{"id":"https://openalex.org/W4415539630","doi":"https://doi.org/10.1145/3746027.3755201","title":"Factorized Transformer Hashing with Adaptive Routing for Large-scale Image Retrieval","display_name":"Factorized Transformer Hashing with Adaptive Routing for Large-scale Image Retrieval","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415539630","doi":"https://doi.org/10.1145/3746027.3755201"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755201","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755201","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5018405816","display_name":"Yadong Huo","orcid":"https://orcid.org/0009-0008-8805-8958"},"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":"Yadong Huo","raw_affiliation_strings":["Ocean University of China, Qingdao, China"],"raw_orcid":"https://orcid.org/0009-0008-8805-8958","affiliations":[{"raw_affiliation_string":"Ocean University of China, Qingdao, China","institution_ids":["https://openalex.org/I59028903"]}]},{"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":["Weifang University, Weifang, China"],"raw_orcid":"https://orcid.org/0000-0001-7976-318X","affiliations":[{"raw_affiliation_string":"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":["Chongqing Normal University, Chongqing, China"],"raw_orcid":"https://orcid.org/0000-0001-7459-2510","affiliations":[{"raw_affiliation_string":"Chongqing Normal University, Chongqing, China","institution_ids":["https://openalex.org/I126924076"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100784430","display_name":"Lei Huang","orcid":"https://orcid.org/0000-0003-4087-3677"},"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":["Ocean University of China, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0003-4087-3677","affiliations":[{"raw_affiliation_string":"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":["Ocean University of China, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0003-4952-7666","affiliations":[{"raw_affiliation_string":"Ocean University of China, Qingdao, China","institution_ids":["https://openalex.org/I59028903"]}]}],"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":0.32911187,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6066","last_page":"6074"},"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":0.9998999834060669,"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":0.9998999834060669,"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":0.998199999332428,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.982699990272522,"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":0.6022999882698059},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.5493000149726868},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5450999736785889},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4984000027179718},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4212000072002411},{"id":"https://openalex.org/keywords/universal-hashing","display_name":"Universal hashing","score":0.40380001068115234},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.39320001006126404},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.3765999972820282},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.3709000051021576},{"id":"https://openalex.org/keywords/locality-sensitive-hashing","display_name":"Locality-sensitive hashing","score":0.3260999917984009}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7211999893188477},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.6022999882698059},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.5493000149726868},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5450999736785889},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4984000027179718},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.489300012588501},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4212000072002411},{"id":"https://openalex.org/C116058348","wikidata":"https://www.wikidata.org/wiki/Q846912","display_name":"Universal hashing","level":5,"score":0.40380001068115234},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.39320001006126404},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.3765999972820282},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3709000051021576},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36489999294281006},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3610999882221222},{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.3260999917984009},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.32269999384880066},{"id":"https://openalex.org/C122907437","wikidata":"https://www.wikidata.org/wiki/Q5318999","display_name":"Dynamic perfect hashing","level":5,"score":0.3206999897956848},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3093000054359436},{"id":"https://openalex.org/C133667856","wikidata":"https://www.wikidata.org/wiki/Q5439682","display_name":"Feature hashing","level":5,"score":0.3050999939441681},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C63435697","wikidata":"https://www.wikidata.org/wiki/Q864135","display_name":"Binary code","level":3,"score":0.3010999858379364},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.28870001435279846},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.28790000081062317},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.2849000096321106},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C191178318","wikidata":"https://www.wikidata.org/wiki/Q2256906","display_name":"Thresholding","level":3,"score":0.2702000141143799},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.27000001072883606},{"id":"https://openalex.org/C36375716","wikidata":"https://www.wikidata.org/wiki/Q6553456","display_name":"Linear hashing","level":5,"score":0.2596000134944916},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.25850000977516174},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755201","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755201","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2227360022","display_name":null,"funder_award_id":"No.62302338, No.62472390","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3959706945","display_name":null,"funder_award_id":"No.CSTB2023NSCQ-MSX0407","funder_id":"https://openalex.org/F4320323172","funder_display_name":"Natural Science Foundation of Chongqing"},{"id":"https://openalex.org/G8944248446","display_name":null,"funder_award_id":"No.ZR2022QF046, No.ZR2023MF033","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":18,"referenced_works":["https://openalex.org/W2411707397","https://openalex.org/W2464915613","https://openalex.org/W2966218308","https://openalex.org/W2986992616","https://openalex.org/W3108274592","https://openalex.org/W4200234862","https://openalex.org/W4225654135","https://openalex.org/W4287367114","https://openalex.org/W4312693803","https://openalex.org/W4379033967","https://openalex.org/W4380303571","https://openalex.org/W4383752469","https://openalex.org/W4386170403","https://openalex.org/W4386280829","https://openalex.org/W4390480900","https://openalex.org/W4396886507","https://openalex.org/W4404446753","https://openalex.org/W4406857563"],"related_works":[],"abstract_inverted_index":{"Transformer":[0,73],"architecture":[1],"has":[2],"driven":[3],"significant":[4],"advancements":[5],"in":[6,61,165],"deep":[7,24],"hashing,":[8],"establishing":[9],"itself":[10],"as":[11],"a":[12,70,79,108,128],"dominant":[13],"framework":[14,160],"for":[15,59,147],"large-scale":[16],"retrieval":[17,60],"and":[18,53,86,99,169],"storage":[19],"applications.":[20],"However,":[21],"existing":[22],"Transformer-based":[23],"hashing":[25,168,171],"methods":[26],"typically":[27],"employ":[28],"unvarying":[29],"feature":[30,115],"transformations":[31],"across":[32],"all":[33],"images,":[34],"limiting":[35],"their":[36],"adaptability":[37],"to":[38,48,82,137,142],"diverse":[39,114],"visual":[40],"patterns.":[41],"This":[42],"rigidity":[43],"restricts":[44],"the":[45,84,95,134,143,157],"model's":[46],"capacity":[47],"learn":[49],"both":[50,166],"highly":[51],"distinctive":[52],"generalizable":[54],"discrete":[55],"representations,":[56],"posing":[57],"challenges":[58],"open-world":[62],"scenarios.":[63],"To":[64],"overcome":[65],"this":[66],"challenge,":[67],"we":[68,93,121],"propose":[69],"novel":[71],"Factorized":[72],"Hashing":[74],"(FTH)":[75],"framework,":[76],"which":[77],"introduces":[78],"factorized":[80],"transformer":[81,109],"enhance":[83],"generalization":[85],"discriminative":[87],"power":[88],"of":[89,130],"hash":[90],"codes.":[91],"Specifically,":[92],"decompose":[94],"Multi-Head":[96],"Self-Attention":[97],"(MHSA)":[98],"Multi-Layer":[100],"Perceptron":[101],"(MLP)":[102],"blocks":[103],"into":[104],"multiple":[105],"sub-blocks,":[106],"forming":[107],"factorization":[110],"scheme":[111],"that":[112,156],"captures":[113],"characteristics":[116],"through":[117],"independent":[118],"sub-blocks.":[119],"Furthermore,":[120],"develop":[122],"an":[123],"adaptive":[124],"selection":[125],"strategy,":[126],"leveraging":[127],"set":[129],"learnable":[131],"selectors":[132],"with":[133],"Softmax":[135],"function,":[136],"dynamically":[138],"route":[139],"each":[140],"image":[141,167],"most":[144],"appropriate":[145],"sub-block":[146],"processing.":[148],"Extensive":[149],"experiments":[150],"on":[151],"three":[152],"benchmark":[153],"datasets":[154],"demonstrate":[155],"proposed":[158],"FTH":[159],"significantly":[161],"outperforms":[162],"state-of-the-art":[163],"baselines":[164],"zero-shot":[170],"tasks.":[172],"Source":[173],"code":[174],"is":[175],"available":[176],"at":[177],"https://github.com/QinLab-WFU/FTH.":[178]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-25T00:00:00"}