{"id":"https://openalex.org/W4416249707","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227703","title":"Latent Space Semantic Alignment Network Based on Momentum Contrast for Image-Text Retrieval","display_name":"Latent Space Semantic Alignment Network Based on Momentum Contrast for Image-Text Retrieval","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416249707","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227703"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11227703","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227703","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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/A5101512008","display_name":"Bo Lu","orcid":"https://orcid.org/0000-0002-4879-1388"},"institutions":[{"id":"https://openalex.org/I61565387","display_name":"Dalian Minzu University","ror":"https://ror.org/02hxfx521","country_code":"CN","type":"education","lineage":["https://openalex.org/I61565387"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Lu","raw_affiliation_strings":["Dalian Minzu University,College of Computer Science and Engineering,Dalian,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian Minzu University,College of Computer Science and Engineering,Dalian,China","institution_ids":["https://openalex.org/I61565387"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101770351","display_name":"Xiaoliang Wu","orcid":"https://orcid.org/0000-0003-2209-870X"},"institutions":[{"id":"https://openalex.org/I61565387","display_name":"Dalian Minzu University","ror":"https://ror.org/02hxfx521","country_code":"CN","type":"education","lineage":["https://openalex.org/I61565387"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojin Wu","raw_affiliation_strings":["Dalian Minzu University,College of Computer Science and Engineering,Dalian,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian Minzu University,College of Computer Science and Engineering,Dalian,China","institution_ids":["https://openalex.org/I61565387"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100567140","display_name":"Haibin Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I61565387","display_name":"Dalian Minzu University","ror":"https://ror.org/02hxfx521","country_code":"CN","type":"education","lineage":["https://openalex.org/I61565387"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haibin Zhu","raw_affiliation_strings":["Dalian Minzu University,College of Computer Science and Engineering,Dalian,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian Minzu University,College of Computer Science and Engineering,Dalian,China","institution_ids":["https://openalex.org/I61565387"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042261863","display_name":"Tianyuan Zhong","orcid":null},"institutions":[{"id":"https://openalex.org/I61565387","display_name":"Dalian Minzu University","ror":"https://ror.org/02hxfx521","country_code":"CN","type":"education","lineage":["https://openalex.org/I61565387"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyuan Zhong","raw_affiliation_strings":["Dalian Minzu University,College of Computer Science and Engineering,Dalian,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian Minzu University,College of Computer Science and Engineering,Dalian,China","institution_ids":["https://openalex.org/I61565387"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104282400","display_name":"Lin Gan","orcid":null},"institutions":[{"id":"https://openalex.org/I61565387","display_name":"Dalian Minzu University","ror":"https://ror.org/02hxfx521","country_code":"CN","type":"education","lineage":["https://openalex.org/I61565387"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Gan","raw_affiliation_strings":["Dalian Minzu University,College of Computer Science and Engineering,Dalian,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian Minzu University,College of Computer Science and Engineering,Dalian,China","institution_ids":["https://openalex.org/I61565387"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113178376","display_name":"Ying Gao","orcid":"https://orcid.org/0009-0000-5196-8896"},"institutions":[{"id":"https://openalex.org/I61565387","display_name":"Dalian Minzu University","ror":"https://ror.org/02hxfx521","country_code":"CN","type":"education","lineage":["https://openalex.org/I61565387"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Gao","raw_affiliation_strings":["Dalian Minzu University,College of Computer Science and Engineering,Dalian,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian Minzu University,College of Computer Science and Engineering,Dalian,China","institution_ids":["https://openalex.org/I61565387"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I61565387"],"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":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9053999781608582,"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":0.9053999781608582,"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":0.019500000402331352,"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":0.016699999570846558,"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/inference","display_name":"Inference","score":0.6453999876976013},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5788999795913696},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5468999743461609},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.5335999727249146},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.5144000053405762},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4706000089645386},{"id":"https://openalex.org/keywords/probabilistic-latent-semantic-analysis","display_name":"Probabilistic latent semantic analysis","score":0.4544000029563904},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.43720000982284546}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7382000088691711},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6453999876976013},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5788999795913696},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5777000188827515},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5468999743461609},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.5335999727249146},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.5144000053405762},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4706000089645386},{"id":"https://openalex.org/C112933361","wikidata":"https://www.wikidata.org/wiki/Q2845258","display_name":"Probabilistic latent semantic analysis","level":2,"score":0.4544000029563904},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.43720000982284546},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4081000089645386},{"id":"https://openalex.org/C170133592","wikidata":"https://www.wikidata.org/wiki/Q1806883","display_name":"Latent semantic analysis","level":2,"score":0.3977000117301941},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3970000147819519},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3953999876976013},{"id":"https://openalex.org/C2986420190","wikidata":"https://www.wikidata.org/wiki/Q39045939","display_name":"Semantic space","level":2,"score":0.38999998569488525},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.35019999742507935},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31130000948905945},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3095000088214874},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.2759000062942505},{"id":"https://openalex.org/C60718061","wikidata":"https://www.wikidata.org/wiki/Q1414747","display_name":"Momentum (technical analysis)","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.25600001215934753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11227703","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227703","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320311687","display_name":"Ministry of Education","ror":"https://ror.org/03m01yf64"},{"id":"https://openalex.org/F4320327681","display_name":"Yunnan Normal University","ror":"https://ror.org/00sc9n023"},{"id":"https://openalex.org/F4320334111","display_name":"Innovation Fund","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1861492603","https://openalex.org/W2185175083","https://openalex.org/W2277195237","https://openalex.org/W2745461083","https://openalex.org/W2962964995","https://openalex.org/W2988823324","https://openalex.org/W2994818707","https://openalex.org/W3035454331","https://openalex.org/W3035524453","https://openalex.org/W3035605030","https://openalex.org/W3118694826","https://openalex.org/W3174808259","https://openalex.org/W3175888430","https://openalex.org/W4210894218","https://openalex.org/W4224952037","https://openalex.org/W4308774120","https://openalex.org/W4312761738","https://openalex.org/W4366241040","https://openalex.org/W4386071498","https://openalex.org/W4386071757"],"related_works":[],"abstract_inverted_index":{"Image-text":[0],"retrieval":[1,74],"is":[2,15],"an":[3,18],"important":[4],"task":[5],"in":[6,68],"bridging":[7],"vision":[8],"and":[9,11,20,53,65,83,100,150,166,192],"language,":[10],"its":[12],"key":[13],"challenge":[14],"to":[16,46,62],"achieve":[17],"accurate":[19],"efficient":[21,207],"semantic":[22,148,151],"alignment":[23],"between":[24],"the":[25,36,87,95,102,136,171,177,182],"two":[26,38],"modalities.":[27,154],"Although":[28],"advancements":[29],"have":[30],"been":[31],"achieved,":[32],"there":[33],"are":[34,56],"still":[35],"following":[37],"limitations:":[39],"(1)":[40],"While":[41],"current":[42],"methods":[43,203],"utilize":[44],"self-attention":[45,139],"capture":[47],"region-level":[48,138],"relationships":[49,55],"within":[50,79],"samples,":[51],"cross-sample":[52],"cross-modal":[54,157],"often":[57],"overlooked,":[58],"making":[59],"it":[60],"difficult":[61],"align":[63],"image":[64],"text":[66],"semantics":[67],"a":[69,112,128,156,163,167],"shared":[70,141],"embedding":[71],"space.":[72],"(2)Image-text":[73],"typically":[75],"involves":[76],"contrastive":[77,159],"learning":[78,104],"batches":[80],"containing":[81],"positive":[82],"negative":[84,98,174,185],"samples;":[85],"however,":[86],"batch":[88,178],"size,":[89,179],"constrained":[90],"by":[91],"GPU":[92],"limitations,":[93],"limits":[94],"scale":[96],"of":[97,162,173,184],"samples":[99,175],"consequently":[101],"model\u2019s":[103],"capability.":[105],"To":[106],"address":[107],"these":[108],"problems,":[109],"we":[110,126],"propose":[111],"novel":[113],"Latent":[114,129],"Space":[115,130],"Semantic":[116],"Alignment":[117,132],"Network(LSAN)":[118],"based":[119],"on":[120,190],"momentum":[121,158,164],"contrast":[122],"for":[123],"ITR.":[124],"Specifically,":[125],"introduce":[127],"Attention":[131],"Module":[133],"that":[134,195],"replaces":[135],"original":[137],"with":[140],"latent":[142],"space":[143],"attention,":[144],"effectively":[145],"identifying":[146],"subtle":[147],"differences":[149],"consistency":[152],"across":[153],"Concurrently,":[155],"framework,":[160],"composed":[161],"encoder":[165],"dynamic":[168],"queue,":[169],"decouples":[170],"number":[172],"from":[176],"which":[180],"expands":[181],"quantity":[183],"samples.":[186],"Extensive":[187],"experiments":[188],"conducted":[189],"Flickr30K":[191],"MSCOCO":[193],"demonstrate":[194],"our":[196],"LSAN":[197],"not":[198],"only":[199],"outperforms":[200],"existing":[201],"state-of-the-art":[202],"but":[204],"also":[205],"maintains":[206],"inference":[208],"performance.":[209]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-14T00:00:00"}