{"id":"https://openalex.org/W2972884859","doi":"https://doi.org/10.18653/v1/k19-1009","title":"Compositional Generalization in Image Captioning","display_name":"Compositional Generalization in Image Captioning","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2972884859","doi":"https://doi.org/10.18653/v1/k19-1009","mag":"2972884859"},"language":"en","primary_location":{"id":"doi:10.18653/v1/k19-1009","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/k19-1009","pdf_url":"https://www.aclweb.org/anthology/K19-1009.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/K19-1009.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Mitja Nikolaus","orcid":null},"institutions":[{"id":"https://openalex.org/I8087733","display_name":"University of T\u00fcbingen","ror":"https://ror.org/03a1kwz48","country_code":"DE","type":"education","lineage":["https://openalex.org/I8087733"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Mitja Nikolaus","raw_affiliation_strings":["University of Tbingen"],"affiliations":[{"raw_affiliation_string":"University of Tbingen","institution_ids":["https://openalex.org/I8087733"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Mostafa Abdou","orcid":null},"institutions":[{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Mostafa Abdou","raw_affiliation_strings":["University of Copenhagen"],"affiliations":[{"raw_affiliation_string":"University of Copenhagen","institution_ids":["https://openalex.org/I124055696"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Matthew Lamm","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew Lamm","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Rahul Aralikatte","orcid":null},"institutions":[{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Rahul Aralikatte","raw_affiliation_strings":["University of Copenhagen"],"affiliations":[{"raw_affiliation_string":"University of Copenhagen","institution_ids":["https://openalex.org/I124055696"]}]},{"author_position":"last","author":{"id":null,"display_name":"Desmond Elliott","orcid":null},"institutions":[{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Desmond Elliott","raw_affiliation_strings":["University of Copenhagen"],"affiliations":[{"raw_affiliation_string":"University of Copenhagen","institution_ids":["https://openalex.org/I124055696"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I8087733"],"apc_list":null,"apc_paid":null,"fwci":0.9196,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.79495692,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"87","last_page":"98"},"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":0.9937999844551086,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9886000156402588,"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":0.9905999898910522},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.8274000287055969},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6263999938964844},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.6183000206947327},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5992000102996826},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5741000175476074},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3379000127315521}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9905999898910522},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.8274000287055969},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6983000040054321},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6263999938964844},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.621399998664856},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6183000206947327},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5992000102996826},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5741000175476074},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.420199990272522},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3379000127315521},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3199999928474426},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.299699991941452},{"id":"https://openalex.org/C143271835","wikidata":"https://www.wikidata.org/wiki/Q254515","display_name":"Similitude","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C45493050","wikidata":"https://www.wikidata.org/wiki/Q7884934","display_name":"Unified Model","level":2,"score":0.28060001134872437},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.25690001249313354}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/k19-1009","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/k19-1009","pdf_url":"https://www.aclweb.org/anthology/K19-1009.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1909.04402","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1909.04402","pdf_url":"https://arxiv.org/pdf/1909.04402","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/2f18fd29-4bcb-4b66-b1fa-9decac2c8b6c","is_oa":true,"landing_page_url":"https://curis.ku.dk/portal/da/publications/compositional-generalization-in-image-captioning(2f18fd29-4bcb-4b66-b1fa-9decac2c8b6c).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306401983","display_name":"Research at the University of Copenhagen (University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I124055696","host_organization_name":"University of Copenhagen","host_organization_lineage":["https://openalex.org/I124055696"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Nikolaus , M , Abdou , M , Lamm , M , Aralikatte , R & Elliott , D 2019 , Compositional Generalization in Image Captioning . in Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL) . Association for Computational Linguistics , pp. 87-98 , 23rd Conference on Computational Natural Language Learning , Hong Kong , China , 03/11/2019 . https://doi.org/10.18653/v1/K19-1009","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.atira.dk:publications/2f18fd29-4bcb-4b66-b1fa-9decac2c8b6c","is_oa":true,"landing_page_url":"https://researchprofiles.ku.dk/da/publications/2f18fd29-4bcb-4b66-b1fa-9decac2c8b6c","pdf_url":null,"source":{"id":"https://openalex.org/S4306401983","display_name":"Research at the University of Copenhagen (University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I124055696","host_organization_name":"University of Copenhagen","host_organization_lineage":["https://openalex.org/I124055696"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Nikolaus , M , Abdou , M , Lamm , M , Aralikatte , R & Elliott , D 2019 , Compositional Generalization in Image Captioning . in Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL) . Association for Computational Linguistics , pp. 87-98 , 23rd Conference on Computational Natural Language Learning , Hong Kong , China , 03/11/2019 . https://doi.org/10.18653/v1/K19-1009","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"doi:10.18653/v1/k19-1009","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/k19-1009","pdf_url":"https://www.aclweb.org/anthology/K19-1009.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320328306","display_name":"Lorentz Center","ror":"https://ror.org/00d503m77"},{"id":"https://openalex.org/F4320335551","display_name":"Erasmus+","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2972884859.pdf","grobid_xml":"https://content.openalex.org/works/W2972884859.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Image":[0],"captioning":[1,48,104],"models":[2,49],"are":[3],"usually":[4],"evaluated":[5],"on":[6,17,54],"their":[7,18,84],"ability":[8,19],"to":[9,20,22,62,86,96,102],"describe":[10],"a":[11,36,59,76],"held-out":[12],"set":[13],"of":[14,29,41,99],"images,":[15],"not":[16],"generalize":[21],"unseen":[23,39,97],"concepts.":[24],"We":[25,57],"study":[26],"the":[27,64,81,87],"problem":[28],"compositional":[30],"generalization,":[31],"which":[32],"measures":[33],"how":[34],"well":[35],"model":[37,61,90],"composes":[38],"combinations":[40,98],"concepts":[42,100],"when":[43],"describing":[44],"images.":[45],"Stateof-the-art":[46],"image":[47],"show":[50],"poor":[51,65],"generalization":[52],"performance":[53],"this":[55],"task.":[56],"propose":[58],"multi-task":[60],"address":[63],"performance,":[66],"that":[67,79],"combines":[68],"caption":[69],"generation":[70],"and":[71,74],"image-sentence":[72],"ranking,":[73],"uses":[75],"decoding":[77],"mechanism":[78],"re-ranks":[80],"captions":[82],"according":[83],"similarity":[85],"image.":[88],"This":[89],"is":[91],"substantially":[92],"better":[93],"at":[94],"generalizing":[95],"compared":[101],"state-of-the-art":[103],"models.":[105]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2019-09-19T00:00:00"}