{"id":"https://openalex.org/W4406890887","doi":"https://doi.org/10.1109/tmm.2025.3535373","title":"Dynamic Visual Semantic Sub-Embeddings and Fast Re-Ranking for Image-Text Retrieval","display_name":"Dynamic Visual Semantic Sub-Embeddings and Fast Re-Ranking for Image-Text Retrieval","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4406890887","doi":"https://doi.org/10.1109/tmm.2025.3535373"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2025.3535373","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3535373","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/A5101245937","display_name":"Wenzhang Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenzhang Wei","raw_affiliation_strings":["School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0009-5748-9437","affiliations":[{"raw_affiliation_string":"School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087201008","display_name":"Zhipeng Gui","orcid":"https://orcid.org/0000-0001-9467-9680"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhipeng Gui","raw_affiliation_strings":["School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0001-9467-9680","affiliations":[{"raw_affiliation_string":"School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100927023","display_name":"Changguang Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changguang Wu","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0005-1813-8897","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Anqi Zhao","orcid":"https://orcid.org/0009-0006-9278-7323"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]},{"id":"https://openalex.org/I4210118728","display_name":"State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing","ror":"https://ror.org/02bpap860","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210118728"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Anqi Zhao","raw_affiliation_strings":["State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Collaborative Innovation Center of Geospatial Technology, Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0006-9278-7323","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Collaborative Innovation Center of Geospatial Technology, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747","https://openalex.org/I4210118728"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064864952","display_name":"Dehua Peng","orcid":"https://orcid.org/0000-0002-9842-0796"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dehua Peng","raw_affiliation_strings":["School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-9842-0796","affiliations":[{"raw_affiliation_string":"School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030670883","display_name":"Huayi Wu","orcid":"https://orcid.org/0000-0003-3971-0512"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]},{"id":"https://openalex.org/I4210118728","display_name":"State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing","ror":"https://ror.org/02bpap860","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210118728"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huayi Wu","raw_affiliation_strings":["State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Collaborative Innovation Center of Geospatial Technology, Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0003-3971-0512","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Collaborative Innovation Center of Geospatial Technology, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747","https://openalex.org/I4210118728"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.8242,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.96489516,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"27","issue":null,"first_page":"3781","last_page":"3796"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9986000061035156,"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":0.9986000061035156,"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":0.9984999895095825,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9934999942779541,"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":0.8606499433517456},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.7052498459815979},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5945227742195129},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.5534602403640747},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5088334679603577},{"id":"https://openalex.org/keywords/visual-word","display_name":"Visual Word","score":0.5031387209892273},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4686412513256073},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3901272714138031},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3276817798614502}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8606499433517456},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.7052498459815979},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5945227742195129},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5534602403640747},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5088334679603577},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.5031387209892273},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4686412513256073},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3901272714138031},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3276817798614502}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2025.3535373","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3535373","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":[{"id":"https://openalex.org/G7944623077","display_name":null,"funder_award_id":"41971349","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8524363716","display_name":null,"funder_award_id":"42090010","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8773897565","display_name":null,"funder_award_id":"41930107","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":false,"pdf":false},"content_urls":null,"referenced_works_count":85,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1677182931","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W2034546064","https://openalex.org/W2108598243","https://openalex.org/W2157331557","https://openalex.org/W2185175083","https://openalex.org/W2194775991","https://openalex.org/W2209877316","https://openalex.org/W2250539671","https://openalex.org/W2463955103","https://openalex.org/W2549139847","https://openalex.org/W2584637367","https://openalex.org/W2596142952","https://openalex.org/W2745461083","https://openalex.org/W2883311563","https://openalex.org/W2956018683","https://openalex.org/W2962964995","https://openalex.org/W2963588253","https://openalex.org/W2963703197","https://openalex.org/W2964120214","https://openalex.org/W2964271799","https://openalex.org/W2981448908","https://openalex.org/W2988823324","https://openalex.org/W3005881764","https://openalex.org/W3010277541","https://openalex.org/W3021938280","https://openalex.org/W3035454331","https://openalex.org/W3035605030","https://openalex.org/W3036900224","https://openalex.org/W3081484346","https://openalex.org/W3088460296","https://openalex.org/W3090449556","https://openalex.org/W3092820619","https://openalex.org/W3094673569","https://openalex.org/W3108373531","https://openalex.org/W3118694826","https://openalex.org/W3119635706","https://openalex.org/W3137228985","https://openalex.org/W3155230099","https://openalex.org/W3168433561","https://openalex.org/W3169472988","https://openalex.org/W3175593095","https://openalex.org/W3175888430","https://openalex.org/W4206314411","https://openalex.org/W4210894218","https://openalex.org/W4224911357","https://openalex.org/W4224952037","https://openalex.org/W4295996379","https://openalex.org/W4304091789","https://openalex.org/W4312761738","https://openalex.org/W4313595453","https://openalex.org/W4317436342","https://openalex.org/W4323797084","https://openalex.org/W4367060669","https://openalex.org/W4385245566","https://openalex.org/W4386071757","https://openalex.org/W4386075677","https://openalex.org/W4386075815","https://openalex.org/W4386501573","https://openalex.org/W4386766892","https://openalex.org/W4387968297","https://openalex.org/W4390603585","https://openalex.org/W4390871707","https://openalex.org/W4391216079","https://openalex.org/W4396842107","https://openalex.org/W6631516269","https://openalex.org/W6638319203","https://openalex.org/W6676647902","https://openalex.org/W6678470764","https://openalex.org/W6738279954","https://openalex.org/W6747225742","https://openalex.org/W6755207826","https://openalex.org/W6766904570","https://openalex.org/W6776644650","https://openalex.org/W6778102432","https://openalex.org/W6780226713","https://openalex.org/W6787356946","https://openalex.org/W6789753369","https://openalex.org/W6791353385","https://openalex.org/W6798805250","https://openalex.org/W6844194202","https://openalex.org/W6846684553","https://openalex.org/W6856418681"],"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":{"The":[0,212],"core":[1],"of":[2,24,65,107,198,209,215,226],"image-text":[3],"retrieval":[4,160,218],"is":[5,77],"to":[6,21,97,123,139,143,156,229],"accurately":[7],"measure":[8],"the":[9,28,62,99,118,144,159,164,168,196,210,224],"similarity":[10],"between":[11],"different":[12,141,199],"modalities":[13],"in":[14,44,75,80],"a":[15,25,90,105,130,135,151,206],"unified":[16],"representation":[17,64],"space.":[18],"However,":[19],"compared":[20],"textual":[22,42],"descriptions":[23],"certain":[26],"perspective,":[27],"visual":[29,109],"modality":[30],"has":[31],"more":[32],"semantic":[33,67,126,231],"variations.":[34,232],"Therefore,":[35],"images":[36],"are":[37],"usually":[38],"associated":[39],"with":[40,170],"multiple":[41,66],"captions":[43],"databases.":[45],"Although":[46],"popular":[47],"symmetric":[48],"embedding":[49],"methods":[50],"have":[51],"explored":[52],"numerous":[53],"modal":[54],"interaction":[55],"approaches,":[56],"they":[57],"often":[58],"learn":[59],"toward":[60],"outputting":[61],"average":[63],"variations":[68],"within":[69],"image":[70,121,176],"embeddings.":[71],"Consequently,":[72],"information":[73,100],"entropy":[74],"embeddings":[76,122],"increased,":[78],"resulting":[79],"redundancy":[81],"and":[82,133,162,179,190,204,219],"decreased":[83],"accuracy.":[84],"In":[85,147],"this":[86],"work,":[87],"we":[88,103,128,149],"propose":[89],"Dynamic":[91],"Visual":[92],"Semantic":[93],"Sub-Embeddings":[94],"framework":[95],"(DVSE)":[96],"reduce":[98],"entropy.":[101],"Specifically,":[102],"obtain":[104],"set":[106],"heterogeneous":[108],"sub-embeddings":[110],"through":[111],"dynamic":[112],"orthogonal":[113],"constraint":[114],"loss.":[115],"To":[116],"encourage":[117],"generated":[119],"candidate":[120],"capture":[124],"various":[125],"variations,":[127],"construct":[129],"mixed":[131],"distribution":[132],"employ":[134],"variance-aware":[136],"weighting":[137],"loss":[138],"assign":[140],"weights":[142],"optimization":[145],"process.":[146],"addition,":[148],"develop":[150],"Fast":[152],"Re-ranking":[153],"strategy":[154],"(FR)":[155],"efficiently":[157],"evaluate":[158],"results":[161],"enhance":[163],"performance.":[165],"We":[166,193],"compare":[167],"performance":[169],"existing":[171],"set-based":[172],"method":[173,228],"using":[174],"five":[175],"feature":[177,182],"encoders":[178,183],"three":[180,185],"text":[181],"on":[184],"benchmark":[186],"datasets:":[187],"MSCOCO,":[188],"Flickr30K":[189],"CUB":[191],"Captions.":[192],"also":[194],"show":[195],"role":[197],"components":[200],"by":[201],"ablation":[202],"studies":[203],"perform":[205],"sensitivity":[207],"analysis":[208,214],"hyperparameters.":[211],"qualitative":[213],"visualized":[216],"bidirectional":[217],"attention":[220],"maps":[221],"further":[222],"demonstrates":[223],"ability":[225],"our":[227],"encode":[230]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":5}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}