{"id":"https://openalex.org/W7124453537","doi":"https://doi.org/10.1109/tmm.2026.3654452","title":"Deep Distance Weighted Sampling Hashing for Cross-Modal Retrieval","display_name":"Deep Distance Weighted Sampling Hashing for Cross-Modal Retrieval","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7124453537","doi":"https://doi.org/10.1109/tmm.2026.3654452"},"language":null,"primary_location":{"id":"doi:10.1109/tmm.2026.3654452","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3654452","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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/A5103438457","display_name":"Kun Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I202126657","display_name":"Qufu Normal University","ror":"https://ror.org/03ceheh96","country_code":"CN","type":"education","lineage":["https://openalex.org/I202126657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Cheng","raw_affiliation_strings":["School of Computer Science, Qufu Normal University, Rizhao, China"],"raw_orcid":"https://orcid.org/0009-0009-3531-6260","affiliations":[{"raw_affiliation_string":"School of Computer Science, Qufu Normal University, Rizhao, China","institution_ids":["https://openalex.org/I202126657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091326895","display_name":"Qibing Qin","orcid":"https://orcid.org/0000-0001-7976-318X"},"institutions":[{"id":"https://openalex.org/I66883779","display_name":"Weifang University","ror":"https://ror.org/01frp7483","country_code":"CN","type":"education","lineage":["https://openalex.org/I66883779"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qibing Qin","raw_affiliation_strings":["School of Computer Engineering, Weifang University, Weifang, China"],"raw_orcid":"https://orcid.org/0000-0001-7976-318X","affiliations":[{"raw_affiliation_string":"School of Computer Engineering, Weifang University, Weifang, China","institution_ids":["https://openalex.org/I66883779"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061246177","display_name":"Wenfeng Zhang","orcid":"https://orcid.org/0000-0001-7459-2510"},"institutions":[{"id":"https://openalex.org/I126924076","display_name":"Chongqing Normal University","ror":"https://ror.org/01dcw5w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I126924076"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenfeng Zhang","raw_affiliation_strings":["College of Computer and Information Science, Chongqing Normal University, Chongqing, China"],"raw_orcid":"https://orcid.org/0000-0001-7459-2510","affiliations":[{"raw_affiliation_string":"College of Computer and Information Science, Chongqing Normal University, Chongqing, China","institution_ids":["https://openalex.org/I126924076"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123182216","display_name":"Lei Huang","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":"Lei Huang","raw_affiliation_strings":["Faculty of Information Science and Engineering, Ocean University of China, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0003-4087-3677","affiliations":[{"raw_affiliation_string":"Faculty of Information Science and Engineering, Ocean University of China, Qingdao, China","institution_ids":["https://openalex.org/I59028903"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058652390","display_name":"Jie Nie","orcid":"https://orcid.org/0000-0003-4952-7666"},"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":"Jie Nie","raw_affiliation_strings":["Faculty of Information Science and Engineering, Ocean University of China, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0003-4952-7666","affiliations":[{"raw_affiliation_string":"Faculty of Information Science and Engineering, Ocean University of China, Qingdao, China","institution_ids":["https://openalex.org/I59028903"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":33.6955,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.99642032,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"28","issue":null,"first_page":"4194","last_page":"4206"},"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":0.9789000153541565,"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":0.9789000153541565,"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":0.00279999990016222,"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":0.0015999999595806003,"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":0.7419999837875366},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.6782000064849854},{"id":"https://openalex.org/keywords/importance-sampling","display_name":"Importance sampling","score":0.5371000170707703},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4657000005245209},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.4535999894142151},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.4341000020503998},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.42969998717308044},{"id":"https://openalex.org/keywords/binary-code","display_name":"Binary code","score":0.42809998989105225},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.4223000109195709},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3813999891281128}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7556999921798706},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.7419999837875366},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.6782000064849854},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.5371000170707703},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4657000005245209},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.4535999894142151},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.4341000020503998},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.42969998717308044},{"id":"https://openalex.org/C63435697","wikidata":"https://www.wikidata.org/wiki/Q864135","display_name":"Binary code","level":3,"score":0.42809998989105225},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.4223000109195709},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4156999886035919},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.399399995803833},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38830000162124634},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3813999891281128},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.37880000472068787},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.34380000829696655},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3431999981403351},{"id":"https://openalex.org/C75917345","wikidata":"https://www.wikidata.org/wiki/Q2725298","display_name":"Sampling bias","level":3,"score":0.34290000796318054},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.3377000093460083},{"id":"https://openalex.org/C187062812","wikidata":"https://www.wikidata.org/wiki/Q6322840","display_name":"K-independent hashing","level":5,"score":0.3337000012397766},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.32760000228881836},{"id":"https://openalex.org/C187192777","wikidata":"https://www.wikidata.org/wiki/Q381699","display_name":"Rejection sampling","level":5,"score":0.3260999917984009},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.32120001316070557},{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.31940001249313354},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3138999938964844},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.3027999997138977},{"id":"https://openalex.org/C20353970","wikidata":"https://www.wikidata.org/wiki/Q1056998","display_name":"Simple random sample","level":3,"score":0.28209999203681946},{"id":"https://openalex.org/C75373757","wikidata":"https://www.wikidata.org/wiki/Q7410160","display_name":"Sampling design","level":3,"score":0.2818000018596649},{"id":"https://openalex.org/C122907437","wikidata":"https://www.wikidata.org/wiki/Q5318999","display_name":"Dynamic perfect hashing","level":5,"score":0.2815999984741211},{"id":"https://openalex.org/C193319292","wikidata":"https://www.wikidata.org/wiki/Q272172","display_name":"Hamming distance","level":2,"score":0.2754000127315521},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C82152865","wikidata":"https://www.wikidata.org/wiki/Q7208505","display_name":"Poisson sampling","level":5,"score":0.2619999945163727},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.2578999996185303},{"id":"https://openalex.org/C122507166","wikidata":"https://www.wikidata.org/wiki/Q628906","display_name":"Crossover","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2026.3654452","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3654452","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7191771268844604,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G3296221036","display_name":null,"funder_award_id":"CSTB2023NSCQMSX0407","funder_id":"https://openalex.org/F4320323172","funder_display_name":"Natural Science Foundation of Chongqing"},{"id":"https://openalex.org/G3751622555","display_name":null,"funder_award_id":"ZR2022QF046","funder_id":"https://openalex.org/F4320324174","funder_display_name":"Natural Science Foundation of Shandong Province"},{"id":"https://openalex.org/G5403098715","display_name":null,"funder_award_id":"62302338","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G971057150","display_name":null,"funder_award_id":"ZR 2023MF033","funder_id":"https://openalex.org/F4320324174","funder_display_name":"Natural Science Foundation of Shandong Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320323172","display_name":"Natural Science Foundation of Chongqing","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324174","display_name":"Natural Science Foundation of Shandong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1869500417","https://openalex.org/W1910300841","https://openalex.org/W1996936615","https://openalex.org/W2021354639","https://openalex.org/W2047221353","https://openalex.org/W2096733369","https://openalex.org/W2096830573","https://openalex.org/W2138621090","https://openalex.org/W2155803963","https://openalex.org/W2266728343","https://openalex.org/W2411707397","https://openalex.org/W2547805042","https://openalex.org/W2894874917","https://openalex.org/W2949588459","https://openalex.org/W2963026686","https://openalex.org/W2963187862","https://openalex.org/W2963350250","https://openalex.org/W2982065678","https://openalex.org/W3003735286","https://openalex.org/W3006683596","https://openalex.org/W3008072721","https://openalex.org/W3012050760","https://openalex.org/W3033799362","https://openalex.org/W3093981303","https://openalex.org/W3108274592","https://openalex.org/W3123742938","https://openalex.org/W3192393047","https://openalex.org/W3202874825","https://openalex.org/W4210593721","https://openalex.org/W4287367114","https://openalex.org/W4304092731","https://openalex.org/W4304099318","https://openalex.org/W4312454624","https://openalex.org/W4367047323","https://openalex.org/W4379033967","https://openalex.org/W4379382581","https://openalex.org/W4383752469","https://openalex.org/W4386914241","https://openalex.org/W4387968356","https://openalex.org/W4388191759","https://openalex.org/W4390480900","https://openalex.org/W4391249024","https://openalex.org/W4391282658","https://openalex.org/W4395029038","https://openalex.org/W4396886507","https://openalex.org/W4401451853","https://openalex.org/W4405741836","https://openalex.org/W4406857563","https://openalex.org/W4410358803"],"related_works":[],"abstract_inverted_index":{"Cross-modal":[0],"hashing":[1],"seeks":[2],"to":[3,21,84,106,181],"encode":[4],"heterogeneous":[5],"image-text":[6],"data":[7,109],"into":[8],"compact":[9],"binary":[10],"codes":[11],"for":[12,62,213],"efficient":[13],"retrieval.":[14],"While":[15],"significant":[16],"efforts":[17],"have":[18],"been":[19],"made":[20],"study":[22,130],"sampling":[23,41,54,73,132,148,183,193],"strategies,":[24],"most":[25],"of":[26,206],"these":[27],"approaches":[28],"are":[29],"tightly":[30],"integrated":[31],"with":[32,163],"loss":[33,60,136,151,165,207],"function":[34,166,208],"engineering,":[35],"lacking":[36],"an":[37,195],"independent":[38,196],"focus":[39],"on":[40],"methods.":[42],"In":[43],"this":[44],"paper,":[45],"we":[46,124],"challenge":[47],"the":[48,126],"convention":[49],"by":[50,68,116,178],"revealing":[51],"that":[52],"batch-level":[53],"strategy":[55],"is":[56,82,215],"equally":[57],"pivotal":[58],"as":[59,194],"design":[61,167],"learning":[63],"discriminative":[64],"hash":[65],"codes.":[66],"Specifically,":[67],"introducing":[69],"a":[70,75,203],"novel":[71],"distribution-aware":[72],"strategy,":[74],"Distance":[76],"Weighted":[77],"Sampling":[78],"Hashing":[79],"(DDWSH)":[80],"framework":[81],"proposed":[83],"dynamically":[85],"select":[86],"stable":[87],"and":[88,135,168,172],"informative":[89],"training":[90,113],"pairs.":[91],"Unlike":[92],"conventional":[93],"random":[94],"or":[95],"semi-hard":[96,158,182],"sampling,":[97],"our":[98,122],"method":[99],"weights":[100],"pairwise":[101],"distances":[102],"within":[103],"each":[104],"batch":[105,186],"approximate":[107],"global":[108],"distribution,":[110],"thereby":[111],"mitigating":[112],"instability":[114],"caused":[115],"biased":[117],"sampling.":[118],"To":[119],"rigorously":[120],"validate":[121],"claims,":[123],"conduct":[125],"first":[127],"comprehensive":[128],"crossover":[129],"between":[131],"strategies":[133],"(random/semi-hard/ours)":[134],"functions":[137],"(contrastive/triplet/ours)":[138],"across":[139],"three":[140],"benchmark":[141],"datasets.":[142],"Experiments":[143],"demonstrate":[144],"that:":[145],"Universality:":[146],"Our":[147],"boosts":[149],"all":[150],"functions'":[152],"performance":[153,176],"(average":[154],"+4.3%":[155],"mAP":[156],"vs.":[157],"mining),":[159],"Superiority:":[160],"DDWSH":[161,214],"competes":[162],"complex":[164],"achieves":[169],"state-of-the-art":[170],"results,":[171],"Stability:":[173],"It":[174],"reduces":[175],"variance":[177],"60.2%":[179],"compared":[180],"under":[184],"varying":[185],"compositions":[187],"average.":[188],"This":[189],"systematic":[190],"analysis":[191],"establishes":[192],"research":[197],"dimension":[198],"in":[199],"deep":[200],"hashing,":[201],"beyond":[202],"mere":[204],"part":[205],"engineering.":[209],"The":[210],"source":[211],"code":[212],"freely":[216],"available":[217],"athttps://github.com/QinLab-WFU/DDWSH.":[218]},"counts_by_year":[{"year":2026,"cited_by_count":5}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2026-01-17T00:00:00"}