{"id":"https://openalex.org/W3174380564","doi":"https://doi.org/10.1145/3460426.3463587","title":"Learning to Select","display_name":"Learning to Select","publication_year":2021,"publication_date":"2021-08-24","ids":{"openalex":"https://openalex.org/W3174380564","doi":"https://doi.org/10.1145/3460426.3463587","mag":"3174380564"},"language":"en","primary_location":{"id":"doi:10.1145/3460426.3463587","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3460426.3463587","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"preprint","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/A5087066850","display_name":"Marco Cagrandi","orcid":null},"institutions":[{"id":"https://openalex.org/I122346577","display_name":"University of Modena and Reggio Emilia","ror":"https://ror.org/02d4c4y02","country_code":"IT","type":"education","lineage":["https://openalex.org/I122346577"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Marco Cagrandi","raw_affiliation_strings":["University of Modena and Reggio Emilia, Modena, Italy"],"affiliations":[{"raw_affiliation_string":"University of Modena and Reggio Emilia, Modena, Italy","institution_ids":["https://openalex.org/I122346577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066519737","display_name":"Marcella Cornia","orcid":"https://orcid.org/0000-0001-9640-9385"},"institutions":[{"id":"https://openalex.org/I122346577","display_name":"University of Modena and Reggio Emilia","ror":"https://ror.org/02d4c4y02","country_code":"IT","type":"education","lineage":["https://openalex.org/I122346577"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Marcella Cornia","raw_affiliation_strings":["University of Modena and Reggio Emilia, Modena, Italy"],"affiliations":[{"raw_affiliation_string":"University of Modena and Reggio Emilia, Modena, Italy","institution_ids":["https://openalex.org/I122346577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016738355","display_name":"Matteo Stefanini","orcid":"https://orcid.org/0000-0001-6153-926X"},"institutions":[{"id":"https://openalex.org/I122346577","display_name":"University of Modena and Reggio Emilia","ror":"https://ror.org/02d4c4y02","country_code":"IT","type":"education","lineage":["https://openalex.org/I122346577"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Matteo Stefanini","raw_affiliation_strings":["University of Modena and Reggio Emilia, Modena, Italy"],"affiliations":[{"raw_affiliation_string":"University of Modena and Reggio Emilia, Modena, Italy","institution_ids":["https://openalex.org/I122346577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048928616","display_name":"Lorenzo Baraldi","orcid":"https://orcid.org/0000-0001-5125-4957"},"institutions":[{"id":"https://openalex.org/I122346577","display_name":"University of Modena and Reggio Emilia","ror":"https://ror.org/02d4c4y02","country_code":"IT","type":"education","lineage":["https://openalex.org/I122346577"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Lorenzo Baraldi","raw_affiliation_strings":["University of Modena and Reggio Emilia, Modena, Italy"],"affiliations":[{"raw_affiliation_string":"University of Modena and Reggio Emilia, Modena, Italy","institution_ids":["https://openalex.org/I122346577"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030948871","display_name":"Rita Cucchiara","orcid":"https://orcid.org/0000-0002-2239-283X"},"institutions":[{"id":"https://openalex.org/I122346577","display_name":"University of Modena and Reggio Emilia","ror":"https://ror.org/02d4c4y02","country_code":"IT","type":"education","lineage":["https://openalex.org/I122346577"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Rita Cucchiara","raw_affiliation_strings":["University of Modena and Reggio Emilia, Modena, Italy"],"affiliations":[{"raw_affiliation_string":"University of Modena and Reggio Emilia, Modena, Italy","institution_ids":["https://openalex.org/I122346577"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5087066850"],"corresponding_institution_ids":["https://openalex.org/I122346577"],"apc_list":null,"apc_paid":null,"fwci":0.81775583,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.73358003,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"437","last_page":"441"},"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":0.9936000108718872,"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":0.9923999905586243,"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/closed-captioning","display_name":"Closed captioning","score":0.9729232788085938},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8425232172012329},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.6740125417709351},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6205010414123535},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.6176000237464905},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6139257550239563},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.578654408454895},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5651733875274658},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.48871874809265137},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4819502532482147},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4164721369743347},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4110095202922821},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3880809545516968},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1167900562286377}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9729232788085938},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8425232172012329},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.6740125417709351},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6205010414123535},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.6176000237464905},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6139257550239563},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.578654408454895},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5651733875274658},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.48871874809265137},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4819502532482147},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4164721369743347},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4110095202922821},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3880809545516968},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1167900562286377},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3460426.3463587","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3460426.3463587","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320323988","display_name":"Ministero degli Affari Esteri e della Cooperazione Internazionale","ror":"https://ror.org/02jkm3388"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1522301498","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2119168550","https://openalex.org/W2123301721","https://openalex.org/W2154652894","https://openalex.org/W2173180041","https://openalex.org/W2185175083","https://openalex.org/W2250539671","https://openalex.org/W2277195237","https://openalex.org/W2506483933","https://openalex.org/W2745461083","https://openalex.org/W2751076261","https://openalex.org/W2795151422","https://openalex.org/W2797733588","https://openalex.org/W2890531016","https://openalex.org/W2904565150","https://openalex.org/W2954598292","https://openalex.org/W2962982762","https://openalex.org/W2963088515","https://openalex.org/W2963101956","https://openalex.org/W2963175879","https://openalex.org/W2963403868","https://openalex.org/W2963877622","https://openalex.org/W2964029788","https://openalex.org/W2979747405","https://openalex.org/W2986670728","https://openalex.org/W2989596775","https://openalex.org/W3034655362","https://openalex.org/W3035284526","https://openalex.org/W3043501111","https://openalex.org/W3083505552","https://openalex.org/W3088493063","https://openalex.org/W3091177855","https://openalex.org/W3091588028","https://openalex.org/W3100115227","https://openalex.org/W3104279398","https://openalex.org/W3174377922","https://openalex.org/W4288329833","https://openalex.org/W4289542422","https://openalex.org/W4293501525","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393"],"abstract_inverted_index":{"Image":[0],"captioning":[1,42,52],"models":[2,53],"have":[3],"lately":[4],"shown":[5],"impressive":[6],"results":[7],"when":[8,111],"applied":[9],"to":[10,14,22,50,75,88,93,137],"standard":[11],"datasets.":[12],"Switching":[13],"real-life":[15],"scenarios,":[16],"however,":[17],"constitutes":[18],"a":[19,48,68,99],"challenge":[20],"due":[21],"the":[23,60,77,89,95,118,127,130],"larger":[24],"variety":[25],"of":[26,81,85,98,129,135],"visual":[27],"concepts":[28],"which":[29,56],"are":[30,57],"not":[31],"covered":[32],"in":[33,133],"existing":[34],"training":[35,61,90],"sets.":[36],"For":[37],"this":[38,64],"reason,":[39],"novel":[40,69,138],"object":[41],"(NOC)":[43],"has":[44],"recently":[45],"emerged":[46],"as":[47],"paradigm":[49],"test":[51],"on":[54,117],"objects":[55,80,139],"unseen":[58],"during":[59],"phase.":[62],"In":[63],"paper,":[65],"we":[66,123],"present":[67],"approach":[70],"for":[71],"NOC":[72],"that":[73],"learns":[74],"select":[76],"most":[78],"relevant":[79],"an":[82],"image,":[83],"regardless":[84],"their":[86],"adherence":[87],"set,":[91],"and":[92,107,140],"constrain":[94],"generative":[96],"process":[97],"language":[100],"model":[101],"accordingly.":[102],"Our":[103],"architecture":[104],"is":[105],"fully-attentive":[106],"end-to-end":[108],"trainable,":[109],"also":[110],"incorporating":[112],"constraints.":[113],"We":[114],"perform":[115],"experiments":[116],"held-out":[119],"COCO":[120],"dataset,":[121],"where":[122],"demonstrate":[124],"improvements":[125],"over":[126],"state":[128],"art,":[131],"both":[132],"terms":[134],"adaptability":[136],"caption":[141],"quality.":[142]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2021-07-05T00:00:00"}