{"id":"https://openalex.org/W7204157465","doi":"https://doi.org/10.1145/3817395.3817428","title":"Top-K Collaborative Optimization for High-Dimensional Vector Deduplication","display_name":"Top-K Collaborative Optimization for High-Dimensional Vector Deduplication","publication_year":2026,"publication_date":"2026-03-20","ids":{"openalex":"https://openalex.org/W7204157465","doi":"https://doi.org/10.1145/3817395.3817428"},"language":"en","primary_location":{"id":"doi:10.1145/3817395.3817428","doi":"https://doi.org/10.1145/3817395.3817428","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3817395.3817428","pdf_url":null,"source":{"id":"https://openalex.org/S7407115342","display_name":"International Conference on Big Data and Intelligent Manufacturing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"conference"},"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 Big Data and Intelligent Manufacturing","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3817395.3817428","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5148113375","display_name":"Hu Ruoqing","orcid":"https://orcid.org/0009-0002-3132-3999","observed_orcids":["https://orcid.org/0009-0002-3132-3999"]},"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":"Hu Ruoqing","raw_affiliation_strings":["Sun Yat-sen University, guangdong, China"],"raw_orcid":"https://orcid.org/0009-0002-3132-3999","affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, guangdong, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5148113375"],"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":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"219","last_page":"223"},"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":0.9053000211715698,"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":0.9053000211715698,"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/T11719","display_name":"Data Quality and Management","score":0.06369999796152115,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.0034000000450760126,"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/high-dimensional-feature-vectors","display_name":"high-dimensional feature vectors","score":0.9350000023841858},{"id":"https://openalex.org/keywords/collaborative-optimization","display_name":"collaborative optimization","score":0.8019999861717224},{"id":"https://openalex.org/keywords/mixed-precision","display_name":"mixed precision","score":0.9430000185966492},{"id":"https://openalex.org/keywords/fp8","display_name":"FP8","score":0.6949999928474426},{"id":"https://openalex.org/keywords/gpu-memory-efficiency","display_name":"GPU memory efficiency","score":0.7110000252723694},{"id":"https://openalex.org/keywords/pre-trained-vision-models","display_name":"pre-trained vision models","score":0.6859999895095825},{"id":"https://openalex.org/keywords/dataset-compression","display_name":"dataset compression","score":0.6449999809265137},{"id":"https://openalex.org/keywords/content-retrieval","display_name":"content retrieval","score":0.9229999780654907}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.9067999720573425},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8503999710083008},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.6643000245094299},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.599399983882904},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4912000000476837},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4708000123500824},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.45170000195503235},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.44369998574256897},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.43309998512268066},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.3885999917984009},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.33390000462532043},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.3312999904155731},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.32670000195503235},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.3111000061035156},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.29840001463890076},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.29679998755455017},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.29409998655319214},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.27070000767707825},{"id":"https://openalex.org/C82687282","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Auxiliary memory","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C551230270","wikidata":"https://www.wikidata.org/wiki/Q4368942","display_name":"Data retrieval","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C2779020251","wikidata":"https://www.wikidata.org/wiki/Q3555171","display_name":"Motion vector","level":3,"score":0.263700008392334},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.26350000500679016},{"id":"https://openalex.org/C2781357197","wikidata":"https://www.wikidata.org/wiki/Q5757597","display_name":"High memory","level":2,"score":0.2581000030040741}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3817395.3817428","doi":"https://doi.org/10.1145/3817395.3817428","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3817395.3817428","pdf_url":null,"source":{"id":"https://openalex.org/S7407115342","display_name":"International Conference on Big Data and Intelligent Manufacturing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"conference"},"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 Big Data and Intelligent Manufacturing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3817395.3817428","doi":"https://doi.org/10.1145/3817395.3817428","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3817395.3817428","pdf_url":null,"source":{"id":"https://openalex.org/S7407115342","display_name":"International Conference on Big Data and Intelligent Manufacturing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"conference"},"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 Big Data and Intelligent Manufacturing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W2124509324","https://openalex.org/W2593864460"],"related_works":["https://openalex.org/W7197025426","https://openalex.org/W4372259898","https://openalex.org/W3083971366","https://openalex.org/W4378418314","https://openalex.org/W4406033018","https://openalex.org/W4285327104","https://openalex.org/W7140278568","https://openalex.org/W3015673245","https://openalex.org/W2920476195","https://openalex.org/W4382052535"],"abstract_inverted_index":{"With":[0,73],"the":[1,38,47,78,90,94,120,132,197,200,228,232,243,252,275],"widespread":[2],"application":[3],"of":[4,86,93,97,123,134,199,262,268,279],"large":[5],"pre-trained":[6,127],"models":[7],"in":[8,21,54],"computer":[9],"vision":[10],"and":[11,31,46,159,169,222,239,257,264,295],"natural":[12],"language":[13],"processing,":[14],"massive":[15],"high-dimensional":[16,56,70,280],"feature":[17,57],"vectors":[18,145],"are":[19,174],"generated":[20],"large-scale":[22,55,276],"industrial":[23],"scenarios,":[24,60],"posing":[25],"an":[26],"urgent":[27],"demand":[28],"for":[29,69,143,148,289],"efficient":[30,286],"accurate":[32],"vector":[33,58,71],"deduplication":[34,59,87,183,234,260,277],"technology.":[35],"To":[36,195],"address":[37],"low":[39],"retrieval":[40,76,100,180,294],"efficiency,":[41],"high":[42],"hardware":[43,157,187],"resource":[44,104,192],"consumption,":[45],"accuracy-speed":[48],"trade-off":[49],"faced":[50],"by":[51,236,248],"traditional":[52],"methods":[53],"this":[61,81],"paper":[62],"proposes":[63],"a":[64,107,170,190,207,259,265],"Top-K":[65,74,135,179],"collaborative":[66,91],"optimization":[67],"scheme":[68,82,230],"deduplication.":[72],"similarity":[75],"as":[77,216,218,292],"core":[79],"hub,":[80],"achieves":[83],"end-to-end":[84],"improvement":[85],"performance":[88],"through":[89,189],"design":[92],"full":[95],"process":[96],"\u201cpre-screening":[98],"-":[99,101,103],"clustering":[102],"management\u201d.":[105],"Specifically,":[106],"model-aware":[108],"dynamic":[109,165,191],"hashing":[110],"strategy":[111],"is":[112,151],"designed":[113],"to":[114,119,153,155,176,274],"customize":[115],"hash":[116],"functions":[117],"according":[118],"distribution":[121],"differences":[122],"features":[124,213,281],"from":[125,214,282],"different":[126],"models,":[128,284],"thereby":[129],"accurately":[130],"narrowing":[131],"scope":[133],"retrieval.":[136],"A":[137,164],"mixed-precision":[138],"computing":[139],"method":[140],"combining":[141],"\u201cFP32":[142],"high-frequency":[144],"+":[146],"FP8":[147],"low-frequency":[149],"vectors\u201d":[150],"adopted":[152],"adapt":[154,273],"GPU":[156,244,253],"characteristics":[158],"reduce":[160],"video":[161,245],"memory":[162,246],"overhead.":[163],"K-value":[166],"adjustment":[167],"mechanism":[168],"parallel":[171,254],"disjoint-set":[172],"algorithm":[173],"introduced":[175],"efficiently":[177],"convert":[178],"results":[181,225],"into":[182],"outputs,":[184],"while":[185],"maximizing":[186],"utilization":[188],"management":[193],"module.":[194],"verify":[196],"effectiveness":[198],"proposed":[201,229],"scheme,":[202,256],"experiments":[203],"were":[204],"conducted":[205],"on":[206],"private":[208],"dataset":[209,296],"comprising":[210],"50,000":[211],"1024-dimensional":[212],"SSCD/ViT/CLIP,":[215],"well":[217],"public":[219],"benchmarks":[220],"(SIFT1M":[221],"DEEP10M).":[223],"Experimental":[224],"show":[226],"that":[227],"reduces":[231],"total":[233],"time":[235],"88.1%,":[237],"63.8%,":[238],"42.0%":[240],"respectively,":[241],"decreases":[242],"usage":[247],"41.7%":[249],"compared":[250],"with":[251],"benchmark":[255],"maintains":[258],"accuracy":[261],"98.3%":[263],"retention":[266],"rate":[267],"86.2%.":[269],"It":[270],"can":[271],"effectively":[272],"requirements":[278],"multiple":[283],"providing":[285],"technical":[287],"support":[288],"scenarios":[290],"such":[291],"content":[293],"compression.":[297]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-26T00:00:00"}