{"id":"https://openalex.org/W4417105708","doi":"https://doi.org/10.1145/3746027.3755468","title":"Hubness Reduction with Dual Bank Sinkhorn Normalization for Cross-Modal Retrieval","display_name":"Hubness Reduction with Dual Bank Sinkhorn Normalization for Cross-Modal Retrieval","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4417105708","doi":"https://doi.org/10.1145/3746027.3755468"},"language":"en","primary_location":{"id":"doi:10.1145/3746027.3755468","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755468","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.02538","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005961599","display_name":"Zhengxin Pan","orcid":"https://orcid.org/0000-0003-2003-0728"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengxin Pan","raw_affiliation_strings":["Zhejiang Key Lab of Accessible Perception & Intelligent Systems, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-2003-0728","affiliations":[{"raw_affiliation_string":"Zhejiang Key Lab of Accessible Perception & Intelligent Systems, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047118636","display_name":"Haishuai Wang","orcid":"https://orcid.org/0000-0003-1617-0920"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haishuai Wang","raw_affiliation_strings":["Zhejiang Key Lab of Accessible Perception & Intelligent Systems, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-1617-0920","affiliations":[{"raw_affiliation_string":"Zhejiang Key Lab of Accessible Perception & Intelligent Systems, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026986847","display_name":"Fangyu Wu","orcid":"https://orcid.org/0000-0001-9618-8965"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangyu Wu","raw_affiliation_strings":["School of Advanced Technology, Xi'an Jiaotong-Liverpool University, Suzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-9618-8965","affiliations":[{"raw_affiliation_string":"School of Advanced Technology, Xi'an Jiaotong-Liverpool University, Suzhou, China","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Peng Zhang","orcid":"https://orcid.org/0000-0001-7973-2746"},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Zhang","raw_affiliation_strings":["Cyberspace Institute of Advanced Technology, Guangzhou University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-7973-2746","affiliations":[{"raw_affiliation_string":"Cyberspace Institute of Advanced Technology, Guangzhou University, Guangzhou, China","institution_ids":["https://openalex.org/I37987034"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052757755","display_name":"Jiajun Bu","orcid":"https://orcid.org/0000-0002-1097-2044"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiajun Bu","raw_affiliation_strings":["Zhejiang Key Lab of Accessible Perception & Intelligent Systems, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-1097-2044","affiliations":[{"raw_affiliation_string":"Zhejiang Key Lab of Accessible Perception & Intelligent Systems, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I4210123185"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6153","last_page":"6162"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.4672999978065491,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.4672999978065491,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.22089999914169312,"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":0.1624000072479248,"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/normalization","display_name":"Normalization (sociology)","score":0.7078999876976013},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.4011000096797943},{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.3880000114440918},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.3009999990463257},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.2890999913215637},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.2676999866962433}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7486000061035156},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7078999876976013},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4887999892234802},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.40119999647140503},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.4011000096797943},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.3880000114440918},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.3009999990463257},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.2890999913215637},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.2676999866962433},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.2639999985694885},{"id":"https://openalex.org/C22088475","wikidata":"https://www.wikidata.org/wiki/Q647974","display_name":"Data envelopment analysis","level":2,"score":0.2621999979019165},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.25839999318122864}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746027.3755468","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755468","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2508.02538","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.02538","pdf_url":"https://arxiv.org/pdf/2508.02538","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2508.02538","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.02538","pdf_url":"https://arxiv.org/pdf/2508.02538","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1927052826","https://openalex.org/W2078238240","https://openalex.org/W2108598243","https://openalex.org/W2185175083","https://openalex.org/W2425121537","https://openalex.org/W2471768434","https://openalex.org/W2526417872","https://openalex.org/W2571918261","https://openalex.org/W2803107279","https://openalex.org/W2885775891","https://openalex.org/W2963017553","https://openalex.org/W2989322838","https://openalex.org/W3015591594","https://openalex.org/W4214807529","https://openalex.org/W4285606530","https://openalex.org/W4304014690","https://openalex.org/W4312299780","https://openalex.org/W4312372711","https://openalex.org/W4312999114","https://openalex.org/W4372260310","https://openalex.org/W4386071512","https://openalex.org/W4390871725","https://openalex.org/W4390872434","https://openalex.org/W4392678259","https://openalex.org/W4393147969","https://openalex.org/W4402541917","https://openalex.org/W4402704596","https://openalex.org/W4402715976","https://openalex.org/W4402727764","https://openalex.org/W4402753881","https://openalex.org/W4409346371","https://openalex.org/W4413145922"],"related_works":[],"abstract_inverted_index":{"The":[0],"past":[1],"decade":[2],"has":[3],"witnessed":[4],"rapid":[5],"advancements":[6],"in":[7,14,79],"cross-modal":[8,20,198],"retrieval,":[9,203,205,208],"with":[10],"significant":[11,159],"progress":[12],"made":[13],"accurately":[15],"measuring":[16],"the":[17,23,46,70,111,132,163,185,214],"similarity":[18,49],"between":[19,162],"pairs.":[21],"However,":[22],"persistent":[24],"hubness":[25,97],"problem,":[26],"a":[27,30,91,146,158,180],"phenomenon":[28],"where":[29,131],"small":[31],"number":[32],"of":[33,48,216],"targets":[34],"frequently":[35],"appear":[36],"as":[37],"nearest":[38],"neighbors":[39],"to":[40,44,55,113,129,149,157,188],"numerous":[41],"queries,":[42],"continues":[43],"hinder":[45],"precision":[47],"measurements.":[50],"Despite":[51],"several":[52],"proposed":[53],"methods":[54],"reduce":[56],"hubness,":[57,152],"their":[58],"underlying":[59],"mechanisms":[60],"remain":[61],"poorly":[62],"understood.":[63],"To":[64,168],"bridge":[65],"this":[66,170,190],"gap,":[67],"we":[68,89,126,172],"analyze":[69],"widely-adopted":[71],"Inverted":[72],"Softmax":[73],"approach":[74],"and":[75,117,166,206,219],"demonstrate":[76],"its":[77],"effectiveness":[78,215],"balancing":[80,102],"target":[81,103,118,151,182],"probabilities":[82,104,119],"during":[83],"retrieval.":[84],"Building":[85],"on":[86,145],"these":[87],"insights,":[88],"propose":[90],"probability-balancing":[92],"framework":[93,112],"for":[94],"more":[95],"effective":[96],"reduction.":[98],"We":[99],"contend":[100],"that":[101,139],"alone":[105],"is":[106,136],"inadequate":[107],"and,":[108],"therefore,":[109],"extend":[110,127],"balance":[114],"both":[115,217],"query":[116,134,147,164,186],"by":[120],"introducing":[121],"Sinkhorn":[122,176],"Normalization":[123,177],"(SN).":[124],"Notably,":[125],"SN":[128,218],"scenarios":[130],"true":[133],"distribution":[135],"unknown,":[137],"showing":[138],"current":[140],"methods,":[141],"which":[142],"rely":[143],"solely":[144],"bank":[148,165,183,187],"estimate":[150],"produce":[153],"suboptimal":[154],"results":[155],"due":[156],"distributional":[160,191],"gap":[161],"targets.":[167],"mitigate":[169],"issue,":[171],"introduce":[173],"Dual":[174],"Bank":[175],"(DBSN),":[178],"incorporating":[179],"corresponding":[181],"alongside":[184],"narrow":[189],"gap.":[192],"Our":[193],"comprehensive":[194],"evaluation":[195],"across":[196],"various":[197],"retrieval":[199],"tasks,":[200],"including":[201],"image-text":[202],"video-text":[204],"audio-text":[207],"demonstrates":[209],"consistent":[210],"performance":[211],"improvements,":[212],"validating":[213],"DBSN.":[220],"All":[221],"codes":[222],"are":[223],"publicly":[224],"available":[225],"at":[226],"https://github.com/ppanzx/DBSN.":[227]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}