{"id":"https://openalex.org/W3202464651","doi":"https://doi.org/10.1109/inista52262.2021.9548414","title":"Multimodal Retrieval with Contrastive Pretraining","display_name":"Multimodal Retrieval with Contrastive Pretraining","publication_year":2021,"publication_date":"2021-08-25","ids":{"openalex":"https://openalex.org/W3202464651","doi":"https://doi.org/10.1109/inista52262.2021.9548414","mag":"3202464651"},"language":"en","primary_location":{"id":"doi:10.1109/inista52262.2021.9548414","is_oa":false,"landing_page_url":"https://doi.org/10.1109/inista52262.2021.9548414","pdf_url":null,"source":{"id":"https://openalex.org/S4306498847","display_name":"2021 International Conference on INnovations in Intelligent SysTems and Applications (INISTA)","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Conference on INnovations in Intelligent SysTems and Applications (INISTA)","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/A5049579400","display_name":"H\u00fcseyin Fuat Alsan","orcid":"https://orcid.org/0000-0003-2988-7656"},"institutions":[{"id":"https://openalex.org/I132286405","display_name":"Kadir Has University","ror":"https://ror.org/03zzckc47","country_code":"TR","type":"education","lineage":["https://openalex.org/I132286405"]}],"countries":["TR"],"is_corresponding":true,"raw_author_name":"Huseyin Fuat Alsan","raw_affiliation_strings":["Kadir Has University,Department of Computer Engineering,Istanbul,Turkey"],"affiliations":[{"raw_affiliation_string":"Kadir Has University,Department of Computer Engineering,Istanbul,Turkey","institution_ids":["https://openalex.org/I132286405"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072069981","display_name":"Ekrem Yildiz","orcid":"https://orcid.org/0000-0003-2233-6974"},"institutions":[{"id":"https://openalex.org/I132286405","display_name":"Kadir Has University","ror":"https://ror.org/03zzckc47","country_code":"TR","type":"education","lineage":["https://openalex.org/I132286405"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Ekrem Yildiz","raw_affiliation_strings":["Kadir Has University,Department of Computer Engineering,Istanbul,Turkey"],"affiliations":[{"raw_affiliation_string":"Kadir Has University,Department of Computer Engineering,Istanbul,Turkey","institution_ids":["https://openalex.org/I132286405"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076968026","display_name":"Ege Burak Safdil","orcid":null},"institutions":[{"id":"https://openalex.org/I132286405","display_name":"Kadir Has University","ror":"https://ror.org/03zzckc47","country_code":"TR","type":"education","lineage":["https://openalex.org/I132286405"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Ege Burak Safdil","raw_affiliation_strings":["Kadir Has University,Department of Computer Engineering,Istanbul,Turkey"],"affiliations":[{"raw_affiliation_string":"Kadir Has University,Department of Computer Engineering,Istanbul,Turkey","institution_ids":["https://openalex.org/I132286405"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031428118","display_name":"Furkan Arslan","orcid":null},"institutions":[{"id":"https://openalex.org/I132286405","display_name":"Kadir Has University","ror":"https://ror.org/03zzckc47","country_code":"TR","type":"education","lineage":["https://openalex.org/I132286405"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Furkan Arslan","raw_affiliation_strings":["Kadir Has University,Department of Computer Engineering,Istanbul,Turkey"],"affiliations":[{"raw_affiliation_string":"Kadir Has University,Department of Computer Engineering,Istanbul,Turkey","institution_ids":["https://openalex.org/I132286405"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069572082","display_name":"Taner Arsan","orcid":"https://orcid.org/0000-0002-4453-3218"},"institutions":[{"id":"https://openalex.org/I132286405","display_name":"Kadir Has University","ror":"https://ror.org/03zzckc47","country_code":"TR","type":"education","lineage":["https://openalex.org/I132286405"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Taner Arsan","raw_affiliation_strings":["Kadir Has University,Department of Computer Engineering,Istanbul,Turkey"],"affiliations":[{"raw_affiliation_string":"Kadir Has University,Department of Computer Engineering,Istanbul,Turkey","institution_ids":["https://openalex.org/I132286405"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5049579400"],"corresponding_institution_ids":["https://openalex.org/I132286405"],"apc_list":null,"apc_paid":null,"fwci":0.1971,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.5669483,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9997000098228455,"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":0.994700014591217,"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/computer-science","display_name":"Computer science","score":0.8358445167541504},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7440376877784729},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7110238671302795},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6084232330322266},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.541654109954834},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5139486193656921},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4978783130645752},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4939618706703186},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.4793301820755005},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.4398183226585388},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4376455843448639},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3790661096572876},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3501511812210083}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8358445167541504},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7440376877784729},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7110238671302795},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6084232330322266},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.541654109954834},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5139486193656921},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4978783130645752},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4939618706703186},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.4793301820755005},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.4398183226585388},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4376455843448639},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3790661096572876},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3501511812210083},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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:10.1109/inista52262.2021.9548414","is_oa":false,"landing_page_url":"https://doi.org/10.1109/inista52262.2021.9548414","pdf_url":null,"source":{"id":"https://openalex.org/S4306498847","display_name":"2021 International Conference on INnovations in Intelligent SysTems and Applications (INISTA)","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Conference on INnovations in Intelligent SysTems and Applications (INISTA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1930223417","https://openalex.org/W2497173630","https://openalex.org/W2801271919","https://openalex.org/W2900595477","https://openalex.org/W2920885526","https://openalex.org/W2964325095","https://openalex.org/W2973126236","https://openalex.org/W2995194910","https://openalex.org/W2999634272","https://openalex.org/W3038774312","https://openalex.org/W3137642335","https://openalex.org/W6791922532"],"related_works":["https://openalex.org/W2732415564","https://openalex.org/W4220775285","https://openalex.org/W4306194456","https://openalex.org/W3156786002","https://openalex.org/W2738221750","https://openalex.org/W564581980","https://openalex.org/W3101956722","https://openalex.org/W2732542196","https://openalex.org/W2949266290","https://openalex.org/W4302376911"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,136,149],"present":[4,39],"multimodal":[5,23,29,54,101],"data":[6,55],"retrieval":[7,24,156,169],"aided":[8],"with":[9,28,46,103,157,167],"contrastive":[10,18],"pretraining.":[11],"Our":[12],"approach":[13],"is":[14,72,80,98,127],"to":[15,20,52,59,112,138],"pretrain":[16],"a":[17,40,73,81,108],"network":[19,45,84,111],"assist":[21],"in":[22,146],"tasks.":[25,170],"We":[26,38,106,161],"work":[27],"data,":[30],"which":[31],"has":[32,91],"image":[33,48],"and":[34,49,57,77,94,96,135],"caption":[35],"(text)":[36],"pairs.":[37],"dual":[41,120],"encoder":[42,51,71,79,121],"deep":[43],"neural":[44,83],"the":[47,114,119,133,151],"text":[50,78],"encode":[53],"(images":[56],"text)":[58],"represent":[60],"vectors.":[61],"These":[62],"representation":[63],"vectors":[64],"are":[65],"used":[66,99,107,145],"for":[67,100],"similarity-based":[68],"retrieval.":[69],"Image":[70],"2D":[74],"convolutional":[75,109],"network,":[76],"recurrent":[82],"(Long-Short":[85],"Term":[86],"Memory).":[87],"MS-COCO":[88],"2014":[89],"dataset":[90],"both":[92],"images":[93,117],"captions,":[95],"it":[97],"training":[102,122],"triplet":[104],"loss.":[105],"Siamese":[110,129,141,154,164],"compute":[113],"similarities":[115],"between":[116],"before":[118],"(contrastive":[123],"pretraining).":[124],"The":[125],"advantage":[126],"that":[128,163],"networks":[130,142],"can":[131,143,165],"aid":[132],"retrieval,":[134],"seek":[137],"show":[139],"if":[140],"be":[144],"practice.":[147],"Finally,":[148],"investigated":[150],"performance":[152],"of":[153],"assisted":[155],"BLEU":[158],"score":[159],"metric.":[160],"conclude":[162],"help":[166],"image-to-text":[168]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}