{"id":"https://openalex.org/W4406821755","doi":"https://doi.org/10.1007/s44163-025-00230-y","title":"Automatic summarization of cooking videos using transfer learning and transformer-based models","display_name":"Automatic summarization of cooking videos using transfer learning and transformer-based models","publication_year":2025,"publication_date":"2025-01-25","ids":{"openalex":"https://openalex.org/W4406821755","doi":"https://doi.org/10.1007/s44163-025-00230-y"},"language":"en","primary_location":{"id":"doi:10.1007/s44163-025-00230-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44163-025-00230-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44163-025-00230-y.pdf","source":{"id":"https://openalex.org/S4210220416","display_name":"Discover Artificial Intelligence","issn_l":"2731-0809","issn":["2731-0809"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Discover Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://link.springer.com/content/pdf/10.1007/s44163-025-00230-y.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5116031383","display_name":"P. M. Alen Sadique","orcid":null},"institutions":[{"id":"https://openalex.org/I876193797","display_name":"Vellore Institute of Technology University","ror":"https://ror.org/00qzypv28","country_code":"IN","type":"education","lineage":["https://openalex.org/I876193797"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"P. M. Alen Sadique","raw_affiliation_strings":["School of Computer Science and Engineering, Vellore Institute of Technology, Chennai, 600127, Tamil Nadu, India"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Vellore Institute of Technology, Chennai, 600127, Tamil Nadu, India","institution_ids":["https://openalex.org/I876193797"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032018978","display_name":"R. V. Aswiga","orcid":null},"institutions":[{"id":"https://openalex.org/I876193797","display_name":"Vellore Institute of Technology University","ror":"https://ror.org/00qzypv28","country_code":"IN","type":"education","lineage":["https://openalex.org/I876193797"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"R. V. Aswiga","raw_affiliation_strings":["School of Computer Science and Engineering, Vellore Institute of Technology, Chennai, 600127, Tamil Nadu, India"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Vellore Institute of Technology, Chennai, 600127, Tamil Nadu, India","institution_ids":["https://openalex.org/I876193797"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5116031383"],"corresponding_institution_ids":["https://openalex.org/I876193797"],"apc_list":{"value":990,"currency":"EUR","value_usd":1067},"apc_paid":{"value":990,"currency":"EUR","value_usd":1067},"fwci":9.6659,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.97922523,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"5","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9764000177383423,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9764000177383423,"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/T11309","display_name":"Music and Audio Processing","score":0.9684000015258789,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11925","display_name":"Culinary Culture and Tourism","score":0.9553999900817871,"subfield":{"id":"https://openalex.org/subfields/1106","display_name":"Food Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.9295964241027832},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7286291122436523},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6461665630340576},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5387538075447083},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4266442060470581},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35958197712898254},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15242326259613037},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.13764166831970215}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.9295964241027832},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7286291122436523},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6461665630340576},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5387538075447083},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4266442060470581},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35958197712898254},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15242326259613037},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.13764166831970215},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s44163-025-00230-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44163-025-00230-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44163-025-00230-y.pdf","source":{"id":"https://openalex.org/S4210220416","display_name":"Discover Artificial Intelligence","issn_l":"2731-0809","issn":["2731-0809"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Discover Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:fd8e75f9522c42a9890c0e35b880dc5e","is_oa":true,"landing_page_url":"https://doaj.org/article/fd8e75f9522c42a9890c0e35b880dc5e","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Discover Artificial Intelligence, Vol 5, Iss 1, Pp 1-20 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s44163-025-00230-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44163-025-00230-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44163-025-00230-y.pdf","source":{"id":"https://openalex.org/S4210220416","display_name":"Discover Artificial Intelligence","issn_l":"2731-0809","issn":["2731-0809"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Discover Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/2","display_name":"Zero hunger","score":0.6700000166893005}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4406821755.pdf"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W2157550655","https://openalex.org/W2766375149","https://openalex.org/W2960503884","https://openalex.org/W2963351113","https://openalex.org/W3014419822","https://openalex.org/W3193979817","https://openalex.org/W4220848440","https://openalex.org/W4283397270","https://openalex.org/W4283585459","https://openalex.org/W4312325116","https://openalex.org/W4323060027","https://openalex.org/W4380995509","https://openalex.org/W4391598244","https://openalex.org/W4394596514","https://openalex.org/W6600213211"],"related_works":["https://openalex.org/W2366403280","https://openalex.org/W1495108544","https://openalex.org/W2091301346","https://openalex.org/W3148229873","https://openalex.org/W4389760904","https://openalex.org/W2150160875","https://openalex.org/W4242223894","https://openalex.org/W4317547544","https://openalex.org/W4313395829","https://openalex.org/W3204019825"],"abstract_inverted_index":{"The":[0,352],"proliferation":[1],"of":[2,13,30,59,100,104,132,196,282,287,313,343],"cooking":[3,31,79,92,124,348,377],"videos":[4,64,168,378],"on":[5,129,359],"the":[6,11,57,78,98,130,182,241,245,253,257,283,296,311,314,323,329,341,356,362,366],"internet":[7],"these":[8,14],"days":[9],"necessitates":[10],"conversion":[12],"lengthy":[15,46],"video":[16,349],"contents":[17],"into":[18,65,169,379],"concise":[19],"text":[20,66],"recipes.":[21],"Many":[22],"online":[23],"platforms":[24],"now":[25],"have":[26],"a":[27,37,95,101,116,158,194,202,233,280,344],"large":[28],"number":[29],"videos,":[32,125],"in":[33,53,63,143,178,256,270,289,355,365,375],"which,":[34],"there":[35,114],"is":[36,51,115,141,176,186,211,224,237,264,275,307],"challenge":[38],"for":[39,82,87,119,188,217,229],"viewers":[40],"to":[41,55,71,156,164,180,239,278,294],"extract":[42],"comprehensive":[43],"recipes":[44,67,121],"from":[45,123,299],"visual":[47,300],"content.":[48],"Effective":[49],"summary":[50,190,255,262,281,316,319],"necessary":[52],"order":[54,179],"translate":[56],"abundance":[58],"culinary":[60,167],"knowledge":[61],"found":[62],"that":[68,160],"are":[69,85,127,358],"easy":[70],"read":[72],"and":[73,110,153,201,220,301,317,321,334,373],"follow.":[74],"This":[75],"will":[76,250],"make":[77],"process":[80,131],"easier":[81,163],"individuals":[83],"who":[84],"searching":[86],"precise":[88],"step":[89,91],"by":[90,244,266],"instructions.":[93],"Such":[94],"system":[96,159],"satisfies":[97],"needs":[99],"broad":[102],"spectrum":[103],"learners":[105],"while":[106],"also":[107],"improving":[108],"accessibility":[109],"user":[111],"simplicity.":[112],"As":[113],"growing":[117],"need":[118],"easy-to-follow":[120],"made":[122],"researchers":[126],"looking":[128],"automated":[133],"summarization":[134,350],"using":[135],"advanced":[136],"techniques.":[137],"One":[138],"such":[139],"approach":[140],"presented":[142],"our":[144,290],"work,":[145],"which":[146,192,249,309,369],"combines":[147,310],"simple":[148],"image-based":[149],"models,":[150],"audio":[151,288,318],"processing,":[152],"GPT-based":[154,203,273,305],"models":[155,248],"create":[157],"makes":[161],"it":[162],"turn":[165],"long":[166],"in-depth":[170],"recipe":[171,381],"texts.":[172,382],"A":[173,205,272],"systematic":[174],"workflow":[175],"adopted":[177],"achieve":[181],"objective.":[183],"Initially,":[184],"Focus":[185],"given":[187],"frame":[189,254,315],"generation":[191,263],"employs":[193],"combination":[195],"two":[197,246],"convolutional":[198],"neural":[199],"networks":[200],"model.":[204],"pre-trained":[206],"CNN":[207,223,247],"model":[208,236,274,306],"called":[209],"Inception-V3":[210],"fine-tuned":[212],"with":[213,226,332,340,361],"food":[214],"image":[215],"dataset":[216],"dish":[218],"recognition":[219],"another":[221],"custom-made":[222],"built":[225],"ingredient":[227,230],"images":[228],"recognition.":[231],"Then":[232],"GPT":[234],"based":[235],"used":[238,277,308],"combine":[240],"results":[242,353],"produced":[243],"give":[251,322],"us":[252],"desired":[258,291],"format.":[259,292],"Subsequently,":[260],"Audio":[261],"tackled":[265],"performing":[267],"Speech-to-text":[268],"functionality":[269],"python.":[271],"then":[276],"generate":[279],"resulting":[284],"textual":[285],"representation":[286],"Finally,":[293],"refine":[295],"summaries":[297],"obtained":[298],"auditory":[302],"content,":[303],"Another":[304],"output":[312],"modules":[320],"final":[324],"enhanced":[325],"summary.":[326],"By":[327],"minimizing":[328],"complications":[330],"involved":[331],"traditional":[333],"sophisticated":[335],"methodologies,":[336],"this":[337],"research":[338],"helps":[339],"development":[342],"straightforward":[345],"but":[346],"efficient":[347],"system.":[351],"achieved":[354],"work":[357,364],"par":[360],"existing":[363],"respective":[367],"field":[368],"demonstrates":[370],"comparable":[371],"performance":[372],"efficacy":[374],"converting":[376],"detailed":[380]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":3}],"updated_date":"2026-04-11T08:14:18.477133","created_date":"2025-10-10T00:00:00"}