{"id":"https://openalex.org/W3139017368","doi":"https://doi.org/10.1162/tacl_a_00473","title":"Retrieve Fast, Rerank Smart: Cooperative and Joint Approaches for Improved Cross-Modal Retrieval","display_name":"Retrieve Fast, Rerank Smart: Cooperative and Joint Approaches for Improved Cross-Modal Retrieval","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W3139017368","doi":"https://doi.org/10.1162/tacl_a_00473","mag":"3139017368"},"language":"en","primary_location":{"id":"doi:10.1162/tacl_a_00473","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00473","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00473/2020706/tacl_a_00473.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00473/2020706/tacl_a_00473.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018004671","display_name":"Gregor Geigle","orcid":null},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Gregor Geigle","raw_affiliation_strings":["Ubiquitous Knowledge Processing Lab, Technical University of Darmstadt, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ubiquitous Knowledge Processing Lab, Technical University of Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024983536","display_name":"Jonas Pfeiffer","orcid":"https://orcid.org/0000-0002-8634-6170"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jonas Pfeiffer","raw_affiliation_strings":["Ubiquitous Knowledge Processing Lab, Technical University of Darmstadt, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ubiquitous Knowledge Processing Lab, Technical University of Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110592354","display_name":"Nils Reimers","orcid":null},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Nils Reimers","raw_affiliation_strings":["Ubiquitous Knowledge Processing Lab, Technical University of Darmstadt, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ubiquitous Knowledge Processing Lab, Technical University of Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014866912","display_name":"Ivan Vuli\u0107","orcid":"https://orcid.org/0000-0002-5161-5422"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ivan Vuli\u0107","raw_affiliation_strings":["Language Technology Lab, University of Cambridge, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technology Lab, University of Cambridge, United Kingdom","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027450194","display_name":"Iryna Gurevych","orcid":"https://orcid.org/0000-0003-2187-7621"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Iryna Gurevych","raw_affiliation_strings":["Ubiquitous Knowledge Processing Lab, Technical University of Darmstadt, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ubiquitous Knowledge Processing Lab, Technical University of Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5018004671"],"corresponding_institution_ids":["https://openalex.org/I31512782"],"apc_list":null,"apc_paid":null,"fwci":4.2622,"has_fulltext":false,"cited_by_count":50,"citation_normalized_percentile":{"value":0.95397497,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"10","issue":null,"first_page":"503","last_page":"521"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9991999864578247,"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"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9991000294685364,"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/computer-science","display_name":"Computer science","score":0.8968960046768188},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6429521441459656},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.550231397151947},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.47793203592300415},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4659745395183563},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40063899755477905}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8968960046768188},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6429521441459656},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.550231397151947},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.47793203592300415},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4659745395183563},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40063899755477905},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1162/tacl_a_00473","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00473","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00473/2020706/tacl_a_00473.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:4d498fb3b1c94145816b84a16b808d1a","is_oa":false,"landing_page_url":"https://doaj.org/article/4d498fb3b1c94145816b84a16b808d1a","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Transactions of the Association for Computational Linguistics, Vol 10 (2022)","raw_type":"article"},{"id":"pmh:oai:tubiblio.ulb.tu-darmstadt.de:129902","is_oa":true,"landing_page_url":"https://transacl.org/ojs/index.php/tacl/article/view/3383","pdf_url":null,"source":{"id":"https://openalex.org/S4377196390","display_name":"TUbilio (Technical University of Darmstadt)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I31512782","host_organization_name":"Technische Universit\u00e4t Darmstadt","host_organization_lineage":["https://openalex.org/I31512782"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Artikel"}],"best_oa_location":{"id":"doi:10.1162/tacl_a_00473","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00473","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00473/2020706/tacl_a_00473.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":95,"referenced_works":["https://openalex.org/W17346433","https://openalex.org/W1532499126","https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W1979065383","https://openalex.org/W2038276547","https://openalex.org/W2088101210","https://openalex.org/W2100799972","https://openalex.org/W2109586012","https://openalex.org/W2297545632","https://openalex.org/W2345720230","https://openalex.org/W2427881153","https://openalex.org/W2598634450","https://openalex.org/W2606473278","https://openalex.org/W2613718673","https://openalex.org/W2745461083","https://openalex.org/W2883311563","https://openalex.org/W2886198413","https://openalex.org/W2886641317","https://openalex.org/W2890907172","https://openalex.org/W2903343986","https://openalex.org/W2912817604","https://openalex.org/W2948110372","https://openalex.org/W2951535825","https://openalex.org/W2951590222","https://openalex.org/W2952267213","https://openalex.org/W2962964995","https://openalex.org/W2963149412","https://openalex.org/W2963331233","https://openalex.org/W2963496089","https://openalex.org/W2963909453","https://openalex.org/W2964727037","https://openalex.org/W2965848243","https://openalex.org/W2966715458","https://openalex.org/W2969876226","https://openalex.org/W2970231061","https://openalex.org/W2970618241","https://openalex.org/W2970641574","https://openalex.org/W2976163105","https://openalex.org/W2982596739","https://openalex.org/W2983040767","https://openalex.org/W2991118492","https://openalex.org/W2993633640","https://openalex.org/W2997786945","https://openalex.org/W2998356391","https://openalex.org/W2998702515","https://openalex.org/W3029678209","https://openalex.org/W3034837085","https://openalex.org/W3035390927","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3092302355","https://openalex.org/W3092683697","https://openalex.org/W3093742767","https://openalex.org/W3097619042","https://openalex.org/W3099700870","https://openalex.org/W3104078590","https://openalex.org/W3121694563","https://openalex.org/W3144596436","https://openalex.org/W3164904666","https://openalex.org/W3177743683","https://openalex.org/W3184735396","https://openalex.org/W3201264086","https://openalex.org/W4287122359","https://openalex.org/W4287645694","https://openalex.org/W4299574851","https://openalex.org/W4300427681","https://openalex.org/W6600697508","https://openalex.org/W6620707391","https://openalex.org/W6676497082","https://openalex.org/W6678470764","https://openalex.org/W6684723771","https://openalex.org/W6729399837","https://openalex.org/W6735531217","https://openalex.org/W6739901393","https://openalex.org/W6747225742","https://openalex.org/W6755207826","https://openalex.org/W6757817989","https://openalex.org/W6758015726","https://openalex.org/W6762832483","https://openalex.org/W6766446443","https://openalex.org/W6769185743","https://openalex.org/W6771430711","https://openalex.org/W6779412326","https://openalex.org/W6779473860","https://openalex.org/W6779872132","https://openalex.org/W6779941907","https://openalex.org/W6784207961","https://openalex.org/W6786707460","https://openalex.org/W6788120775","https://openalex.org/W6790019176","https://openalex.org/W6791353385","https://openalex.org/W6795887067","https://openalex.org/W6798068716","https://openalex.org/W6798805250"],"related_works":["https://openalex.org/W2364921833","https://openalex.org/W2275988210","https://openalex.org/W2302028273","https://openalex.org/W1525643724","https://openalex.org/W2067938758","https://openalex.org/W2382623646","https://openalex.org/W3087771547","https://openalex.org/W2333420780","https://openalex.org/W2375199418","https://openalex.org/W2368437561"],"abstract_inverted_index":{"Abstract":[0],"Current":[1],"state-of-the-art":[2,186],"approaches":[3],"to":[4,112,146],"cross-":[5,74,187],"modal":[6,75],"retrieval":[7,34,52,93,169],"process":[8],"text":[9],"and":[10,26,44,54,72,124,174,180],"visual":[11],"input":[12],"jointly,":[13],"relying":[14],"on":[15,99,163],"Transformer-based":[16],"architectures":[17],"with":[18,153],"cross-attention":[19],"mechanisms":[20],"that":[21,83,104],"attend":[22],"over":[23,184],"all":[24,115],"words":[25],"objects":[27],"in":[28,61,171],"an":[29,91],"image.":[30],"While":[31],"offering":[32],"unmatched":[33],"performance,":[35],"such":[36],"models:":[37],"1)":[38,106],"are":[39],"typically":[40],"pretrained":[41,86],"from":[42,50],"scratch":[43],"thus":[45],"less":[46],"scalable,":[47],"2)":[48,125],"suffer":[49],"huge":[51,181],"latency":[53],"inefficiency":[55],"issues,":[56],"which":[57],"makes":[58],"them":[59],"impractical":[60],"realistic":[62],"applications.":[63],"To":[64],"address":[65],"these":[66],"crucial":[67],"gaps":[68],"towards":[69],"both":[70],"improved":[71,178],"efficient":[73,92,121],"retrieval,":[76,123],"we":[77],"propose":[78,145],"a":[79,100,110,118,126,130,157,164],"novel":[80],"fine-tuning":[81],"framework":[82,96],"turns":[84],"any":[85],"text-image":[87],"multi-modal":[88],"model":[89],"into":[90],"model.":[94,160],"The":[95],"is":[97],"based":[98],"cooperative":[101],"retrieve-and-rerank":[102],"approach":[103],"combines:":[105],"twin":[107],"networks":[108],"(i.e.,":[109,133],"bi-encoder)":[111],"separately":[113],"encode":[114],"items":[116],"of":[117,136,141,166],"corpus,":[119],"enabling":[120],"initial":[122],"cross-encoder":[127],"component":[128],"for":[129],"more":[131,158],"nuanced":[132],"smarter)":[134],"ranking":[135],"the":[137,150,185],"retrieved":[138],"small":[139],"set":[140],"items.":[142],"We":[143],"also":[144],"jointly":[147],"fine-":[148],"tune":[149],"two":[151],"components":[152],"shared":[154],"weights,":[155],"yielding":[156],"parameter-efficient":[159],"Our":[161],"experiments":[162],"series":[165],"standard":[167],"cross-modal":[168],"benchmarks":[170],"monolingual,":[172],"multilingual,":[173],"zero-shot":[175],"setups,":[176],"demonstrate":[177],"accuracy":[179],"efficiency":[182],"benefits":[183],"encoders.1":[188]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":6}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}