{"id":"https://openalex.org/W4390872633","doi":"https://doi.org/10.1109/iccv51070.2023.01029","title":"LexLIP: Lexicon-Bottlenecked Language-Image Pre-Training for Large-Scale Image-Text Sparse Retrieval","display_name":"LexLIP: Lexicon-Bottlenecked Language-Image Pre-Training for Large-Scale Image-Text Sparse Retrieval","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4390872633","doi":"https://doi.org/10.1109/iccv51070.2023.01029"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51070.2023.01029","pdf_url":null,"source":{"id":"https://openalex.org/S4363607764","display_name":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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/A5114803621","display_name":"Ziyang Luo","orcid":"https://orcid.org/0009-0009-4522-6525"},"institutions":[{"id":"https://openalex.org/I141568987","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131","country_code":"HK","type":"education","lineage":["https://openalex.org/I141568987"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ziyang Luo","raw_affiliation_strings":["Hong Kong Baptist University, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"Hong Kong Baptist University, Hong Kong SAR, China","institution_ids":["https://openalex.org/I141568987"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073885088","display_name":"Pu Zhao","orcid":"https://orcid.org/0000-0001-5018-2859"},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Pu Zhao","raw_affiliation_strings":["Microsoft Corporation"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057548170","display_name":"Can Xu","orcid":"https://orcid.org/0000-0002-0726-790X"},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Can Xu","raw_affiliation_strings":["Microsoft Corporation"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084564357","display_name":"Xiubo Geng","orcid":"https://orcid.org/0000-0001-6477-7933"},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Xiubo Geng","raw_affiliation_strings":["Microsoft Corporation"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100611243","display_name":"Tao Shen","orcid":"https://orcid.org/0000-0003-3315-2468"},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Tao Shen","raw_affiliation_strings":["Microsoft Corporation"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073065834","display_name":"Chongyang Tao","orcid":"https://orcid.org/0000-0002-4162-2119"},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Chongyang Tao","raw_affiliation_strings":["Microsoft Corporation"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100460560","display_name":"Jing Ma","orcid":"https://orcid.org/0000-0003-0103-9858"},"institutions":[{"id":"https://openalex.org/I141568987","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131","country_code":"HK","type":"education","lineage":["https://openalex.org/I141568987"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jing Ma","raw_affiliation_strings":["Hong Kong Baptist University, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"Hong Kong Baptist University, Hong Kong SAR, China","institution_ids":["https://openalex.org/I141568987"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088646345","display_name":"Qingwei Lin","orcid":"https://orcid.org/0000-0003-2559-2383"},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Qingwei Lin","raw_affiliation_strings":["Microsoft Corporation"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060116992","display_name":"Daxin Jiang","orcid":"https://orcid.org/0000-0002-6657-5806"},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Daxin Jiang","raw_affiliation_strings":["Microsoft Corporation"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]}],"institution_assertions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.289,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.999956,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"11172","last_page":"11183"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998,"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":0.9998,"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":0.9994,"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":0.9987,"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/leverage","display_name":"Leverage (statistics)","score":0.46695265},{"id":"https://openalex.org/keywords/semantic-gap","display_name":"Semantic gap","score":0.429768}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.81642556},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.6418401},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6136436},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5494336},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.50214815},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.4991927},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48757237},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.46695265},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.429768},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33673394},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3192312},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51070.2023.01029","pdf_url":null,"source":{"id":"https://openalex.org/S4363607764","display_name":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.78,"id":"https://metadata.un.org/sdg/4","display_name":"Quality education"}],"grants":[{"funder":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China","award_id":null}],"datasets":[],"versions":[],"referenced_works_count":40,"referenced_works":["https://openalex.org/W12634471","https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W2017814585","https://openalex.org/W2047643928","https://openalex.org/W2108598243","https://openalex.org/W2112796928","https://openalex.org/W2155904486","https://openalex.org/W2297545632","https://openalex.org/W2533598788","https://openalex.org/W2600067905","https://openalex.org/W2606473278","https://openalex.org/W2740321901","https://openalex.org/W2886641317","https://openalex.org/W2998702515","https://openalex.org/W3035524453","https://openalex.org/W3118608800","https://openalex.org/W3154280800","https://openalex.org/W3166125679","https://openalex.org/W3166304536","https://openalex.org/W3171668871","https://openalex.org/W3176463841","https://openalex.org/W3176641147","https://openalex.org/W3188983256","https://openalex.org/W3201703290","https://openalex.org/W3204588463","https://openalex.org/W3213454282","https://openalex.org/W4206121183","https://openalex.org/W4281562781","https://openalex.org/W4283327148","https://openalex.org/W4284663260","https://openalex.org/W4284664419","https://openalex.org/W4290960530","https://openalex.org/W4313178921","https://openalex.org/W4313181088","https://openalex.org/W4367047068","https://openalex.org/W4385567664","https://openalex.org/W4385571915","https://openalex.org/W4385574227"],"related_works":["https://openalex.org/W2735794310","https://openalex.org/W2605741187","https://openalex.org/W2373526234","https://openalex.org/W2370180225","https://openalex.org/W2186394444","https://openalex.org/W2146107302","https://openalex.org/W2140369944","https://openalex.org/W2120663665","https://openalex.org/W2071180033","https://openalex.org/W2002918846"],"abstract_inverted_index":{"Image-text":[0],"retrieval":[1,21,42,56,86,165,173],"(ITR)":[2],"aims":[3],"to":[4,76,136],"retrieve":[5],"images":[6,26,69],"or":[7],"texts":[8,28],"that":[9,60,116],"match":[10],"a":[11,53,98,108],"query":[12],"originating":[13],"from":[14,92],"the":[15,65,126],"other":[16],"modality.":[17],"The":[18],"conventional":[19],"dense":[20,30],"paradigm":[22,57,73],"relies":[23],"on":[24,155],"encoding":[25],"and":[27,70,80,129,141,160,175],"into":[29],"representations":[31,63],"with":[32,147,170],"dual-stream":[33,127],"encoders.":[34],"However,":[35],"this":[36,49,104],"approach":[37],"is":[38],"limited":[39],"by":[40],"slow":[41],"speeds":[43],"in":[44,64,97,163],"large-scale":[45,164],"scenarios.":[46],"To":[47,102],"address":[48],"issue,":[50],"we":[51,106,133],"propose":[52],"novel":[54,109],"sparse":[55,62,99],"for":[58,68],"ITR":[59,157],"exploits":[61],"vocabulary":[66,100],"space":[67],"texts.":[71],"This":[72],"enables":[74],"us":[75],"leverage":[77],"bag-of-words":[78,139],"models":[79],"efficient":[81],"inverted":[82],"indexes,":[83],"significantly":[84],"reducing":[85],"latency.":[87],"A":[88],"critical":[89],"gap":[90],"emerges":[91],"representing":[93],"continuous":[94,138],"image":[95,192],"data":[96],"space.":[101],"bridge":[103],"gap,":[105],"introduce":[107],"pre-training":[110,146],"framework,":[111],"Lexicon-Bottlenecked":[112],"Language-Image":[113],"Pre-Training":[114],"(LexLIP),":[115],"learns":[117],"importance-aware":[118],"lexicon":[119],"representations.":[120],"By":[121],"using":[122],"lexicon-bottlenecked":[123],"modules":[124],"between":[125],"encoders":[128],"weakened":[130],"text":[131],"decoders,":[132],"are":[134],"able":[135],"construct":[137],"bottlenecks":[140],"learn":[142],"lexicon-importance":[143],"distributions.":[144],"Upon":[145],"same-scale":[148],"data,":[149],"our":[150],"LexLIP":[151,167,183],"achieves":[152],"state-of-the-art":[153],"performance":[154],"two":[156],"benchmarks,":[158],"MSCOCO":[159],"Flickr30k.":[161],"Furthermore,":[162],"scenarios,":[166],"outperforms":[168],"CLIP":[169,185],"5.8\u00d7":[171],"faster":[172],"speed":[174],"19.1\u00d7":[176],"less":[177],"index":[178],"storage":[179],"memory.":[180],"Beyond":[181],"this,":[182],"surpasses":[184],"across":[186],"8":[187],"out":[188],"of":[189],"10":[190],"zero-shot":[191],"classification":[193],"tasks.":[194]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4390872633","counts_by_year":[{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":3}],"updated_date":"2025-01-06T07:46:02.067931","created_date":"2024-01-16"}