{"id":"https://openalex.org/W7125953078","doi":"https://doi.org/10.1109/smc58881.2025.11343235","title":"QCSH: Quantization Controlled Semantic Hashing for Effective Similar Text Search","display_name":"QCSH: Quantization Controlled Semantic Hashing for Effective Similar Text Search","publication_year":2025,"publication_date":"2025-10-05","ids":{"openalex":"https://openalex.org/W7125953078","doi":"https://doi.org/10.1109/smc58881.2025.11343235"},"language":null,"primary_location":{"id":"doi:10.1109/smc58881.2025.11343235","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343235","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001112243","display_name":"Zihan Ye","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zihan Ye","raw_affiliation_strings":["Sun Yat-sen University,School of Computer Science and Engineering,Guangzhou,China"],"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University,School of Computer Science and Engineering,Guangzhou,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112198633","display_name":"Z. HOU","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhitian Hou","raw_affiliation_strings":["Sun Yat-sen University,School of Computer Science and Engineering,Guangzhou,China"],"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University,School of Computer Science and Engineering,Guangzhou,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103988236","display_name":"Ge Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ge Lin","raw_affiliation_strings":["Sun Yat-Sen University,National Engineering Research Center of Digital Life,Guangzhou,China"],"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University,National Engineering Research Center of Digital Life,Guangzhou,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024320209","display_name":"Kun Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Zeng","raw_affiliation_strings":["Sun Yat-sen University,School of Computer Science and Engineering,Guangzhou,China"],"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University,School of Computer Science and Engineering,Guangzhou,China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5001112243"],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.68759204,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2715","last_page":"2720"},"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":0.8698999881744385,"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":0.8698999881744385,"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":0.012799999676644802,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.011099999770522118,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.67330002784729},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.6687999963760376},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4781000018119812},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.47269999980926514},{"id":"https://openalex.org/keywords/binary-code","display_name":"Binary code","score":0.45329999923706055},{"id":"https://openalex.org/keywords/locality-sensitive-hashing","display_name":"Locality-sensitive hashing","score":0.44119998812675476},{"id":"https://openalex.org/keywords/dynamic-perfect-hashing","display_name":"Dynamic perfect hashing","score":0.40689998865127563},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.3896999955177307}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7387999892234802},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.67330002784729},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.6687999963760376},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5159000158309937},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4781000018119812},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.47269999980926514},{"id":"https://openalex.org/C63435697","wikidata":"https://www.wikidata.org/wiki/Q864135","display_name":"Binary code","level":3,"score":0.45329999923706055},{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.44119998812675476},{"id":"https://openalex.org/C122907437","wikidata":"https://www.wikidata.org/wiki/Q5318999","display_name":"Dynamic perfect hashing","level":5,"score":0.40689998865127563},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3953000009059906},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.3896999955177307},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.38940000534057617},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.37310001254081726},{"id":"https://openalex.org/C133667856","wikidata":"https://www.wikidata.org/wiki/Q5439682","display_name":"Feature hashing","level":5,"score":0.364300012588501},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36070001125335693},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.359499990940094},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.3544999957084656},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.34869998693466187},{"id":"https://openalex.org/C116058348","wikidata":"https://www.wikidata.org/wiki/Q846912","display_name":"Universal hashing","level":5,"score":0.34540000557899475},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.30889999866485596},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.30160000920295715},{"id":"https://openalex.org/C36375716","wikidata":"https://www.wikidata.org/wiki/Q6553456","display_name":"Linear hashing","level":5,"score":0.2849000096321106},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2694000005722046},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26100000739097595},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25440001487731934}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc58881.2025.11343235","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343235","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1994389483","https://openalex.org/W2053017876","https://openalex.org/W2085922539","https://openalex.org/W2147069236","https://openalex.org/W2147152072","https://openalex.org/W2162006472","https://openalex.org/W2411707397","https://openalex.org/W2740797857","https://openalex.org/W2798666412","https://openalex.org/W2913932916","https://openalex.org/W2962919781","https://openalex.org/W2963213486","https://openalex.org/W2963605131","https://openalex.org/W2985730480","https://openalex.org/W3012800455","https://openalex.org/W3035640753","https://openalex.org/W3189475579","https://openalex.org/W3198459119","https://openalex.org/W4210350273","https://openalex.org/W4318477599","https://openalex.org/W4399418686"],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,89,103],"rapid":[2],"growth":[3],"of":[4,105,162,164],"digital":[5],"information,":[6,136],"efficient":[7],"similarity":[8],"search":[9],"has":[10,43],"become":[11],"a":[12,143],"crucial":[13],"challenge":[14],"in":[15],"large-scale":[16],"information":[17,131],"retrieval.":[18],"Semantic":[19,80],"hashing":[20,42,76,99],"provides":[21],"an":[22,71,125],"effective":[23,106],"solution":[24],"by":[25,109],"encoding":[26],"high-dimensional":[27],"data":[28],"into":[29],"compact":[30],"binary":[31],"representations,":[32],"thereby":[33],"significantly":[34],"improving":[35],"retrieval":[36],"efficiency.":[37],"While":[38],"deep":[39],"learning-based":[40],"semantic":[41,74],"shown":[44],"promising":[45],"results,":[46],"existing":[47],"methods":[48],"struggle":[49],"to":[50,61,97],"preserve":[51],"fine-grained":[52],"features":[53],"and":[54,108,114,133,141],"suffer":[55],"from":[56],"excessive":[57],"quantization":[58,115,139],"errors":[59,140],"due":[60],"fixed-threshold":[62],"hard":[63],"binarization.":[64],"To":[65],"address":[66],"these":[67],"issues,":[68],"we":[69],"propose":[70],"unsupervised":[72],"novel":[73],"text":[75],"framework,":[77],"Quantization":[78],"Controlled":[79],"Hashing":[81],"(QCSH),":[82],"which":[83],"enhances":[84,102],"feature":[85],"representation":[86],"while":[87],"refines":[88],"binarization":[90,127],"process.":[91],"QCSH":[92,101,123,155],"integrates":[93],"several":[94],"specialized":[95],"modules":[96],"enhance":[98],"performance.":[100],"extraction":[104],"features,":[107],"jointly":[110],"optimizing":[111],"hash":[112,165],"codes":[113],"factors,":[116],"it":[117],"effectively":[118,137],"captures":[119],"their":[120],"interdependence.":[121],"Additionally,":[122],"applies":[124],"optimized":[126],"strategy":[128],"that":[129,154],"preserves":[130],"fidelity":[132],"maximizes":[134],"mutual":[135],"reducing":[138],"ensuring":[142],"balanced":[144],"bit":[145],"distribution.":[146],"Extensive":[147],"experiments":[148],"on":[149,159],"three":[150],"public":[151],"datasets":[152],"show":[153],"outperforms":[156],"state-of-the-art":[157],"baselines":[158],"various":[160],"numbers":[161],"bits":[163],"codes.":[166]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-01-29T00:00:00"}