{"id":"https://openalex.org/W7100749464","doi":null,"title":"A Survey of Current Datasets for Vision and Language Research Francis Ferraro1\u2217, Nasrin Mostafazadeh2\u2217, Ting-Hao (Kenneth) Huang3,","display_name":"A Survey of Current Datasets for Vision and Language Research Francis Ferraro1\u2217, Nasrin Mostafazadeh2\u2217, Ting-Hao (Kenneth) Huang3,","publication_year":2015,"publication_date":"2015-12-04","ids":{"openalex":"https://openalex.org/W7100749464"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.696.9391","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.696.9391","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://aclweb.org/anthology/D/D15/D15-1021.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5144658235","display_name":"Lucy V","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lucy V","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057457287","display_name":"Jacob Devlin","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jacob Devlin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107838508","display_name":"Michel Galley","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michel Galley","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5145285590","display_name":"Margaret Mitchell","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Margaret Mitchell","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.58349979,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.0,"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/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"}}],"keywords":[{"id":"https://openalex.org/keywords/multimodal-corpus","display_name":"multimodal corpus","score":0.8109999895095825},{"id":"https://openalex.org/keywords/dataset-evaluation","display_name":"dataset evaluation","score":0.7300000190734863},{"id":"https://openalex.org/keywords/vision-language-integration","display_name":"vision-language integration","score":0.4729999899864197}],"concepts":[{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.7312999963760376},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.70660001039505},{"id":"https://openalex.org/C63882131","wikidata":"https://www.wikidata.org/wiki/Q17122954","display_name":"Strengths and weaknesses","level":2,"score":0.6152999997138977},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6046000123023987},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5098000168800354},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4871000051498413},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4512999951839447},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.40139999985694885},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.39800000190734863},{"id":"https://openalex.org/C2781095916","wikidata":"https://www.wikidata.org/wiki/Q36348","display_name":"Dream","level":2,"score":0.37059998512268066},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.33500000834465027},{"id":"https://openalex.org/C2779313563","wikidata":"https://www.wikidata.org/wiki/Q17072565","display_name":"On Language","level":2,"score":0.3052000105381012},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.30410000681877136},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.3009999990463257},{"id":"https://openalex.org/C94922259","wikidata":"https://www.wikidata.org/wiki/Q33215","display_name":"Constructed language","level":2,"score":0.2915000021457672},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.2700999975204468},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2623000144958496}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.696.9391","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.696.9391","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://aclweb.org/anthology/D/D15/D15-1021.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.715.1461","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.715.1461","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cs.rochester.edu/%7Enasrinm/files/Papers/Survey-Vision-and-Language.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.858.8864","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.858.8864","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.emnlp2015.org/proceedings/EMNLP/pdf/EMNLP021.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3198196812","https://openalex.org/W3011101596","https://openalex.org/W1749884237","https://openalex.org/W2786470004","https://openalex.org/W4400025147","https://openalex.org/W166382231","https://openalex.org/W7099446827","https://openalex.org/W3021000432","https://openalex.org/W4313304663","https://openalex.org/W2888211297"],"abstract_inverted_index":{"Integrating":[0],"vision":[1,30],"and":[2,31,37,65,72,90,99],"language":[3,32,70,89],"has":[4],"long":[5],"been":[6,85],"a":[7,44,58],"dream":[8],"in":[9,47,101],"work":[10,26],"on":[11],"artificial":[12],"intel-ligence":[13],"(AI).":[14],"In":[15,53],"the":[16,67,80],"past":[17],"two":[18],"years,":[19],"we":[20,56],"have":[21,42,84],"witnessed":[22],"an":[23],"explosion":[24],"of":[25,51,60],"that":[27,79],"brings":[28],"together":[29],"from":[33],"images":[34],"to":[35],"videos":[36],"beyond.":[38],"The":[39],"avail-able":[40],"corpora":[41],"played":[43],"crucial":[45],"role":[46],"advancing":[48],"this":[49,54],"area":[50],"research.":[52],"paper,":[55],"propose":[57],"set":[59],"quality":[61],"met-rics":[62],"for":[63],"evaluating":[64],"analyzing":[66],"vi-sion":[68],"&":[69],"datasets":[71,83],"categorize":[73],"them":[74],"accordingly.":[75],"Our":[76],"analyses":[77],"show":[78],"most":[81],"recent":[82],"us-ing":[86],"more":[87,91],"complex":[88],"ab-stract":[92],"concepts,":[93],"however,":[94],"there":[95],"are":[96],"differ-ent":[97],"strengths":[98],"weaknesses":[100],"each.":[102],"1":[103]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2026-08-07T00:00:00"}
