{"id":"https://openalex.org/W3013137071","doi":"https://doi.org/10.1007/978-3-030-58536-5_44","title":"TextCaps: A Dataset for Image Captioning with Reading Comprehension","display_name":"TextCaps: A Dataset for Image Captioning with Reading Comprehension","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3013137071","doi":"https://doi.org/10.1007/978-3-030-58536-5_44","mag":"3013137071"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-030-58536-5_44","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-58536-5_44","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2003.12462","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006391126","display_name":"Oleksii Sidorov","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]},{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["IL","US"],"is_corresponding":true,"raw_author_name":"Oleksii Sidorov","raw_affiliation_strings":["Facebook AI Research, Menlo Park, USA","Facebook"],"affiliations":[{"raw_affiliation_string":"Facebook AI Research, Menlo Park, USA","institution_ids":["https://openalex.org/I4210114444","https://openalex.org/I4210099336"]},{"raw_affiliation_string":"Facebook","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072304825","display_name":"Ronghang Hu","orcid":"https://orcid.org/0000-0002-5060-9485"},"institutions":[{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]},{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]},{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["IL","US"],"is_corresponding":false,"raw_author_name":"Ronghang Hu","raw_affiliation_strings":["Facebook AI Research, Menlo Park, USA","University of California, Berkeley, USA","Facebook"],"affiliations":[{"raw_affiliation_string":"Facebook AI Research, Menlo Park, USA","institution_ids":["https://openalex.org/I4210114444","https://openalex.org/I4210099336"]},{"raw_affiliation_string":"University of California, Berkeley, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"Facebook","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024481540","display_name":"Marcus Rohrbach","orcid":"https://orcid.org/0000-0001-5908-7751"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]},{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["IL","US"],"is_corresponding":false,"raw_author_name":"Marcus Rohrbach","raw_affiliation_strings":["Facebook AI Research, Menlo Park, USA","Facebook"],"affiliations":[{"raw_affiliation_string":"Facebook AI Research, Menlo Park, USA","institution_ids":["https://openalex.org/I4210114444","https://openalex.org/I4210099336"]},{"raw_affiliation_string":"Facebook","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100672985","display_name":"Amanpreet Singh","orcid":"https://orcid.org/0000-0002-3409-9833"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amanpreet Singh","raw_affiliation_strings":["Facebook AI Research, Menlo Park, USA","University of California\u2013Berkeley"],"affiliations":[{"raw_affiliation_string":"Facebook AI Research, Menlo Park, USA","institution_ids":["https://openalex.org/I4210114444","https://openalex.org/I4210099336"]},{"raw_affiliation_string":"University of California\u2013Berkeley","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5006391126"],"corresponding_institution_ids":["https://openalex.org/I2252078561","https://openalex.org/I4210099336","https://openalex.org/I4210114444"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":1.3859,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.88216881,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"742","last_page":"758"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9914000034332275,"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/T10028","display_name":"Topic Modeling","score":0.9833999872207642,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.972345232963562},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8193416595458984},{"id":"https://openalex.org/keywords/paraphrase","display_name":"Paraphrase","score":0.7421373128890991},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6796112060546875},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6318663358688354},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6223170161247253},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.5498433709144592},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.5349951982498169},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5109278559684753},{"id":"https://openalex.org/keywords/reading-comprehension","display_name":"Reading comprehension","score":0.504642128944397},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4884778559207916},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.43247556686401367},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.179928719997406}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.972345232963562},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8193416595458984},{"id":"https://openalex.org/C2780922921","wikidata":"https://www.wikidata.org/wiki/Q255189","display_name":"Paraphrase","level":2,"score":0.7421373128890991},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6796112060546875},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6318663358688354},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6223170161247253},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.5498433709144592},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.5349951982498169},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5109278559684753},{"id":"https://openalex.org/C2778780117","wikidata":"https://www.wikidata.org/wiki/Q3269423","display_name":"Reading comprehension","level":3,"score":0.504642128944397},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4884778559207916},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.43247556686401367},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.179928719997406},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1007/978-3-030-58536-5_44","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-58536-5_44","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:arXiv.org:2003.12462","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2003.12462","pdf_url":"https://arxiv.org/pdf/2003.12462","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":"","raw_type":"text"},{"id":"mag:3013137071","is_oa":true,"landing_page_url":"http://arxiv.org/pdf/2003.12462.pdf","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2003.12462","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2003.12462","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2003.12462","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2003.12462","pdf_url":"https://arxiv.org/pdf/2003.12462","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":"","raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8899999856948853,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1889081078","https://openalex.org/W1956340063","https://openalex.org/W2001642682","https://openalex.org/W2008806374","https://openalex.org/W2053317383","https://openalex.org/W2058556535","https://openalex.org/W2090048052","https://openalex.org/W2101105183","https://openalex.org/W2109586012","https://openalex.org/W2133459682","https://openalex.org/W2154652894","https://openalex.org/W2185175083","https://openalex.org/W2493916176","https://openalex.org/W2506483933","https://openalex.org/W2507756961","https://openalex.org/W2602024037","https://openalex.org/W2613718673","https://openalex.org/W2745461083","https://openalex.org/W2795151422","https://openalex.org/W2809273748","https://openalex.org/W2886641317","https://openalex.org/W2904565150","https://openalex.org/W2923014074","https://openalex.org/W2947555604","https://openalex.org/W2962986948","https://openalex.org/W2963341956","https://openalex.org/W2964018263","https://openalex.org/W2964296749","https://openalex.org/W2975501350","https://openalex.org/W2979382951","https://openalex.org/W2986670728","https://openalex.org/W2988326850","https://openalex.org/W2990873191","https://openalex.org/W3004268082","https://openalex.org/W3020257313","https://openalex.org/W3034336960","https://openalex.org/W3104279398","https://openalex.org/W3110019360"],"related_works":["https://openalex.org/W3136908527","https://openalex.org/W2988326850","https://openalex.org/W3123631020","https://openalex.org/W3103971440","https://openalex.org/W2954598292","https://openalex.org/W2888597673","https://openalex.org/W3094071022","https://openalex.org/W3106343121","https://openalex.org/W2293605478","https://openalex.org/W2979987972","https://openalex.org/W68733909","https://openalex.org/W2949474740","https://openalex.org/W2794317666","https://openalex.org/W2898692195","https://openalex.org/W144280133","https://openalex.org/W3099632088","https://openalex.org/W2394041778","https://openalex.org/W3006508020","https://openalex.org/W3012901398","https://openalex.org/W2006143799"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
