{"id":"https://openalex.org/W7164815348","doi":"https://doi.org/10.1145/3805622.3810819","title":"Unsupervised Cross-Modal Semantic Invariance Hashing","display_name":"Unsupervised Cross-Modal Semantic Invariance Hashing","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164815348","doi":"https://doi.org/10.1145/3805622.3810819"},"language":null,"primary_location":{"id":"doi:10.1145/3805622.3810819","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810819","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/10.1145/3805622.3810819","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138666087","display_name":"Qiyou Huang","orcid":"https://orcid.org/0009-0008-7976-7218"},"institutions":[{"id":"https://openalex.org/I18570673","display_name":"Guangxi University of Science and Technology","ror":"https://ror.org/02fj6b627","country_code":"CN","type":"education","lineage":["https://openalex.org/I18570673"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiyou Huang","raw_affiliation_strings":["Guangxi University of Science and Technology, Liuzhou, Guangxi, China"],"raw_orcid":"https://orcid.org/0009-0008-7976-7218","affiliations":[{"raw_affiliation_string":"Guangxi University of Science and Technology, Liuzhou, Guangxi, China","institution_ids":["https://openalex.org/I18570673"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5138668189","display_name":"Meng Wang","orcid":"https://orcid.org/0009-0002-4725-8669"},"institutions":[{"id":"https://openalex.org/I18570673","display_name":"Guangxi University of Science and Technology","ror":"https://ror.org/02fj6b627","country_code":"CN","type":"education","lineage":["https://openalex.org/I18570673"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Wang","raw_affiliation_strings":["Guangxi University of Science and Technology, Liuzhou, Guangxi, China"],"raw_orcid":"https://orcid.org/0009-0002-4725-8669","affiliations":[{"raw_affiliation_string":"Guangxi University of Science and Technology, Liuzhou, Guangxi, China","institution_ids":["https://openalex.org/I18570673"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.93476081,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"157","last_page":"166"},"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":0.9520999789237976,"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":0.9520999789237976,"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":0.007499999832361937,"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":0.00570000009611249,"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":0.6658999919891357},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5809999704360962},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.5422000288963318},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.48989999294281006},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4702000021934509},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4650000035762787},{"id":"https://openalex.org/keywords/locality-sensitive-hashing","display_name":"Locality-sensitive hashing","score":0.4505000114440918},{"id":"https://openalex.org/keywords/binary-code","display_name":"Binary code","score":0.40450000762939453}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7050999999046326},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.6658999919891357},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6158000230789185},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5809999704360962},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.5422000288963318},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.48989999294281006},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4702000021934509},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4650000035762787},{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.4505000114440918},{"id":"https://openalex.org/C63435697","wikidata":"https://www.wikidata.org/wiki/Q864135","display_name":"Binary code","level":3,"score":0.40450000762939453},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.4034999907016754},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.37549999356269836},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.37470000982284546},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.3499999940395355},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.325300008058548},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.31299999356269836},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2994000017642975},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.29809999465942383},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.295199990272522},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.28540000319480896},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27559998631477356},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2612000107765198},{"id":"https://openalex.org/C105611402","wikidata":"https://www.wikidata.org/wiki/Q2976589","display_name":"Spectral clustering","level":3,"score":0.25870001316070557},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.25859999656677246},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805622.3810819","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810819","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:10.1145/3805622.3810819","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810819","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":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7137833833694458}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W320879671","https://openalex.org/W1922199343","https://openalex.org/W1976258951","https://openalex.org/W2007972815","https://openalex.org/W2049993534","https://openalex.org/W2086958058","https://openalex.org/W2150593711","https://openalex.org/W2155803963","https://openalex.org/W2266728343","https://openalex.org/W2345649690","https://openalex.org/W2733636222","https://openalex.org/W2748725735","https://openalex.org/W2953106684","https://openalex.org/W2963187862","https://openalex.org/W2982905682","https://openalex.org/W3008072721","https://openalex.org/W3033587904","https://openalex.org/W3033799362","https://openalex.org/W3034890701","https://openalex.org/W3035552787","https://openalex.org/W3035747010","https://openalex.org/W3122091215","https://openalex.org/W3166396011","https://openalex.org/W3175740157","https://openalex.org/W3183864931","https://openalex.org/W3187176672","https://openalex.org/W3192393047","https://openalex.org/W4200632612","https://openalex.org/W4225700096","https://openalex.org/W4304014355","https://openalex.org/W4304092731","https://openalex.org/W4312477797","https://openalex.org/W4312749754","https://openalex.org/W4321021417","https://openalex.org/W4385614537","https://openalex.org/W4387129530","https://openalex.org/W4390061801","https://openalex.org/W4393034333","https://openalex.org/W4395029038","https://openalex.org/W4402351477","https://openalex.org/W4402979747","https://openalex.org/W4406387563","https://openalex.org/W4407355684","https://openalex.org/W4409366012","https://openalex.org/W4409369987","https://openalex.org/W4412586073"],"related_works":[],"abstract_inverted_index":{"Cross-modal":[0],"hashing":[1,30,183],"retrieval":[2],"aims":[3],"to":[4,56,110,136,150],"learn":[5],"compact":[6],"binary":[7],"representations":[8,155],"for":[9],"data":[10],"from":[11,48],"different":[12],"modalities,":[13],"enabling":[14],"efficient":[15],"cross-modal":[16,29,119,182],"similarity":[17,37,43,120],"retrieval,":[18],"and":[19,58,143,174,177],"has":[20],"attracted":[21],"increasing":[22],"attention":[23],"in":[24,62,98,139],"recent":[25],"years.":[26],"Existing":[27],"unsupervised":[28,181],"methods":[31],"usually":[32],"rely":[33],"on":[34,94,152,161],"automatically":[35],"constructed":[36],"matrices":[38,44],"as":[39],"supervisory":[40],"signals.":[41],"These":[42],"are":[45,108],"often":[46],"derived":[47],"shallow":[49],"statistical":[50],"co-occurrence":[51],"patterns,":[52],"making":[53],"them":[54],"susceptible":[55],"noise":[57],"spurious":[59],"correlations,":[60],"which":[61,132],"turn":[63],"weaken":[64],"the":[65,69,140,148],"semantic":[66,96,113,154],"discriminability":[67],"of":[68,172],"learned":[70],"hash":[71],"codes.":[72],"To":[73],"address":[74],"this":[75],"problem,":[76],"we":[77],"propose":[78],"Unsupervised":[79],"Cross-Modal":[80],"Semantic":[81,127],"Invariance":[82,128],"Hashing":[83],"(USIH).":[84],"USIH":[85,124,168],"first":[86],"designs":[87],"an":[88],"Object-aware":[89],"Attention":[90],"Mechanism":[91],"that":[92,167],"focuses":[93],"key":[95],"objects":[97],"images":[99],"while":[100],"suppressing":[101],"background":[102],"interference.":[103],"Subsequently,":[104],"object":[105],"clustering":[106],"results":[107,160],"leveraged":[109],"guide":[111],"textual":[112],"modeling,":[114],"thereby":[115],"obtaining":[116],"more":[117],"reliable":[118],"matrices.":[121],"In":[122],"addition,":[123],"introduces":[125],"a":[126],"Enhancement":[129],"(SIE)":[130],"module,":[131],"applies":[133],"controlled":[134],"perturbations":[135],"multimodal":[137],"features":[138],"frequency":[141],"domain":[142],"enforces":[144],"consistency":[145],"constraints,":[146],"guiding":[147],"model":[149],"focus":[151],"deep":[153],"shared":[156],"across":[157],"modalities.":[158],"Experimental":[159],"two":[162],"public":[163],"benchmark":[164],"datasets":[165],"demonstrate":[166],"achieves":[169],"mAP":[170],"scores":[171],"78%":[173],"68%,":[175],"respectively,":[176],"consistently":[178],"outperforms":[179],"representative":[180],"methods.":[184]},"counts_by_year":[],"updated_date":"2026-06-16T07:37:23.134862","created_date":"2026-06-16T00:00:00"}