{"id":"https://openalex.org/W7133122658","doi":"https://doi.org/10.1016/j.patcog.2026.113393","title":"Feature space sharing via visual projector for open-vocabulary multi-label classification","display_name":"Feature space sharing via visual projector for open-vocabulary multi-label classification","publication_year":2026,"publication_date":"2026-03-01","ids":{"openalex":"https://openalex.org/W7133122658","doi":"https://doi.org/10.1016/j.patcog.2026.113393"},"language":"en","primary_location":{"id":"doi:10.1016/j.patcog.2026.113393","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.patcog.2026.113393","pdf_url":null,"source":{"id":"https://openalex.org/S414566","display_name":"Pattern Recognition","issn_l":"0031-3203","issn":["0031-3203","1873-5142"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Pattern Recognition","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.patcog.2026.113393","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5127770930","display_name":"Zhanfang Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I95946905","display_name":"Hebei GEO University","ror":"https://ror.org/013x4kb81","country_code":"CN","type":"education","lineage":["https://openalex.org/I95946905"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhanfang Zhao","raw_affiliation_strings":["School of Information Engineering, Hebei GEO University, Shijiazhuang 050031, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Engineering, Hebei GEO University, Shijiazhuang 050031, China","institution_ids":["https://openalex.org/I95946905"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5127773218","display_name":"Xiaohan Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I95946905","display_name":"Hebei GEO University","ror":"https://ror.org/013x4kb81","country_code":"CN","type":"education","lineage":["https://openalex.org/I95946905"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaohan Yang","raw_affiliation_strings":["School of Information Engineering, Hebei GEO University, Shijiazhuang 050031, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Engineering, Hebei GEO University, Shijiazhuang 050031, China","institution_ids":["https://openalex.org/I95946905"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5127773218"],"corresponding_institution_ids":["https://openalex.org/I95946905"],"apc_list":{"value":2850,"currency":"USD","value_usd":2850},"apc_paid":{"value":2850,"currency":"USD","value_usd":2850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24081906,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"178","issue":null,"first_page":"113393","last_page":"113393"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.5196999907493591,"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"}},"topics":[{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.5196999907493591,"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"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.06689999997615814,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.03530000150203705,"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/security-token","display_name":"Security token","score":0.5934000015258789},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5914999842643738},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5375000238418579},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5177000164985657},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4722999930381775},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4458000063896179},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4235999882221222},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.39739999175071716},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.37540000677108765}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8439000248908997},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6759999990463257},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5934000015258789},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5914999842643738},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5375000238418579},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5177000164985657},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4722999930381775},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4458000063896179},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4235999882221222},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.40220001339912415},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.39739999175071716},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.37540000677108765},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.3571999967098236},{"id":"https://openalex.org/C2777311342","wikidata":"https://www.wikidata.org/wiki/Q578801","display_name":"Shared space","level":3,"score":0.3562000095844269},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.35019999742507935},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.3375999927520752},{"id":"https://openalex.org/C207363949","wikidata":"https://www.wikidata.org/wiki/Q462915","display_name":"Visual space","level":3,"score":0.3221000134944916},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.31610000133514404},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.31459999084472656},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.30869999527931213},{"id":"https://openalex.org/C2776035091","wikidata":"https://www.wikidata.org/wiki/Q7928819","display_name":"Viewpoints","level":2,"score":0.30090001225471497},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3000999987125397},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2985000014305115},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.28940001130104065},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28700000047683716},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.27160000801086426},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.2551000118255615}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.patcog.2026.113393","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.patcog.2026.113393","pdf_url":null,"source":{"id":"https://openalex.org/S414566","display_name":"Pattern Recognition","issn_l":"0031-3203","issn":["0031-3203","1873-5142"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Pattern Recognition","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.patcog.2026.113393","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.patcog.2026.113393","pdf_url":null,"source":{"id":"https://openalex.org/S414566","display_name":"Pattern Recognition","issn_l":"0031-3203","issn":["0031-3203","1873-5142"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Pattern Recognition","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1948489639","https://openalex.org/W2114315281","https://openalex.org/W2171061940","https://openalex.org/W2954721224","https://openalex.org/W2963499153","https://openalex.org/W3124902415","https://openalex.org/W3198377975","https://openalex.org/W4225832925","https://openalex.org/W4399490424","https://openalex.org/W4405833922","https://openalex.org/W4413325615"],"related_works":[],"abstract_inverted_index":{"\u2022":[0,10,21,33],"New":[1],"VPFSS":[2,209],"model":[3],"simplifies":[4],"training":[5,81,184],"and":[6,44,154,175,196,202,233],"avoids":[7],"complex":[8],"distillation":[9],"Local":[11],"token":[12,143,170],"extraction":[13,144,171],"helps":[14],"capture":[15],"fine":[16],"image":[17,49],"details":[18],"for":[19,66,107,130,236],"labels":[20,25,38,77,164],"Shared":[22],"features":[23,36,103],"let":[24],"reuse":[26],"cues,":[27],"improving":[28],"recognition":[29],"of":[30,138,222],"new":[31],"classes":[32],"Shares":[34],"visual":[35,102,142,149,189],"across":[37,191],"to":[39,74,98,163],"boost":[40],"performance":[41],"on":[42,87,194],"rare":[43,58],"unseen":[45,61,76],"categories":[46],"In":[47,110],"real-world":[48],"understanding,":[50],"images":[51],"often":[52,96],"contain":[53],"multiple":[54],"semantic":[55],"concepts,":[56],"including":[57],"or":[59],"previously":[60],"categories,":[62],"posing":[63],"significant":[64],"challenges":[65],"multi-label":[67,108,132,238],"classification.":[68,133],"Multi-Label":[69],"Zero-Shot":[70,200,204],"Learning":[71],"(ML-ZSL)":[72],"aims":[73],"recognize":[75],"without":[78],"requiring":[79],"annotated":[80],"data.":[82],"While":[83],"recent":[84],"approaches":[85],"based":[86],"Vision-Language":[88],"Pre-training":[89],"(VLP)":[90],"models":[91,129],"have":[92],"shown":[93],"promise,":[94],"they":[95],"struggle":[97],"preserve":[99],"fine-grained":[100],"local":[101],"that":[104,125,146,160,208,219],"are":[105],"critical":[106],"recognition.":[109,239],"this":[111],"work,":[112],"we":[113],"present":[114],"Visual":[115],"Projector":[116],"with":[117,226],"Feature":[118],"Space":[119],"Sharing":[120],"(VPFSS),":[121],"a":[122,141,155,182,231],"lightweight":[123],"framework":[124,180],"adapts":[126],"frozen":[127],"VLP":[128],"open-vocabulary":[131,237],"The":[134,216],"proposed":[135],"method":[136],"consists":[137],"two":[139],"components:":[140],"module":[145],"derives":[147],"localized":[148,223],"tokens":[150,162,224],"from":[151,172],"spatial":[152],"features,":[153],"feature":[156,228],"space":[157],"sharing":[158,229],"mechanism":[159],"assigns":[161],"through":[165],"similarity":[166],"maximization.":[167],"By":[168],"decoupling":[169],"label":[173],"matching":[174],"avoiding":[176],"knowledge":[177],"distillation,":[178],"the":[179],"maintains":[181],"simple":[183],"pipeline":[185],"while":[186],"enabling":[187],"reusable":[188],"representations":[190],"labels.":[192],"Experiments":[193],"NUS-WIDE":[195],"MS-COCO":[197],"under":[198],"both":[199],"Learning(ZSL)":[201],"Generalized":[203],"Learning(GZSL)":[205],"settings":[206],"demonstrate":[207],"achieves":[210],"consistent":[211],"improvements":[212],"over":[213],"representative":[214],"baselines.":[215],"results":[217],"indicate":[218],"explicit":[220],"modeling":[221],"combined":[225],"cross-label":[227],"provides":[230],"practical":[232],"effective":[234],"solution":[235]},"counts_by_year":[],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2026-03-02T00:00:00"}