{"id":"https://openalex.org/W7138049414","doi":"https://doi.org/10.48550/arxiv.2603.14349","title":"Learning Image-Text Matching with Optimal Partial Transport","display_name":"Learning Image-Text Matching with Optimal Partial Transport","publication_year":2026,"publication_date":"2026-03-15","ids":{"openalex":"https://openalex.org/W7138049414","doi":"https://doi.org/10.48550/arxiv.2603.14349"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.14349","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.14349","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.14349","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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pan, Zhengxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129698198","display_name":"Haishuai Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Haishuai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026986847","display_name":"Fangyu Wu","orcid":"https://orcid.org/0000-0001-9618-8965"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Fangyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101991543","display_name":"Bailing Zhang","orcid":"https://orcid.org/0000-0001-5762-5763"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Bailing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129715618","display_name":"Jiajun Bu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bu, Jiajun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129652643","display_name":"Hongyang Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Hongyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":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":0.8463000059127808,"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":0.8463000059127808,"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":0.12349999696016312,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.006599999964237213,"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/bridging","display_name":"Bridging (networking)","score":0.6625999808311462},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6291000247001648},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5885999798774719},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5508999824523926},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5332000255584717},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4074000120162964},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.39590001106262207}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8510000109672546},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.6625999808311462},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6291000247001648},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5885999798774719},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5638999938964844},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5508999824523926},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5332000255584717},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4530999958515167},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4074000120162964},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.39590001106262207},{"id":"https://openalex.org/C2778493491","wikidata":"https://www.wikidata.org/wiki/Q7449072","display_name":"Semantic matching","level":3,"score":0.34869998693466187},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.34779998660087585},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34769999980926514},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.32330000400543213},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.29829999804496765},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.2971000075340271},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2939999997615814},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2797999978065491},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.275299996137619},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.26809999346733093}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.14349","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.14349","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.14349","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.14349","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Cross-modal":[0,79],"matching,":[1,168],"a":[2],"fundamental":[3],"task":[4],"in":[5,67,153],"bridging":[6],"vision":[7],"and":[8,41,90,138],"language,":[9],"has":[10],"recently":[11],"garnered":[12],"substantial":[13],"research":[14],"interest.":[15],"Despite":[16],"the":[17,25,49,68,76,85,102,119],"development":[18],"of":[19,36,71,78,104,121,128],"numerous":[20],"methods":[21,32],"aimed":[22],"at":[23,180],"quantifying":[24],"semantic":[26],"relatedness":[27],"between":[28,87],"image-text":[29,133],"pairs,":[30],"these":[31],"often":[33],"fall":[34],"short":[35],"achieving":[37],"both":[38,147],"outstanding":[39],"performance":[40,62,142],"high":[42],"efficiency.":[43,65],"In":[44],"this":[45],"paper,":[46],"we":[47,107,161],"propose":[48],"crOss-Modal":[50],"sInkhorn":[51],"maTching":[52],"(OMIT)":[53],"network":[54],"as":[55],"an":[56],"effective":[57],"solution":[58],"to":[59,82,117],"effectively":[60],"improving":[61],"while":[63],"maintaining":[64],"Rooted":[66],"theoretical":[69],"foundations":[70],"Optimal":[72],"Transport,":[73],"OMIT":[74,129,145],"harnesses":[75],"capabilities":[77],"Mover's":[80],"Distance":[81],"precisely":[83],"compute":[84],"similarity":[86],"fine-grained":[88],"visual":[89],"textual":[91],"fragments,":[92],"utilizing":[93],"Sinkhorn":[94],"iterations":[95],"for":[96],"efficient":[97],"approximation.":[98],"To":[99],"further":[100],"alleviate":[101],"issue":[103],"redundant":[105],"alignments,":[106],"seamlessly":[108],"integrate":[109],"partial":[110],"matching":[111],"into":[112],"OMIT,":[113],"leveraging":[114],"local-to-global":[115],"similarities":[116],"eliminate":[118],"interference":[120],"irrelevant":[122],"fragments.":[123],"We":[124],"conduct":[125],"extensive":[126],"evaluations":[127],"on":[130,146,172],"two":[131],"benchmark":[132],"retrieval":[134],"datasets,":[135],"namely":[136],"Flickr30K":[137],"MS-COCO.":[139],"The":[140],"superior":[141],"achieved":[143],"by":[144],"datasets":[148],"unequivocally":[149],"demonstrates":[150],"its":[151,173],"effectiveness":[152],"cross-modal":[154],"matching.":[155],"Furthermore,":[156],"through":[157],"comprehensive":[158],"visualization":[159],"analysis,":[160],"elucidate":[162],"OMIT's":[163],"inherent":[164],"tendency":[165],"towards":[166],"focal":[167],"thereby":[169],"shedding":[170],"light":[171],"efficacy.":[174],"Our":[175],"code":[176],"is":[177],"publicly":[178],"available":[179],"https://github.com/ppanzx/OMIT.":[181]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-18T00:00:00"}