{"id":"https://openalex.org/W4293248850","doi":"https://doi.org/10.1145/3539813.3545148","title":"U-BERT for Fast and Scalable Text-Image Retrieval","display_name":"U-BERT for Fast and Scalable Text-Image Retrieval","publication_year":2022,"publication_date":"2022-08-23","ids":{"openalex":"https://openalex.org/W4293248850","doi":"https://doi.org/10.1145/3539813.3545148"},"language":"en","primary_location":{"id":"doi:10.1145/3539813.3545148","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3539813.3545148","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 ACM SIGIR International Conference on Theory of Information Retrieval","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/A5018887598","display_name":"Tan Yu","orcid":"https://orcid.org/0000-0001-6071-0395"},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tan Yu","raw_affiliation_strings":["Baidu Research, Bellevue, WA, USA"],"affiliations":[{"raw_affiliation_string":"Baidu Research, Bellevue, WA, USA","institution_ids":["https://openalex.org/I4210108985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068755696","display_name":"Hongliang Fei","orcid":null},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongliang Fei","raw_affiliation_strings":["Baidu Research, Bellevue, WA, USA"],"affiliations":[{"raw_affiliation_string":"Baidu Research, Bellevue, WA, USA","institution_ids":["https://openalex.org/I4210108985"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100435527","display_name":"Ping Li","orcid":"https://orcid.org/0000-0002-5979-8868"},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ping Li","raw_affiliation_strings":["Baidu Research, Bellevue, WA, USA"],"affiliations":[{"raw_affiliation_string":"Baidu Research, Bellevue, WA, USA","institution_ids":["https://openalex.org/I4210108985"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5018887598"],"corresponding_institution_ids":["https://openalex.org/I4210108985"],"apc_list":null,"apc_paid":null,"fwci":0.604,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.67017648,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"193","last_page":"203"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9995999932289124,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9962999820709229,"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/modal","display_name":"Modal","score":0.7573368549346924},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6633284687995911},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5363487005233765},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.5316254496574402},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.44103577733039856},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4104304015636444},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3616654872894287},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3289273977279663},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3212553560733795},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09525629878044128}],"concepts":[{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7573368549346924},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6633284687995911},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5363487005233765},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5316254496574402},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.44103577733039856},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4104304015636444},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3616654872894287},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3289273977279663},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3212553560733795},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09525629878044128},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3539813.3545148","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3539813.3545148","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 ACM SIGIR International Conference on Theory of Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.6800000071525574,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1202352811","https://openalex.org/W1905882502","https://openalex.org/W2070753207","https://openalex.org/W2100235303","https://openalex.org/W2185175083","https://openalex.org/W2251084241","https://openalex.org/W2277195237","https://openalex.org/W2546696630","https://openalex.org/W2552579943","https://openalex.org/W2745461083","https://openalex.org/W2886641317","https://openalex.org/W2905169750","https://openalex.org/W2956018683","https://openalex.org/W2962964995","https://openalex.org/W2964120214","https://openalex.org/W2970231061","https://openalex.org/W2978329087","https://openalex.org/W2979304729","https://openalex.org/W2981851019","https://openalex.org/W2988823324","https://openalex.org/W2998356391","https://openalex.org/W3034727271","https://openalex.org/W3035454331","https://openalex.org/W3035588244","https://openalex.org/W3045277523","https://openalex.org/W3080510735","https://openalex.org/W3081143589","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3092767330","https://openalex.org/W3104152799","https://openalex.org/W3110042533","https://openalex.org/W3154430790","https://openalex.org/W3166304536","https://openalex.org/W3168851777","https://openalex.org/W3171734937","https://openalex.org/W3173220247","https://openalex.org/W3173789715","https://openalex.org/W3173909648","https://openalex.org/W3177155667","https://openalex.org/W3177224328","https://openalex.org/W3177654849","https://openalex.org/W3209275363","https://openalex.org/W3211032667","https://openalex.org/W3212100893","https://openalex.org/W4247950230","https://openalex.org/W4284697766","https://openalex.org/W4310895557"],"related_works":["https://openalex.org/W2364921833","https://openalex.org/W2275988210","https://openalex.org/W1525643724","https://openalex.org/W2067938758","https://openalex.org/W2379533788","https://openalex.org/W2382623646","https://openalex.org/W3087771547","https://openalex.org/W2333420780","https://openalex.org/W2375199418","https://openalex.org/W2368437561"],"abstract_inverted_index":{"Exploiting":[0],"cross-modal":[1,10,22,26,40,75,115],"attention":[2],"on":[3,153,217],"image":[4],"region":[5],"features":[6,145],"and":[7,46,68,113,128,171,223],"text":[8],"features,":[9],"BERT":[11,27,41,76],"models":[12,28,42],"have":[13],"achieved":[14],"higher":[15],"accuracy":[16],"than":[17],"the":[18,56,69,73,93,96,133,139,143,148,163,168,174,178,183,191,202,206,221,226],"embedding-based":[19,61],"methods":[20],"in":[21,95],"text-image":[23,149],"retrieval.":[24,116],"Nevertheless,":[25,82],"take":[29],"image-text":[30],"pairs":[31],"as":[32,177],"input,":[33],"requiring":[34],"a":[35,52,85,106,158,212],"quadratic":[36],"computational":[37],"complexity.":[38,161],"Thus,":[39],"are":[43],"prohibitively":[44],"slow":[45],"not":[47],"scalable.":[48],"A":[49],"remedy":[50],"is":[51],"two-stage":[53],"strategy,":[54],"wherein":[55],"first":[57,134],"stage":[58,71],"uses":[59,138],"an":[60,111,125,129],"method":[62],"to":[63,77,83,109,146,181,200],"retrieve":[64],"top":[65],"K":[66,80,88],"items":[67],"second":[70,97,164,207],"deploys":[72],"heavy":[74],"re-rank":[78],"these":[79],"items.":[81],"achieve":[84,110],"satisfying":[86],"accuracy,":[87],"should":[89],"be":[90],"large,":[91],"making":[92,205],"retrieval":[94],"phase":[98,208],"still":[99],"slow.":[100],"In":[101,132,162],"this":[102],"paper,":[103],"we":[104,194],"propose":[105],"U-BERT":[107,119,136,166],"model":[108],"effective":[112],"efficient":[114,209],"The":[117],"proposed":[118,227],"decomposes":[120],"each":[121],"image/text":[122,144],"feature":[123],"into":[124],"intra-modal":[126,140,169,184,192],"component":[127,141,170,176],"inter-modal":[130,175,203],"component.":[131],"stage,":[135,165],"only":[137,195],"of":[142,225],"obtain":[147],"similarity":[150],"scores":[151],"based":[152],"two":[154],"independent":[155],"encoders,":[156],"with":[157],"linear":[159],"computation":[160],"reuses":[167],"additionally":[172],"use":[173],"complementary":[179],"residual":[180],"enhance":[182],"component's":[185],"discriminating":[186],"capability.":[187],"Benefited":[188],"from":[189],"reusing":[190],"component,":[193,204],"need":[196],"few":[197],"Transformer":[198],"layers":[199],"generate":[201],"even":[210],"facing":[211],"large":[213],"K.":[214],"Extensive":[215],"experiments":[216],"public":[218],"benchmarks":[219],"demonstrate":[220],"efficiency":[222],"effectiveness":[224],"U-BERT.":[228]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}