{"id":"https://openalex.org/W2888166343","doi":"https://doi.org/10.1145/3240508.3240712","title":"Webly Supervised Joint Embedding for Cross-Modal Image-Text Retrieval","display_name":"Webly Supervised Joint Embedding for Cross-Modal Image-Text Retrieval","publication_year":2018,"publication_date":"2018-10-15","ids":{"openalex":"https://openalex.org/W2888166343","doi":"https://doi.org/10.1145/3240508.3240712","mag":"2888166343"},"language":"en","primary_location":{"id":"doi:10.1145/3240508.3240712","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3240508.3240712","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3240508.3240712","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM international conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3240508.3240712","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012973327","display_name":"Niluthpol Chowdhury Mithun","orcid":"https://orcid.org/0000-0003-3611-4141"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Niluthpol Chowdhury Mithun","raw_affiliation_strings":["University of California, Riverside, Riverside, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Riverside, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049734237","display_name":"Rameswar Panda","orcid":"https://orcid.org/0000-0003-4359-2475"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rameswar Panda","raw_affiliation_strings":["University of California, Riverside, Riverside, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Riverside, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054849323","display_name":"Evangelos E. Papalexakis","orcid":"https://orcid.org/0000-0002-3411-8483"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Evangelos E. Papalexakis","raw_affiliation_strings":["University of California, Riverside, Riverside, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Riverside, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004732580","display_name":"Amit K. Roy\u2013Chowdhury","orcid":"https://orcid.org/0000-0001-6690-9725"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amit K. Roy-Chowdhury","raw_affiliation_strings":["University of California, Riverside, Riverside, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Riverside, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I103635307"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":81,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1856","last_page":"1864"},"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":0.9983999729156494,"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":0.9983999729156494,"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":0.8443496227264404},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6757850646972656},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6490797996520996},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.5687580704689026},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.5186178088188171},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.47724032402038574},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4765344560146332},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4559186100959778},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4437781572341919},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.41962751746177673},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40357857942581177},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40284353494644165},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.35499995946884155},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3238535523414612}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8443496227264404},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6757850646972656},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6490797996520996},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.5687580704689026},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.5186178088188171},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.47724032402038574},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4765344560146332},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4559186100959778},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4437781572341919},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.41962751746177673},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40357857942581177},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40284353494644165},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.35499995946884155},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3238535523414612},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3240508.3240712","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3240508.3240712","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3240508.3240712","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM international conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3240508.3240712","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3240508.3240712","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3240508.3240712","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM international conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7599999904632568,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1824974782","display_name":"CPS: Synergy: Collaborative Research: Extracting Time-Critical Situational Awareness from Resource Constrained Networks","funder_award_id":"1544969","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2619233807","display_name":null,"funder_award_id":"IIS-1746031, CNS-1544969","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3619066000","display_name":"EAGER: Joint Modeling and Querying of Social Media and Video Data","funder_award_id":"1746031","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3755745404","display_name":null,"funder_award_id":"IIS-1746031","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3905886410","display_name":null,"funder_award_id":"CNS-1544969","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2888166343.pdf","grobid_xml":"https://content.openalex.org/works/W2888166343.grobid-xml"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W92662927","https://openalex.org/W1527575280","https://openalex.org/W1591825359","https://openalex.org/W1686810756","https://openalex.org/W1773149199","https://openalex.org/W1852255964","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W1924770834","https://openalex.org/W1949478088","https://openalex.org/W1957706851","https://openalex.org/W2028742638","https://openalex.org/W2031342017","https://openalex.org/W2033740597","https://openalex.org/W2062955551","https://openalex.org/W2067562626","https://openalex.org/W2070753207","https://openalex.org/W2096733369","https://openalex.org/W2112912048","https://openalex.org/W2126942721","https://openalex.org/W2155803963","https://openalex.org/W2172888184","https://openalex.org/W2194775991","https://openalex.org/W2287418003","https://openalex.org/W2296073425","https://openalex.org/W2406012631","https://openalex.org/W2526851297","https://openalex.org/W2552579943","https://openalex.org/W2558358930","https://openalex.org/W2592170186","https://openalex.org/W2606473278","https://openalex.org/W2613031639","https://openalex.org/W2618264341","https://openalex.org/W2739181657","https://openalex.org/W2742318416","https://openalex.org/W2743151379","https://openalex.org/W2765262252","https://openalex.org/W2765619745","https://openalex.org/W2808399042","https://openalex.org/W2950577311","https://openalex.org/W2962787423","https://openalex.org/W2963040148","https://openalex.org/W2963502184","https://openalex.org/W3000226596","https://openalex.org/W3099206234","https://openalex.org/W3101854735","https://openalex.org/W3103081334","https://openalex.org/W4241307704"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W4295532600","https://openalex.org/W2063823869","https://openalex.org/W2047973478","https://openalex.org/W2067569035","https://openalex.org/W2090985514","https://openalex.org/W2037549926","https://openalex.org/W2345479200","https://openalex.org/W2183306018","https://openalex.org/W2849310602"],"abstract_inverted_index":{"Cross-modal":[0],"retrieval":[1,18,177],"between":[2],"visual":[3],"data":[4],"and":[5,70,114],"natural":[6],"language":[7],"description":[8],"remains":[9],"a":[10,45,60,74,132,141,155,171],"long-standing":[11],"challenge":[12],"in":[13,86,122,175],"multimedia.":[14],"While":[15],"recent":[16,80],"image-text":[17,102,176],"methods":[19,33],"oer":[20],"great":[21],"promise":[22],"by":[23,36,63,78],"learning":[24,85,125],"deep":[25,87],"representations":[26],"aligned":[27],"across":[28],"modalities,":[29],"most":[30],"of":[31,39,48,66,82],"these":[32],"are":[34],"plagued":[35],"the":[37,79,126,136],"issue":[38],"training":[40,123],"with":[41,50,68,96,118,149],"small-scale":[42],"datasets":[43,165],"covering":[44],"limited":[46],"number":[47],"images":[49,67,95,113,152],"ground-truth":[51],"sentences.":[52],"Moreover,":[53],"it":[54],"is":[55,109],"extremely":[56],"expensive":[57],"to":[58,73,99,110,153,179],"create":[59],"larger":[61],"dataset":[62],"annotating":[64],"millions":[65],"sentences":[69],"may":[71],"lead":[72],"biased":[75],"model.":[76],"Inspired":[77],"success":[81],"webly":[83],"supervised":[84,143],"neural":[88],"networks,":[89],"we":[90],"capitalize":[91],"on":[92,161],"readily-available":[93],"web":[94,112,151],"noisy":[97],"annotations":[98],"learn":[100,154],"robust":[101,157],"joint":[103,128],"representation.":[104],"Specically,":[105],"our":[106,168],"main":[107],"idea":[108],"leverage":[111],"corresponding":[115],"tags,":[116],"along":[117],"fully":[119],"annotated":[120],"datasets,":[121],"for":[124,135],"visual-semantic":[127,158],"embedding.":[129,159],"We":[130],"propose":[131],"twostage":[133],"approach":[134],"task":[137],"that":[138,167],"can":[139],"augment":[140],"typical":[142],"pair-wise":[144],"ranking":[145],"loss":[146],"based":[147],"formulation":[148],"weakly-annotated":[150],"more":[156],"Experiments":[160],"two":[162],"standard":[163],"benchmark":[164],"demonstrate":[166],"method":[169],"achieves":[170],"signicant":[172],"performance":[173],"gain":[174],"compared":[178],"state-of-the-art":[180],"approaches.":[181]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":19},{"year":2020,"cited_by_count":22},{"year":2019,"cited_by_count":11}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}