{"id":"https://openalex.org/W2137251014","doi":"https://doi.org/10.1145/2072298.2072058","title":"Automatic sentence generation from images","display_name":"Automatic sentence generation from images","publication_year":2011,"publication_date":"2011-11-28","ids":{"openalex":"https://openalex.org/W2137251014","doi":"https://doi.org/10.1145/2072298.2072058","mag":"2137251014"},"language":"en","primary_location":{"id":"doi:10.1145/2072298.2072058","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2072298.2072058","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th ACM international conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5077707500","display_name":"Yoshitaka Ushiku","orcid":"https://orcid.org/0000-0002-9014-1389"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yoshitaka Ushiku","raw_affiliation_strings":["The University of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042711470","display_name":"Tatsuya Harada","orcid":"https://orcid.org/0000-0002-3712-3691"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tatsuya Harada","raw_affiliation_strings":["The University of Tokyo / JST PRESTO, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo / JST PRESTO, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010543059","display_name":"Yasuo Kuniyoshi","orcid":"https://orcid.org/0000-0001-8443-4161"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yasuo Kuniyoshi","raw_affiliation_strings":["The University of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5077707500"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":1.2879,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.83867366,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1533","last_page":"1536"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9997000098228455,"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":0.9990000128746033,"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/computer-science","display_name":"Computer science","score":0.8525265455245972},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6879533529281616},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6262891292572021},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6044087409973145},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5310583114624023},{"id":"https://openalex.org/keywords/grammar","display_name":"Grammar","score":0.5077036619186401},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4930126368999481},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.15735283493995667}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8525265455245972},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6879533529281616},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6262891292572021},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6044087409973145},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5310583114624023},{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.5077036619186401},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4930126368999481},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.15735283493995667},{"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:10.1145/2072298.2072058","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2072298.2072058","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th ACM international conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7799999713897705}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W117943111","https://openalex.org/W1566135517","https://openalex.org/W1897761818","https://openalex.org/W2027922120","https://openalex.org/W2039051707","https://openalex.org/W2061571889","https://openalex.org/W2075006521","https://openalex.org/W2078861931","https://openalex.org/W2082451464","https://openalex.org/W2101105183","https://openalex.org/W2137123920","https://openalex.org/W2151103935","https://openalex.org/W2154124206","https://openalex.org/W2162762921"],"related_works":["https://openalex.org/W2375873920","https://openalex.org/W2146114872","https://openalex.org/W2392060890","https://openalex.org/W2392760275","https://openalex.org/W2083530853","https://openalex.org/W2982905616","https://openalex.org/W2009831055","https://openalex.org/W2393172683","https://openalex.org/W2368686738","https://openalex.org/W2389383932"],"abstract_inverted_index":{"For":[0],"the":[1,8,20,78,96,115],"overwhelming":[2],"amounts":[3],"of":[4,11,64,109],"multimedia":[5,43],"used":[6],"on":[7],"Web,":[9],"methods":[10],"search":[12,36],"and":[13,40,56,111],"understanding":[14],"with":[15,37],"sentences":[16,29,51],"are":[17,67,74],"necessary.":[18],"Representing":[19],"contents":[21],"not":[22],"only":[23],"using":[24,28,105],"labels":[25],"but":[26],"also":[27],"including":[30],"labels'":[31],"relations":[32,55],"enables":[33],"users":[34],"to":[35,41,69,76,81,90],"a":[38,87,92,106],"story":[39],"understand":[42],"deeply.":[44],"However,":[45],"few":[46],"existing":[47],"works":[48],"describe":[49],"such":[50],"because":[52],"obtaining":[53],"objects'":[54],"grammar":[57],"is":[58],"difficult.":[59],"We":[60],"specifically":[61],"examine":[62],"captions":[63],"images":[65,110],"that":[66,114],"similar":[68],"an":[70],"input":[71,79,97],"image.":[72],"They":[73],"expected":[75],"explain":[77],"image":[80,98],"some":[82],"degree.":[83],"Therefore,":[84],"we":[85],"propose":[86],"novel":[88],"approach":[89],"generate":[91,119],"sentential":[93,120],"caption":[94],"for":[95],"by":[99],"summarizing":[100],"those":[101],"captions.":[102,121],"Our":[103],"experiment":[104],"dataset":[107],"consisting":[108],"text":[112],"demonstrates":[113],"proposed":[116],"method":[117],"can":[118]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2},{"year":2012,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}