University of People's Armed Police, 710078, Shaanxi, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Engineering University of People\u2019s Armed Police, 710078, Shaanxi, Xi\u2019an, China","institution_ids":["https://openalex.org/I4210134428"]},{"raw_affiliation_string":"Engineering University of People's Armed Police, 710078, Shaanxi, Xi'an, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031638251","display_name":"Wentao Ma","orcid":"https://orcid.org/0000-0003-3059-6629"},"institutions":[{"id":"https://openalex.org/I140221134","display_name":"Anhui Agricultural University","ror":"https://ror.org/0327f3359","country_code":"CN","type":"education","lineage":["https://openalex.org/I140221134"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wentao Ma","raw_affiliation_strings":["School of Information and Artificial Intelligence, Anhui Agricultural University, Hefei, 230036, Anhui, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Artificial Intelligence, Anhui Agricultural University, Hefei, 230036, Anhui, China","institution_ids":["https://openalex.org/I140221134"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063724348","display_name":"Qi Guo","orcid":"https://orcid.org/0000-0001-5507-3424"},"institutions":[{"id":"https://openalex.org/I4210134428","display_name":"Chinese People's Armed Police Force Engineering University","ror":"https://ror.org/031jzbb03","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210134428"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qian\u2019ge Guo","raw_affiliation_strings":["Engineering University of People\u2019s Armed Police, 710078, Shaanxi, Xi\u2019an, China","Engineering University of People's Armed Police, 710078, Shaanxi, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Engineering University of People\u2019s Armed Police, 710078, Shaanxi, Xi\u2019an, China","institution_ids":["https://openalex.org/I4210134428"]},{"raw_affiliation_string":"Engineering University of People's Armed Police, 710078, Shaanxi, Xi'an, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5031638251"],"corresponding_institution_ids":["https://openalex.org/I140221134"],"apc_list":{"value":1320,"currency":"GBP","value_usd":1619},"apc_paid":{"value":1320,"currency":"GBP","value_usd":1619},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11729769,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"11","issue":"8","first_page":null,"last_page":null},"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":0.9994999766349792,"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":0.9973999857902527,"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":0.7301390171051025},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6418078541755676},{"id":"https://openalex.org/keywords/linear-subspace","display_name":"Linear subspace","score":0.6196793913841248},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6086424589157104},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5680227279663086},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.5494545698165894},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5384812951087952},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5123144388198853},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4934765100479126},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.4857902526855469},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4836919903755188},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40742573142051697},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34741514921188354},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12302544713020325}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7301390171051025},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6418078541755676},{"id":"https://openalex.org/C12362212","wikidata":"https://www.wikidata.org/wiki/Q728435","display_name":"Linear subspace","level":2,"score":0.6196793913841248},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6086424589157104},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5680227279663086},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.5494545698165894},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5384812951087952},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5123144388198853},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4934765100479126},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.4857902526855469},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4836919903755188},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40742573142051697},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34741514921188354},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12302544713020325},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s40747-025-01946-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-025-01946-1","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-025-01946-1.pdf","source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex & Intelligent Systems","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:f2a130956e4c43659d7551a72a939fd5","is_oa":true,"landing_page_url":"https://doaj.org/article/f2a130956e4c43659d7551a72a939fd5","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Complex & Intelligent Systems, Vol 11, Iss 8, Pp 1-16 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s40747-025-01946-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-025-01946-1","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-025-01946-1.pdf","source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex & Intelligent Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6299999952316284,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G4715595647","display_name":null,"funder_award_id":"62072465","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6518624845","display_name":null,"funder_award_id":"61772561","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411215554.pdf","grobid_xml":"https://content.openalex.org/works/W4411215554.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1532008752","https://openalex.org/W1861492603","https://openalex.org/W2185175083","https://openalex.org/W2883311563","https://openalex.org/W2962964995","https://openalex.org/W2988823324","https://openalex.org/W2994818707","https://openalex.org/W3004153761","https://openalex.org/W3005971801","https://openalex.org/W3010277541","https://openalex.org/W3035356601","https://openalex.org/W3035552787","https://openalex.org/W3035605030","https://openalex.org/W3110042533","https://openalex.org/W3175888430","https://openalex.org/W3205408642","https://openalex.org/W3206597437","https://openalex.org/W3207608362","https://openalex.org/W4206546481","https://openalex.org/W4213348104","https://openalex.org/W4214593719","https://openalex.org/W4214819138","https://openalex.org/W4224952037","https://openalex.org/W4283394402","https://openalex.org/W4285138127","https://openalex.org/W4285606530","https://openalex.org/W4295679074","https://openalex.org/W4304014690","https://openalex.org/W4307233751","https://openalex.org/W4312372711","https://openalex.org/W4388145471","https://openalex.org/W4388430673","https://openalex.org/W6611765436"],"related_works":["https://openalex.org/W3100286349","https://openalex.org/W2896134808","https://openalex.org/W4289378085","https://openalex.org/W4294291164","https://openalex.org/W3172436493","https://openalex.org/W1887135636","https://openalex.org/W4287164812","https://openalex.org/W2386063599","https://openalex.org/W1975884855","https://openalex.org/W3213150849"],"abstract_inverted_index":{"Abstract":[0],"Text-image":[1],"cross-model":[2],"matching":[3],"is":[4],"a":[5,51,97,122,137,171,192],"core":[6],"challenge":[7],"in":[8,26,78,85],"multimodal":[9],"machine":[10],"learning,":[11],"aiming":[12],"to":[13,42,49,68,132,140,153],"enable":[14],"efficient":[15],"retrieval":[16,44,189],"of":[17,74,81,170,195],"images":[18],"and":[19,36,58,130,147,182,197],"texts":[20],"across":[21],"different":[22,79],"modalities.":[23,90],"The":[24],"difficulty":[25],"this":[27],"task":[28],"stems":[29],"from":[30],"the":[31,71,82,89,117],"inherent":[32],"gap":[33,119],"between":[34,88],"text":[35,59],"image":[37,57,146],"representations,":[38],"which":[39,149],"can":[40,60],"lead":[41],"suboptimal":[43],"performance.":[45],"Traditional":[46],"approaches":[47],"attempt":[48],"learn":[50],"shared":[52,172],"representation":[53,173],"space":[54],"where":[55],"both":[56,145],"be":[61],"directly":[62],"compared.":[63],"However,":[64],"they":[65],"often":[66],"fail":[67],"account":[69],"for":[70,111,144],"varying":[72],"levels":[73],"semantic":[75],"information":[76],"captured":[77],"layers":[80],"encoders,":[83],"resulting":[84],"inadequate":[86],"alignment":[87],"To":[91],"address":[92],"these":[93],"limitations,":[94],"we":[95],"propose":[96],"novel":[98],"approach":[99],"called":[100],"P":[101],"rogressive":[102],"M":[103],"ulti-":[104],"S":[105],"ubspace":[106],"F":[107],"usion,":[108],"dubbed":[109],"PMSF":[110,186],"text-image":[112],"matching.":[113],"Our":[114],"model":[115,118],"reduces":[116],"by":[120],"using":[121],"progressive":[123],"learning":[124,169],"process,":[125],"starting":[126],"with":[127],"shallow":[128],"representations":[129],"moving":[131],"deeper":[133],"layers.":[134],"We":[135],"use":[136],"dual-tower":[138],"structure":[139],"encode":[141],"multi-level":[142],"features":[143],"text,":[148],"are":[150,159],"then":[151],"mapped":[152],"corresponding":[154],"auxiliary":[155],"subspaces.":[156],"These":[157],"subspaces":[158],"fused":[160],"through":[161],"an":[162],"adaptive":[163],"GPO":[164],"pooling":[165],"strategy,":[166],"enabling":[167],"joint":[168],"space.":[174],"Experimental":[175],"results":[176],"on":[177],"benchmark":[178],"datasets,":[179],"including":[180],"Flickr30K":[181],"MSCOCO,":[183],"show":[184],"that":[185],"significantly":[187],"improves":[188],"performance,":[190],"achieving":[191],"Rsum":[193],"score":[194],"516.9":[196],"510.7,":[198],"outperforming":[199],"23":[200],"state-of-the-art":[201],"methods.":[202]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}