{"id":"https://openalex.org/W3007178519","doi":"https://doi.org/10.1145/3378184.3378217","title":"Generating Cooking Recipes from Cooking Videos Using Deep Learning Considering Previous Process with Video Encoding","display_name":"Generating Cooking Recipes from Cooking Videos Using Deep Learning Considering Previous Process with Video Encoding","publication_year":2020,"publication_date":"2020-01-07","ids":{"openalex":"https://openalex.org/W3007178519","doi":"https://doi.org/10.1145/3378184.3378217","mag":"3007178519"},"language":"en","primary_location":{"id":"doi:10.1145/3378184.3378217","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3378184.3378217","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Conference on Applications of Intelligent Systems","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101041389","display_name":"Tatsuki Fujii","orcid":null},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tatsuki Fujii","raw_affiliation_strings":["University of Electro-Communications, Chofu, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electro-Communications, Chofu, Tokyo, Japan","institution_ids":["https://openalex.org/I20529979"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017186793","display_name":"Ryohei Orihara","orcid":"https://orcid.org/0000-0002-9039-7704"},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryohei Orihara","raw_affiliation_strings":["University of Electro-Communications, Chofu, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electro-Communications, Chofu, Tokyo, Japan","institution_ids":["https://openalex.org/I20529979"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045716284","display_name":"Yuichi Sei","orcid":"https://orcid.org/0000-0002-2552-6717"},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuichi Sei","raw_affiliation_strings":["University of Electro-Communications, Chofu, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electro-Communications, Chofu, Tokyo, Japan","institution_ids":["https://openalex.org/I20529979"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013743040","display_name":"Yasuyuki Tahara","orcid":"https://orcid.org/0000-0002-1939-4455"},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yasuyuki Tahara","raw_affiliation_strings":["University of Electro-Communications, Chofu, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electro-Communications, Chofu, Tokyo, Japan","institution_ids":["https://openalex.org/I20529979"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013259601","display_name":"Akihiko Ohsuga","orcid":"https://orcid.org/0000-0001-6717-7028"},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akihiko Ohsuga","raw_affiliation_strings":["University of Electro-Communications, Chofu, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electro-Communications, Chofu, Tokyo, Japan","institution_ids":["https://openalex.org/I20529979"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I20529979"],"apc_list":null,"apc_paid":null,"fwci":0.2563,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.53484548,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9926999807357788,"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":0.9912999868392944,"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":0.9515464901924133},{"id":"https://openalex.org/keywords/recipe","display_name":"Recipe","score":0.9167584180831909},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8397072553634644},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6365612149238586},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6008216142654419},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5982919931411743},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5976237058639526},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5801557898521423},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5442355871200562},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.504348635673523},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4966779351234436},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4604502320289612},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.35902827978134155},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08466047048568726}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9515464901924133},{"id":"https://openalex.org/C2778671685","wikidata":"https://www.wikidata.org/wiki/Q219239","display_name":"Recipe","level":2,"score":0.9167584180831909},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8397072553634644},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6365612149238586},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6008216142654419},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5982919931411743},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5976237058639526},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5801557898521423},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5442355871200562},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.504348635673523},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4966779351234436},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4604502320289612},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.35902827978134155},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08466047048568726},{"id":"https://openalex.org/C31903555","wikidata":"https://www.wikidata.org/wiki/Q1637030","display_name":"Food science","level":1,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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":1,"locations":[{"id":"doi:10.1145/3378184.3378217","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3378184.3378217","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Conference on Applications of Intelligent Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7900000214576721,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W2064675550","https://openalex.org/W2080672747","https://openalex.org/W2112796928","https://openalex.org/W2153579005","https://openalex.org/W2157331557","https://openalex.org/W2463955103","https://openalex.org/W2527145521","https://openalex.org/W2600463316","https://openalex.org/W2737041163","https://openalex.org/W2952132648","https://openalex.org/W2963177403","https://openalex.org/W2964042428","https://openalex.org/W2964887566"],"related_works":["https://openalex.org/W258429745","https://openalex.org/W3161239248","https://openalex.org/W1584543623","https://openalex.org/W2561508161","https://openalex.org/W3195543079","https://openalex.org/W2098178683","https://openalex.org/W4210416330","https://openalex.org/W2740680361","https://openalex.org/W3207562294","https://openalex.org/W3187068967"],"abstract_inverted_index":{"Research":[0],"on":[1],"generating":[2],"natural":[3],"language":[4],"captions":[5],"to":[6,33,54,59,75,115,146,156],"visual":[7,94],"data":[8,83],"such":[9,97],"as":[10,47,98],"images":[11,88],"and":[12,22,127],"videos":[13,39],"has":[14],"produced":[15],"considerable":[16],"results":[17],"with":[18,157],"deep":[19],"learning":[20],"methods":[21,96],"attracted":[23],"attention":[24],"in":[25,57,143],"recent":[26],"years.":[27],"In":[28],"this":[29],"research,":[30],"we":[31,131],"aim":[32],"generate":[34],"recipe":[35,134],"sentences":[36],"from":[37,41,89,159],"cooking":[38],"acquired":[40],"YouTube.":[42],"We":[43,62,104,136,152],"treat":[44],"the":[45,65,77,117,120,128,148,154],"task":[46],"image":[48,149],"captioning.":[49],"There":[50],"are":[51,141],"two":[52],"aspects":[53],"be":[55,71,102],"considered":[56],"order":[58],"do":[60],"so.":[61],"believe":[63],"that":[64,85,140],"semantics":[66],"of":[67,119],"each":[68,90],"process":[69,91],"should":[70,101],"taken":[72],"into":[73],"account":[74],"improve":[76],"captioning":[78,107,150],"'":[79],"s":[80],"accuracy.":[81],"Furthermore,":[82],"processing,":[84],"is":[86,113],"obtaining":[87],"using":[92],"several":[93],"processing":[95],"object":[99],"detection":[100],"important.":[103],"propose":[105],"a":[106,110],"model":[108],"where":[109],"sentence":[111],"vector":[112],"embedded":[114],"consider":[116],"consistency":[118],"recipe.":[121],"From":[122],"differences":[123],"between":[124],"generated":[125],"recipes":[126],"reference":[129],"recipe,":[130],"can":[132],"calculate":[133],"scores.":[135],"use":[137],"three":[138],"metrics":[139],"used":[142],"previous":[144],"studies":[145],"evaluate":[147],"model.":[151],"compare":[153],"scores":[155],"ones":[158],"baseline":[160],"models.":[161]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}