{"id":"https://openalex.org/W7164850708","doi":"https://doi.org/10.1145/3805622.3810663","title":"Global-Regional Dual Hashing for Unsupervised Visual-Textual Retrieval via Concept Similarity Guidance","display_name":"Global-Regional Dual Hashing for Unsupervised Visual-Textual Retrieval via Concept Similarity Guidance","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164850708","doi":"https://doi.org/10.1145/3805622.3810663"},"language":null,"primary_location":{"id":"doi:10.1145/3805622.3810663","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810663","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805622.3810663","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063575625","display_name":"Yewen Li","orcid":"https://orcid.org/0000-0001-8406-0606"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yewen Li","raw_affiliation_strings":["College of Computer Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0001-8406-0606","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138681089","display_name":"Zongwei Tang","orcid":"https://orcid.org/0009-0009-5128-5070"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zongwei Tang","raw_affiliation_strings":["College of Computer Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0009-0009-5128-5070","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5115695468","display_name":"Xiaodong Wang","orcid":"https://orcid.org/0000-0001-8949-5967"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaodong Wang","raw_affiliation_strings":["College of Computer Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0001-8949-5967","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.93897895,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"347","last_page":"355"},"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":0.9653000235557556,"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":0.9653000235557556,"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":0.004399999976158142,"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":0.0027000000700354576,"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/hash-function","display_name":"Hash function","score":0.6995000243186951},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.5063999891281128},{"id":"https://openalex.org/keywords/locality-sensitive-hashing","display_name":"Locality-sensitive hashing","score":0.46320000290870667},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.46000000834465027},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.439300000667572},{"id":"https://openalex.org/keywords/dynamic-perfect-hashing","display_name":"Dynamic perfect hashing","score":0.41429999470710754},{"id":"https://openalex.org/keywords/feature-hashing","display_name":"Feature hashing","score":0.3806000053882599},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.3801000118255615},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.37040001153945923},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36419999599456787}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7156999707221985},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.6995000243186951},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.5063999891281128},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4772000014781952},{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.46320000290870667},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.46000000834465027},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.45489999651908875},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.439300000667572},{"id":"https://openalex.org/C122907437","wikidata":"https://www.wikidata.org/wiki/Q5318999","display_name":"Dynamic perfect hashing","level":5,"score":0.41429999470710754},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.38929998874664307},{"id":"https://openalex.org/C133667856","wikidata":"https://www.wikidata.org/wiki/Q5439682","display_name":"Feature hashing","level":5,"score":0.3806000053882599},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.3801000118255615},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.37040001153945923},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36419999599456787},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.359499990940094},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.35569998621940613},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.35030001401901245},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.33059999346733093},{"id":"https://openalex.org/C193319292","wikidata":"https://www.wikidata.org/wiki/Q272172","display_name":"Hamming distance","level":2,"score":0.32679998874664307},{"id":"https://openalex.org/C116058348","wikidata":"https://www.wikidata.org/wiki/Q846912","display_name":"Universal hashing","level":5,"score":0.3224000036716461},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3027999997138977},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.2948000133037567},{"id":"https://openalex.org/C138111711","wikidata":"https://www.wikidata.org/wiki/Q478351","display_name":"Double hashing","level":4,"score":0.2944999933242798},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.29249998927116394},{"id":"https://openalex.org/C36375716","wikidata":"https://www.wikidata.org/wiki/Q6553456","display_name":"Linear hashing","level":5,"score":0.2892000079154968},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C87431388","wikidata":"https://www.wikidata.org/wiki/Q2070573","display_name":"Perfect hash function","level":4,"score":0.26820001006126404},{"id":"https://openalex.org/C2776517306","wikidata":"https://www.wikidata.org/wiki/Q29017317","display_name":"Similarity measure","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2655999958515167},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C197947376","wikidata":"https://www.wikidata.org/wiki/Q5155608","display_name":"Comparability","level":2,"score":0.25189998745918274},{"id":"https://openalex.org/C2779494224","wikidata":"https://www.wikidata.org/wiki/Q5645799","display_name":"Hamming space","level":5,"score":0.2517000138759613},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805622.3810663","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810663","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805622.3810663","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810663","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6881269812583923}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W2007972815","https://openalex.org/W2155803963","https://openalex.org/W2266728343","https://openalex.org/W2982905682","https://openalex.org/W3033587904","https://openalex.org/W3034890701","https://openalex.org/W3035747010","https://openalex.org/W3122091215","https://openalex.org/W3175740157","https://openalex.org/W3198377975","https://openalex.org/W4206706211","https://openalex.org/W4224324956","https://openalex.org/W4284687590","https://openalex.org/W4285288078","https://openalex.org/W4304092731","https://openalex.org/W4306317671","https://openalex.org/W4312310776","https://openalex.org/W4312477797","https://openalex.org/W4379806204","https://openalex.org/W4380303571","https://openalex.org/W4390872633","https://openalex.org/W4390873312","https://openalex.org/W4392203450","https://openalex.org/W4400579109","https://openalex.org/W4403707460","https://openalex.org/W4403780544","https://openalex.org/W4403792396","https://openalex.org/W4404735265","https://openalex.org/W4405740219","https://openalex.org/W4405741836","https://openalex.org/W4409256215","https://openalex.org/W4409369987","https://openalex.org/W7133187299"],"related_works":[],"abstract_inverted_index":{"Visual-textual":[0],"cross-modal":[1,162,172],"hashing":[2,153,164],"is":[3,99],"an":[4],"efficient":[5],"method":[6],"for":[7,55,111],"large-scale":[8],"multi-source":[9],"heterogeneous":[10],"data":[11],"retrieval.":[12],"However,":[13],"existing":[14],"unsupervised":[15,56,194],"methods":[16],"predominantly":[17],"learn":[18],"coarse-grained":[19],"representations":[20,71],"and":[21,36,68,137,145,184],"establish":[22],"global":[23],"matching":[24],"relationships,":[25],"neglecting":[26],"fine-grained":[27],"alignment.":[28],"Furthermore,":[29],"image-text":[30,66],"pairs":[31,67],"exhibit":[32],"partial":[33],"semantic":[34,63,131,168],"gaps":[35],"noise,":[37],"leading":[38],"to":[39,60,87,101],"inaccurate":[40],"similarity":[41,79],"measurements.":[42],"To":[43],"tackle":[44],"these":[45],"issues,":[46],"this":[47],"paper":[48],"proposes":[49],"a":[50,73],"Global-Regional":[51],"Dual":[52],"Hashing":[53],"(GRDH)":[54],"visual-textual":[57,85],"retrieval,":[58],"aiming":[59],"bridge":[61],"the":[62,84,122,129,150,197],"ambiguity":[64],"between":[65],"align":[69],"multi-granularity":[70],"within":[72],"unified":[74],"transformer-based":[75],"framework":[76],"through":[77],"concept":[78],"guidance.":[80],"Specifically,":[81],"we":[82,127],"design":[83],"transformers":[86],"extract":[88],"global-region":[89,112],"tokens":[90],"from":[91],"multimodal":[92],"data.":[93],"The":[94],"region":[95,105,117],"token":[96],"refinement":[97],"module":[98,154],"designed":[100],"eliminate":[102],"semantically":[103],"ambiguous":[104],"tokens,":[106],"effectively":[107],"reducing":[108],"computational":[109],"overhead":[110],"interactions":[113],"while":[114],"promoting":[115],"attention-based":[116],"information":[118],"coordination.":[119],"Secondly,":[120],"under":[121],"guidance":[123],"of":[124,158,171,199],"concept-enhanced":[125],"similarity,":[126],"constructed":[128],"global-regional":[130,151,159],"alignment":[132,139],"loss":[133],"that":[134,187],"enables":[135],"token-level":[136],"hash-level":[138],"in":[140],"both":[141],"continuous":[142],"Euclidean":[143],"space":[144],"discrete":[146],"Hamming":[147],"space.":[148],"Finally,":[149],"dual":[152],"generates":[155],"hash":[156,173],"codes":[157],"branches.":[160],"Through":[161],"consistent":[163],"learning,":[165],"it":[166],"maintains":[167],"distribution":[169],"consistency":[170],"codes.":[174],"Extensive":[175],"experiments":[176],"conducted":[177],"on":[178],"two":[179],"baseline":[180],"datasets":[181],"(i.e.,":[182],"MIRFLICKR-25K":[183],"NUS-WIDE)":[185],"demonstrate":[186],"our":[188,200],"GRDH":[189],"model":[190],"outperforms":[191],"recent":[192],"state-of-the-art":[193],"methods,":[195],"validating":[196],"effectiveness":[198],"approach.":[201]},"counts_by_year":[],"updated_date":"2026-06-16T07:37:23.134862","created_date":"2026-06-16T00:00:00"}