{"id":"https://openalex.org/W2886641317","doi":"https://doi.org/10.18653/v1/p18-1238","title":"Conceptual Captions: A Cleaned, Hypernymed, Image Alt-text Dataset For Automatic Image Captioning","display_name":"Conceptual Captions: A Cleaned, Hypernymed, Image Alt-text Dataset For Automatic Image Captioning","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2886641317","doi":"https://doi.org/10.18653/v1/p18-1238","mag":"2886641317"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p18-1238","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-1238","pdf_url":"https://www.aclweb.org/anthology/P18-1238.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 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P18-1238.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100679058","display_name":"Piyush Sharma","orcid":"https://orcid.org/0009-0003-0372-4303"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Piyush Sharma","raw_affiliation_strings":["Google AI Venice, CA 90291"],"affiliations":[{"raw_affiliation_string":"Google AI Venice, CA 90291","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023501811","display_name":"Nan Ding","orcid":"https://orcid.org/0000-0002-4876-6553"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nan Ding","raw_affiliation_strings":["Google AI Venice, CA 90291"],"affiliations":[{"raw_affiliation_string":"Google AI Venice, CA 90291","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090365098","display_name":"Sebastian Goodman","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sebastian Goodman","raw_affiliation_strings":["Google AI Venice, CA 90291"],"affiliations":[{"raw_affiliation_string":"Google AI Venice, CA 90291","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089152779","display_name":"Radu Soricut","orcid":"https://orcid.org/0000-0003-1565-3365"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Radu Soricut","raw_affiliation_strings":["Google AI Venice, CA 90291"],"affiliations":[{"raw_affiliation_string":"Google AI Venice, CA 90291","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100679058"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":51.1664,"has_fulltext":true,"cited_by_count":1758,"citation_normalized_percentile":{"value":0.99883627,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2556","last_page":"2565"},"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":0.9958000183105469,"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/T11439","display_name":"Video Analysis and Summarization","score":0.988099992275238,"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":0.9521260261535645},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7976267337799072},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.6419398784637451},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.621394157409668},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.582534670829773},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47257864475250244},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3782098889350891},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37659984827041626},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3616167902946472}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9521260261535645},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7976267337799072},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6419398784637451},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.621394157409668},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.582534670829773},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47257864475250244},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3782098889350891},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37659984827041626},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3616167902946472},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/p18-1238","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-1238","pdf_url":"https://www.aclweb.org/anthology/P18-1238.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 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/p18-1238","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-1238","pdf_url":"https://www.aclweb.org/anthology/P18-1238.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 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.4399999976158142,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2886641317.pdf","grobid_xml":"https://content.openalex.org/works/W2886641317.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W68733909","https://openalex.org/W1514535095","https://openalex.org/W1527575280","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1924770834","https://openalex.org/W1931639407","https://openalex.org/W1947481528","https://openalex.org/W1956340063","https://openalex.org/W1978924650","https://openalex.org/W2064675550","https://openalex.org/W2072128103","https://openalex.org/W2108325777","https://openalex.org/W2108598243","https://openalex.org/W2123301721","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2146502635","https://openalex.org/W2163605009","https://openalex.org/W2176263492","https://openalex.org/W2185175083","https://openalex.org/W2274287116","https://openalex.org/W2282219577","https://openalex.org/W2481240925","https://openalex.org/W2506483933","https://openalex.org/W2551915941","https://openalex.org/W2557728737","https://openalex.org/W2558533273","https://openalex.org/W2951597448","https://openalex.org/W2953390309","https://openalex.org/W2963248296","https://openalex.org/W2963403868","https://openalex.org/W2963673305","https://openalex.org/W2964049455","https://openalex.org/W2964308564","https://openalex.org/W2964350391","https://openalex.org/W4231109964","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W3122720459","https://openalex.org/W4298897568","https://openalex.org/W1938708284","https://openalex.org/W4380190185","https://openalex.org/W3161816943","https://openalex.org/W4387608643"],"abstract_inverted_index":{"We":[0,23,37],"present":[1,39],"a":[2,43,52],"new":[3],"dataset":[4,22],"of":[5,15,35,42,45],"image":[6,30,46],"caption":[7,31],"annotations,":[8],"Conceptual":[9],"Captions,":[10],"which":[11],"contains":[12],"an":[13],"order":[14],"magnitude":[16],"more":[17],"images":[18],"than":[19],"the":[20],"MS-COCO":[21],"achieve":[24],"this":[25],"by":[26],"extracting":[27],"and":[28,49,66],"filtering":[29],"annotations":[32],"from":[33],"billions":[34],"webpages.":[36],"also":[38],"quantitative":[40],"evaluations":[41],"number":[44],"captioning":[47],"models":[48],"show":[50],"that":[51],"model":[53],"architecture":[54],"based":[55],"on":[56],"Inception-":[57],"ResNet-v2":[58],"(Szegedy":[59],"et":[60],"al.,":[61],"2016)":[62],"for":[63],"image-feature":[64],"extraction":[65],"Transformer":[67]},"counts_by_year":[{"year":2026,"cited_by_count":30},{"year":2025,"cited_by_count":250},{"year":2024,"cited_by_count":353},{"year":2023,"cited_by_count":392},{"year":2022,"cited_by_count":254},{"year":2021,"cited_by_count":281},{"year":2020,"cited_by_count":151},{"year":2019,"cited_by_count":46},{"year":2018,"cited_by_count":1}],"updated_date":"2026-03-29T08:15:47.926485","created_date":"2025-10-10T00:00:00"}