{"id":"https://openalex.org/W7138139487","doi":"https://doi.org/10.1609/aaai.v40i15.38247","title":"Proxy Zero-Shot Hashing with Multimodal Fusion via Stable Diffusion","display_name":"Proxy Zero-Shot Hashing with Multimodal Fusion via Stable Diffusion","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138139487","doi":"https://doi.org/10.1609/aaai.v40i15.38247"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i15.38247","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i15.38247","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i15.38247","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129751037","display_name":"Hui Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Zhang","raw_affiliation_strings":["Ocean University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ocean University of China","institution_ids":["https://openalex.org/I59028903"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104298776","display_name":"W. K. Gao","orcid":"https://orcid.org/0009-0009-0444-2010"},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weikang Gao","raw_affiliation_strings":["Ocean University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ocean University of China","institution_ids":["https://openalex.org/I59028903"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129648451","display_name":"Tao Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Yang","raw_affiliation_strings":["Ocean University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ocean University of China","institution_ids":["https://openalex.org/I59028903"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129667311","display_name":"Yuan Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Cao","raw_affiliation_strings":["Ocean University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ocean University of China","institution_ids":["https://openalex.org/I59028903"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I59028903"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38034188,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"15","first_page":"12529","last_page":"12537"},"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":0.9082000255584717,"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":0.9082000255584717,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.00860000029206276,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.007000000216066837,"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/hash-function","display_name":"Hash function","score":0.7486000061035156},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6554999947547913},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5641000270843506},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5611000061035156},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5475999712944031},{"id":"https://openalex.org/keywords/feature-hashing","display_name":"Feature hashing","score":0.541700005531311},{"id":"https://openalex.org/keywords/locality-sensitive-hashing","display_name":"Locality-sensitive hashing","score":0.41019999980926514},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.38839998841285706},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.3840999901294708},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.373199999332428}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7760999798774719},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.7486000061035156},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6554999947547913},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.652999997138977},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5641000270843506},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5611000061035156},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5475999712944031},{"id":"https://openalex.org/C133667856","wikidata":"https://www.wikidata.org/wiki/Q5439682","display_name":"Feature hashing","level":5,"score":0.541700005531311},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4325999915599823},{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.41019999980926514},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.38839998841285706},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.3840999901294708},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.373199999332428},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37119999527931213},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.3700999915599823},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.3668999969959259},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.36399999260902405},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3628999888896942},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.34610000252723694},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.3431999981403351},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3418999910354614},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.3292999863624573},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.3231000006198883},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.3084999918937683},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.3084000051021576},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.2935999929904938},{"id":"https://openalex.org/C145741570","wikidata":"https://www.wikidata.org/wiki/Q7251534","display_name":"Proteogenomics","level":5,"score":0.29319998621940613},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2921999990940094},{"id":"https://openalex.org/C173414695","wikidata":"https://www.wikidata.org/wiki/Q5510276","display_name":"Fusion mechanism","level":4,"score":0.2791999876499176},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.26579999923706055},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2596000134944916},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2596000134944916}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i15.38247","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i15.38247","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/38247","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/38247","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i15.38247","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i15.38247","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7561699748039246,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,19,56,78,104],"rapid":[2],"growth":[3],"of":[4,21,38,106],"visual":[5,45],"content":[6],"in":[7,60],"open-world":[8],"environments,":[9],"zero-shot":[10],"hashing":[11,107,164],"image":[12],"retrieval":[13],"(ZSHIR)":[14],"has":[15],"emerged":[16],"to":[17,54,81,144,153,166,185],"tackle":[18],"challenge":[20],"recognizing":[22],"novel":[23,116],"classes":[24,98],"using":[25],"attribute-level":[26],"and":[27,44,74,96,103,133,148],"semantic":[28,58,89,155],"information.":[29],"However,":[30],"existing":[31],"methods":[32],"often":[33],"rely":[34],"on":[35,173],"shallow":[36],"fusion":[37],"multi-source":[39],"cues":[40],"(e.g.,":[41],"attributes,":[42],"labels,":[43],"features)":[46],"through":[47],"external":[48],"supervision":[49],"or":[50,91],"feature":[51],"concatenation,":[52],"failing":[53],"capture":[55],"underlying":[57],"structure":[59],"a":[61,115,138,162],"generative":[62,131],"way.":[63],"Particularly,":[64],"current":[65],"bridging":[66],"strategies":[67],"between":[68,94],"modalities":[69],"suffer":[70],"from":[71],"information":[72],"fragmentation":[73],"weak":[75],"alignment,":[76],"hindering":[77],"model's":[79],"ability":[80],"fully":[82],"understand":[83],"complex":[84],"attribute-visual":[85],"relations.":[86],"Moreover,":[87],"subtle":[88],"gaps":[90],"\u201csemantic":[92],"drift\u201d":[93],"seen":[95],"unseen":[97,186],"further":[99,160],"degrade":[100],"inter-class":[101],"separability":[102],"scalability":[105],"models.":[108],"To":[109],"address":[110],"these":[111],"issues,":[112],"we":[113],"propose":[114],"framework":[117],"called":[118],"Proxy":[119],"Zero-Shot":[120],"Hashing":[121],"with":[122,182],"Multimodal":[123],"Fusion":[124],"via":[125],"Stable":[126,140],"Diffusion":[127,141],"(PZSH),":[128],"which":[129],"integrates":[130],"modeling":[132],"contrastive":[134],"learning.":[135],"PZSH":[136,178],"leverages":[137],"pre-trained":[139],"(SD)":[142],"model":[143],"synthesize":[145],"multimodal":[146],"content,":[147],"uses":[149],"dual":[150],"BLIP":[151],"encoders":[152],"enhance":[154],"alignment":[156],"across":[157],"modalities.":[158],"We":[159],"design":[161],"proxy":[163],"loss":[165],"enforce":[167],"discriminative":[168],"binary":[169],"representations.":[170],"Extensive":[171],"experiments":[172],"benchmark":[174],"datasets":[175],"show":[176],"that":[177],"achieves":[179],"state-of-the-art":[180],"performance":[181],"stronger":[183],"generalization":[184],"classes.":[187]},"counts_by_year":[],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2026-03-18T00:00:00"}