{"id":"https://openalex.org/W2969295463","doi":"https://doi.org/10.1109/iccv.2019.00751","title":"Towards Unsupervised Image Captioning With Shared Multimodal Embeddings","display_name":"Towards Unsupervised Image Captioning With Shared Multimodal Embeddings","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W2969295463","doi":"https://doi.org/10.1109/iccv.2019.00751","mag":"2969295463"},"language":"en","primary_location":{"id":"doi:10.1109/iccv.2019.00751","doi":"https://doi.org/10.1109/iccv.2019.00751","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv.2019.00751","pdf_url":null,"source":{"id":"https://openalex.org/S4363607764","display_name":"IEEE/CVF International Conference on Computer Vision (ICCV)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1908.09317","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062808708","display_name":"Iro Laina","orcid":"https://orcid.org/0000-0001-8857-7709","observed_orcids":["https://orcid.org/0000-0001-8857-7709"]},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Iro Laina","raw_affiliation_strings":["Technische Universit\u00e4t M\u00fcnchen","Technical University of Munich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t M\u00fcnchen","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Technical University of Munich","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083153177","display_name":"Christian Rupprecht","orcid":"https://orcid.org/0000-0003-3994-8045","observed_orcids":["https://orcid.org/0000-0003-3994-8045"]},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Christian Rupprecht","raw_affiliation_strings":["University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046896448","display_name":"Nassir Navab","orcid":"https://orcid.org/0000-0002-6032-5611","observed_orcids":["https://orcid.org/0000-0002-6032-5611"]},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Nassir Navab","raw_affiliation_strings":["Technische Universit\u00e4t M\u00fcnchen","Technical University of Munich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t M\u00fcnchen","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Technical University of Munich","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.0415,"has_fulltext":true,"cited_by_count":107,"citation_normalized_percentile":{"value":0.9530904,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"7413","last_page":"7423"},"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.0,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/visual-concepts","display_name":"visual concepts","score":0.6669999957084656},{"id":"https://openalex.org/keywords/domain-alignment","display_name":"domain alignment","score":0.625},{"id":"https://openalex.org/keywords/sentence-embeddings","display_name":"sentence embeddings","score":0.5649999976158142},{"id":"https://openalex.org/keywords/language-models","display_name":"language models","score":0.37700000405311584},{"id":"https://openalex.org/keywords/cross-modal-translation","display_name":"cross-modal translation","score":0.4740000069141388}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9234681129455566},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8214774131774902},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7087687849998474},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6668206453323364},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6588805913925171},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5976691246032715},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5366665124893188},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4835081398487091},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.46996089816093445},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.46788376569747925},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4590761363506317},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.4435959458351135},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.42035722732543945},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32924240827560425},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07347020506858826},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/iccv.2019.00751","doi":"https://doi.org/10.1109/iccv.2019.00751","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv.2019.00751","pdf_url":null,"source":{"id":"https://openalex.org/S4363607764","display_name":"IEEE/CVF International Conference on Computer Vision (ICCV)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1908.09317","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1908.09317","pdf_url":"https://arxiv.org/pdf/1908.09317","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"mag:2969295463","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1908.09317","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1908.09317","doi":"https://doi.org/10.48550/arxiv.1908.09317","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1908.09317","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1908.09317","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1908.09317","pdf_url":"https://arxiv.org/pdf/1908.09317","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G6409975174","display_name":"Integrated and Detailed Image Understanding","funder_award_id":"638009","funder_id":"https://openalex.org/F4320338335","funder_display_name":"H2020 European Research Council"}],"funders":[{"id":"https://openalex.org/F4320338335","display_name":"H2020 European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2969295463.pdf","grobid_xml":"https://content.openalex.org/works/W2969295463.grobid-xml"},"referenced_works_count":78,"referenced_works":["https://openalex.org/W658020064","https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1527575280","https://openalex.org/W1573040851","https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1931639407","https://openalex.org/W1933349210","https://openalex.org/W1947481528","https://openalex.org/W1956340063","https://openalex.org/W2117539524","https://openalex.org/W2123442489","https://openalex.org/W2130942839","https://openalex.org/W2133459682","https://openalex.org/W2139380585","https://openalex.org/W2154652894","https://openalex.org/W2157331557","https://openalex.org/W2173180041","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2277195237","https://openalex.org/W2302086703","https://openalex.org/W2412320034","https://openalex.org/W2463508871","https://openalex.org/W2506483933","https://openalex.org/W2544271936","https://openalex.org/W2552161745","https://openalex.org/W2557728737","https://openalex.org/W2560207749","https://openalex.org/W2560313346","https://openalex.org/W2575842049","https://openalex.org/W2588822708","https://openalex.org/W2604178507","https://openalex.org/W2605135824","https://openalex.org/W2620761940","https://openalex.org/W2625940279","https://openalex.org/W2745461083","https://openalex.org/W2765961751","https://openalex.org/W2767577934","https://openalex.org/W2768661419","https://openalex.org/W2774267535","https://openalex.org/W2788643321","https://openalex.org/W2794583223","https://openalex.org/W2795151422","https://openalex.org/W2807725536","https://openalex.org/W2808503835","https://openalex.org/W2886641317","https://openalex.org/W2890531016","https://openalex.org/W2891521313","https://openalex.org/W2891641674","https://openalex.org/W2898609520","https://openalex.org/W2949376505","https://openalex.org/W2950635152","https://openalex.org/W2951183276","https://openalex.org/W2955956881","https://openalex.org/W2962793481","https://openalex.org/W2962849532","https://openalex.org/W2962879692","https://openalex.org/W2962968835","https://openalex.org/W2963048642","https://openalex.org/W2963175879","https://openalex.org/W2963206679","https://openalex.org/W2963267809","https://openalex.org/W2963349562","https://openalex.org/W2963499204","https://openalex.org/W2963594498","https://openalex.org/W2963602293","https://openalex.org/W2963743213","https://openalex.org/W2963758027","https://openalex.org/W2963992143","https://openalex.org/W2964121744","https://openalex.org/W3195066681","https://openalex.org/W4249013746","https://openalex.org/W4288083516"],"related_works":["https://openalex.org/W2963743213","https://openalex.org/W4386554289","https://openalex.org/W2706870434","https://openalex.org/W7123718623","https://openalex.org/W2992478697","https://openalex.org/W3089515120","https://openalex.org/W2512219048","https://openalex.org/W4386074179","https://openalex.org/W3093374703","https://openalex.org/W7160410132"],"abstract_inverted_index":{"Understanding":[0],"images":[1,32,105],"without":[2,26],"explicit":[3],"supervision":[4],"has":[5],"become":[6],"an":[7],"important":[8],"problem":[9],"in":[10],"computer":[11],"vision.":[12],"In":[13,53],"this":[14,54,81],"paper,":[15],"we":[16],"address":[17],"image":[18],"captioning":[19],"by":[20,50],"generating":[21],"language":[22,63,92],"descriptions":[23,88],"of":[24,31,39,132],"scenes":[25],"learning":[27],"from":[28,102],"annotated":[29,130],"pairs":[30],"and":[33,106,115],"their":[34],"captions.":[35],"The":[36],"core":[37],"component":[38],"our":[40],"approach":[41,121],"is":[42,48,65,100],"a":[43,109,116,144],"shared":[44],"latent":[45],"space":[46,83],"that":[47,77,138],"structured":[49,73],"visual":[51],"concepts.":[52],"space,":[55],"the":[56,90,129,139],"two":[57],"modalities":[58],"should":[59],"be":[60,85],"indistinguishable.":[61],"A":[62],"model":[64],"first":[66],"trained":[67],"to":[68,95,112,123],"encode":[69],"sentences":[70],"into":[71,80,87],"semantically":[72,145],"embeddings.":[74,97],"Image":[75],"features":[76],"are":[78],"translated":[79],"embedding":[82],"can":[84],"decoded":[86],"through":[89],"same":[91],"model,":[93],"similarly":[94],"sentence":[96],"This":[98],"translation":[99],"learned":[101],"weakly":[103],"paired":[104],"text":[107,126],"using":[108],"loss":[110],"robust":[111],"noisy":[113],"assignments":[114],"conditional":[117],"adversarial":[118],"component.":[119],"Our":[120,135],"allows":[122],"exploit":[124],"large":[125],"corpora":[127],"outside":[128],"distributions":[131],"image/caption":[133],"data.":[134],"experiments":[136],"show":[137],"proposed":[140],"domain":[141],"alignment":[142],"learns":[143],"meaningful":[146],"representation":[147],"which":[148],"outperforms":[149],"previous":[150],"work.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":24},{"year":2023,"cited_by_count":26},{"year":2022,"cited_by_count":20},{"year":2021,"cited_by_count":21},{"year":2020,"cited_by_count":9}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2019-08-29T00:00:00"}