{"id":"https://openalex.org/W2982553295","doi":"https://doi.org/10.1109/bcd.2019.8885222","title":"\u201cNever fry carrots without cutting.\u201d Cooking Recipe Generation from Videos Using Deep Learning Considering Previous Process","display_name":"\u201cNever fry carrots without cutting.\u201d Cooking Recipe Generation from Videos Using Deep Learning Considering Previous Process","publication_year":2019,"publication_date":"2019-05-01","ids":{"openalex":"https://openalex.org/W2982553295","doi":"https://doi.org/10.1109/bcd.2019.8885222","mag":"2982553295"},"language":"en","primary_location":{"id":"doi:10.1109/bcd.2019.8885222","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bcd.2019.8885222","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Big Data, Cloud Computing, Data Science & Engineering (BCD)","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/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":true,"raw_author_name":"Tatsuki FUJII","raw_affiliation_strings":["Graduate School of Informatics and Engineering, University of Electro-Communications, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics and Engineering, University of Electro-Communications, 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":["Graduate School of Informatics and Engineering, University of Electro-Communications, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics and Engineering, University of Electro-Communications, 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":["Graduate School of Informatics and Engineering, University of Electro-Communications, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics and Engineering, University of Electro-Communications, 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":["Graduate School of Informatics and Engineering, University of Electro-Communications, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics and Engineering, University of Electro-Communications, 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":["Graduate School of Informatics and Engineering, University of Electro-Communications, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics and Engineering, University of Electro-Communications, Tokyo, Japan","institution_ids":["https://openalex.org/I20529979"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101041389"],"corresponding_institution_ids":["https://openalex.org/I20529979"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.1212523,"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":null,"last_page":null},"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":0.9976000189781189,"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":0.9958999752998352,"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/recipe","display_name":"Recipe","score":0.9606650471687317},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.9442226886749268},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8330364227294922},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6171064376831055},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6065500974655151},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5823885202407837},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5723943710327148},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5166497826576233},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5061952471733093},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.49916505813598633},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4397527575492859},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4280610978603363},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3906722068786621},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38165634870529175}],"concepts":[{"id":"https://openalex.org/C2778671685","wikidata":"https://www.wikidata.org/wiki/Q219239","display_name":"Recipe","level":2,"score":0.9606650471687317},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9442226886749268},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8330364227294922},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6171064376831055},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6065500974655151},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5823885202407837},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5723943710327148},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5166497826576233},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5061952471733093},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.49916505813598633},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4397527575492859},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4280610978603363},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3906722068786621},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38165634870529175},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bcd.2019.8885222","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bcd.2019.8885222","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Big Data, Cloud Computing, Data Science & Engineering (BCD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6299999952316284,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1486649854","https://openalex.org/W1522301498","https://openalex.org/W1686810756","https://openalex.org/W1956340063","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2112796928","https://openalex.org/W2123301721","https://openalex.org/W2131744502","https://openalex.org/W2153579005","https://openalex.org/W2157331557","https://openalex.org/W2194775991","https://openalex.org/W2560920409","https://openalex.org/W2737041163","https://openalex.org/W6629028937","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6679775712","https://openalex.org/W6687483927","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W3007178519","https://openalex.org/W3135078442","https://openalex.org/W3202567960","https://openalex.org/W3090602574","https://openalex.org/W2945961616","https://openalex.org/W2970754407","https://openalex.org/W2773550412","https://openalex.org/W3036736353","https://openalex.org/W2901467237","https://openalex.org/W2944270022","https://openalex.org/W2965697393","https://openalex.org/W3207130959","https://openalex.org/W2964335490","https://openalex.org/W3035112208","https://openalex.org/W2904771064","https://openalex.org/W2964040984","https://openalex.org/W3047151004","https://openalex.org/W2507365558","https://openalex.org/W3161603460","https://openalex.org/W2943294985"],"abstract_inverted_index":{"Research":[0],"on":[1],"captioning":[2,48,78],"that":[3,60,134],"modifies":[4],"the":[5,54,70,74,113,117,129],"contents":[6],"of":[7,64,76],"images":[8,11],"and":[9,22,49,85,127],"moving":[10],"with":[12,116,123],"natural":[13],"language":[14],"using":[15],"deep":[16],"training":[17],"has":[18],"had":[19],"considerable":[20],"results":[21,132],"attracted":[23],"attention":[24],"in":[25,69],"recent":[26],"years.":[27],"In":[28],"this":[29,45],"research,":[30],"we":[31,81],"aim":[32],"to":[33,73,88,97,106],"generate":[34],"recipe":[35,72,125],"sentences":[36,84,87],"from":[37,41],"cooking":[38],"videos":[39],"acquired":[40],"YouTube.":[42],"We":[43,56,91,100,110],"treat":[44],"as":[46],"image":[47],"propose":[50,57,93],"methods":[51,137],"suitable":[52],"for":[53],"task.":[55],"a":[58,62,65,77,94],"method":[59,96],"adds":[61],"vector":[63],"sentence":[66],"already":[67],"generated":[68,83],"same":[71,114],"input":[75],"model.":[79],"Then,":[80],"compare":[82,121],"correct":[86,124],"calculate":[89,128],"scores.":[90],"also":[92],"data-processing":[95],"improve":[98],"accuracy.":[99,140],"employ":[101],"several":[102],"widely":[103],"used":[104],"metrics":[105],"evaluate":[107],"image-captioning":[108],"problems.":[109],"then":[111],"train":[112],"data":[115],"simplest":[118],"encoder-decoder":[119],"model,":[120],"it":[122],"sentences,":[126],"metrics.":[130],"The":[131],"indicate":[133],"my":[135],"proposal":[136],"help":[138],"increase":[139]},"counts_by_year":[{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}