{"id":"https://openalex.org/W7204195708","doi":"https://doi.org/10.3390/electronics15173804","title":"PWFAR: Patch\u2013Word Fine-Grained Alignment for Long-Text Image\u2013Text Retrieval","display_name":"PWFAR: Patch\u2013Word Fine-Grained Alignment for Long-Text Image\u2013Text Retrieval","publication_year":2026,"publication_date":"2026-08-25","ids":{"openalex":"https://openalex.org/W7204195708","doi":"https://doi.org/10.3390/electronics15173804"},"language":"en","primary_location":{"id":"doi:10.3390/electronics15173804","doi":"https://doi.org/10.3390/electronics15173804","is_oa":true,"landing_page_url":"https://doi.org/10.3390/electronics15173804","pdf_url":null,"source":{"id":"https://openalex.org/S4210202905","display_name":"Electronics","issn_l":"2079-9292","issn":["2079-9292"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Electronics","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3390/electronics15173804","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126256751","display_name":"Yong Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1334729051","display_name":"Xinjiang Normal University","ror":"https://ror.org/00ndrvk93","country_code":"CN","type":"education","lineage":["https://openalex.org/I1334729051"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Yang","raw_affiliation_strings":["College of Computer Science and Technology, Xinjiang Normal University, Urumqi 830054, China","Smart Education Engineering Technology Research Center of Xinjiang Normal University, Urumqi 830054, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Xinjiang Normal University, Urumqi 830054, China","institution_ids":["https://openalex.org/I1334729051"]},{"raw_affiliation_string":"Smart Education Engineering Technology Research Center of Xinjiang Normal University, Urumqi 830054, China","institution_ids":["https://openalex.org/I1334729051"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100781839","display_name":"Penghui Li","orcid":"https://orcid.org/0000-0001-7257-6381","observed_orcids":["https://orcid.org/0000-0001-7257-6381","https://orcid.org/0009-0002-6319-807X","https://orcid.org/0009-0008-6414-0818"]},"institutions":[{"id":"https://openalex.org/I1334729051","display_name":"Xinjiang Normal University","ror":"https://ror.org/00ndrvk93","country_code":"CN","type":"education","lineage":["https://openalex.org/I1334729051"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Penghui Li","raw_affiliation_strings":["College of Computer Science and Technology, Xinjiang Normal University, Urumqi 830054, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Xinjiang Normal University, Urumqi 830054, China","institution_ids":["https://openalex.org/I1334729051"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148174066","display_name":"Hulong He","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1334729051","display_name":"Xinjiang Normal University","ror":"https://ror.org/00ndrvk93","country_code":"CN","type":"education","lineage":["https://openalex.org/I1334729051"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hulong He","raw_affiliation_strings":["College of Computer Science and Technology, Xinjiang Normal University, Urumqi 830054, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Xinjiang Normal University, Urumqi 830054, China","institution_ids":["https://openalex.org/I1334729051"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5134600553","display_name":"Ge Ren","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1334729051","display_name":"Xinjiang Normal University","ror":"https://ror.org/00ndrvk93","country_code":"CN","type":"education","lineage":["https://openalex.org/I1334729051"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ge Ren","raw_affiliation_strings":["College of Computer Science and Technology, Xinjiang Normal University, Urumqi 830054, China","Smart Education Engineering Technology Research Center of Xinjiang Normal University, Urumqi 830054, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Xinjiang Normal University, Urumqi 830054, China","institution_ids":["https://openalex.org/I1334729051"]},{"raw_affiliation_string":"Smart Education Engineering Technology Research Center of Xinjiang Normal University, Urumqi 830054, China","institution_ids":["https://openalex.org/I1334729051"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1334729051"],"apc_list":{"value":2400,"currency":"CHF","value_usd":2896},"apc_paid":{"value":2400,"currency":"CHF","value_usd":2896},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.67546725,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"15","issue":"17","first_page":"3804","last_page":"3804"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9854000210762024,"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":0.9854000210762024,"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":0.010700000450015068,"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":0.0034000000450760126,"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/fine-grained-alignment","display_name":"fine-grained alignment","score":0.8029999732971191},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.859000027179718},{"id":"https://openalex.org/keywords/spatial-relationships","display_name":"spatial relations","score":0.5249999761581421}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8294000029563904},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.5968999862670898},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5949000120162964},{"id":"https://openalex.org/C2778493491","wikidata":"https://www.wikidata.org/wiki/Q7449072","display_name":"Semantic matching","level":3,"score":0.5468999743461609},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5264000296592712},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4803999960422516},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.4708000123500824},{"id":"https://openalex.org/C173862523","wikidata":"https://www.wikidata.org/wiki/Q5421270","display_name":"Explicit semantic analysis","level":5,"score":0.42800000309944153},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.3840000033378601},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3702000081539154},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.34310001134872437},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3370000123977661},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.3337000012397766},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3237999975681305},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3001999855041504},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2971999943256378},{"id":"https://openalex.org/C511149849","wikidata":"https://www.wikidata.org/wiki/Q7449051","display_name":"Semantic computing","level":3,"score":0.29649999737739563},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.2809999883174896},{"id":"https://openalex.org/C2986492983","wikidata":"https://www.wikidata.org/wiki/Q861092","display_name":"Image matching","level":3,"score":0.27140000462532043},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.27090001106262207}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3390/electronics15173804","doi":"https://doi.org/10.3390/electronics15173804","is_oa":true,"landing_page_url":"https://doi.org/10.3390/electronics15173804","pdf_url":null,"source":{"id":"https://openalex.org/S4210202905","display_name":"Electronics","issn_l":"2079-9292","issn":["2079-9292"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Electronics","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.3390/electronics15173804","doi":"https://doi.org/10.3390/electronics15173804","is_oa":true,"landing_page_url":"https://doi.org/10.3390/electronics15173804","pdf_url":null,"source":{"id":"https://openalex.org/S4210202905","display_name":"Electronics","issn_l":"2079-9292","issn":["2079-9292"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Electronics","raw_type":"journal-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.40654274821281433,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G4876773019","display_name":null,"funder_award_id":"62167008","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W2048430744","https://openalex.org/W2096733369","https://openalex.org/W2962964995","https://openalex.org/W2965848243","https://openalex.org/W2988823324","https://openalex.org/W2994818707","https://openalex.org/W3035454331","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3160179442","https://openalex.org/W3173220247","https://openalex.org/W4290043985","https://openalex.org/W4312761738","https://openalex.org/W4400528838","https://openalex.org/W4403841197","https://openalex.org/W4404575065","https://openalex.org/W4413145913"],"related_works":[],"abstract_inverted_index":{"The":[0,157],"main":[1],"challenge":[2],"in":[3,8,41,62,212,236],"long-text":[4,127,203,246],"image\u2013text":[5,247],"retrieval":[6,73,190,204,214],"lies":[7],"the":[9,56,79,82,103,111,162,166,172,201,220,228,241],"fact":[10],"that":[11,180,219],"some":[12],"existing":[13],"vision\u2013language":[14],"models":[15,32],"mainly":[16],"rely":[17],"on":[18,161,171,200],"global":[19,63,128],"image":[20,92,107],"and":[21,51,94,135,152,169,174,189,194,210],"text":[22,95],"features":[23],"for":[24,245],"matching.":[25],"Without":[26],"explicit":[27,87],"local":[28,47,60,106,116,153,233],"alignment":[29,72,89,223],"constraints,":[30],"these":[31],"may":[33],"struggle":[34],"to":[35,101,114,144,231],"fully":[36],"capture":[37,115,232],"complex":[38],"semantic":[39,64,117,133,147,150,234],"information":[40],"long":[42,237],"textual":[43,99],"descriptions,":[44],"such":[45],"as":[46],"objects,":[48],"fine-grained":[49,71,88,137,222],"attributes,":[50],"spatial":[52],"relationships.":[53,156],"To":[54],"address":[55],"insufficient":[57],"modeling":[58],"of":[59,105,122,165,243],"details":[61],"matching,":[65],"this":[66],"paper":[67],"proposes":[68],"a":[69],"patch\u2013word":[70,136],"model,":[74],"named":[75],"PWFAR.":[76],"Built":[77],"upon":[78],"Long-CLIP":[80,209],"framework,":[81],"proposed":[83,221],"method":[84],"introduces":[85],"an":[86],"mechanism":[90,224],"between":[91],"patches":[93],"tokens.":[96],"By":[97],"using":[98],"words":[100],"guide":[102],"matching":[104,155],"regions,":[108],"PWFAR":[109,120,181,244],"enhances":[110],"model\u2019s":[112,229],"ability":[113,230],"correspondences.":[118],"Specifically,":[119],"consists":[121],"three":[123],"complementary":[124],"training":[125],"objectives:":[126],"contrastive":[129],"learning,":[130],"short-text":[131],"compact":[132],"supervision,":[134],"alignment.":[138],"These":[139,216],"objectives":[140],"are":[141,198],"jointly":[142],"optimized":[143],"constrain":[145],"overall":[146],"consistency,":[148],"core":[149],"stability,":[151],"detail":[154],"model":[158],"is":[159],"trained":[160],"888k":[163],"subset":[164],"ShareGPT4V":[167],"dataset":[168],"evaluated":[170],"COCO2017":[173],"Urban1k":[175,202],"datasets.":[176],"Experimental":[177],"results":[178,217],"show":[179],"achieves":[182],"competitive":[183],"performance":[184],"across":[185],"different":[186],"backbone":[187],"networks":[188],"directions.":[191,215],"Its":[192],"clearest":[193],"most":[195],"consistent":[196],"gains":[197],"observed":[199],"task,":[205],"where":[206],"it":[207],"outperforms":[208],"Long-CLIP-888k":[211],"both":[213],"indicate":[218],"can":[225],"effectively":[226],"improve":[227],"relationships":[235],"texts,":[238],"thereby":[239],"verifying":[240],"effectiveness":[242],"retrieval.":[248]},"counts_by_year":[],"updated_date":"2026-09-24T07:57:37.273135","created_date":"2026-08-26T00:00:00"}