{"id":"https://openalex.org/W4414539643","doi":"https://doi.org/10.23919/mva65244.2025.11175067","title":"Object State Recognition in Cooking Videos through End State Frames Analysis","display_name":"Object State Recognition in Cooking Videos through End State Frames Analysis","publication_year":2025,"publication_date":"2025-07-26","ids":{"openalex":"https://openalex.org/W4414539643","doi":"https://doi.org/10.23919/mva65244.2025.11175067"},"language":"en","primary_location":{"id":"doi:10.23919/mva65244.2025.11175067","is_oa":false,"landing_page_url":"https://doi.org/10.23919/mva65244.2025.11175067","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 19th International Conference on Machine Vision and Applications (MVA)","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/A5119739878","display_name":"Yutaro Kitakami","orcid":null},"institutions":[{"id":"https://openalex.org/I4387152983","display_name":"Osaka Metropolitan University","ror":"https://ror.org/01hvx5h04","country_code":"JP","type":"education","lineage":["https://openalex.org/I4387152983"]},{"id":"https://openalex.org/I69740276","display_name":"Tokyo Metropolitan University","ror":"https://ror.org/00ws30h19","country_code":"JP","type":"education","lineage":["https://openalex.org/I69740276"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yutaro Kitakami","raw_affiliation_strings":["Osaka Metropolitan University,Osaka,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Osaka Metropolitan University,Osaka,Japan","institution_ids":["https://openalex.org/I69740276","https://openalex.org/I4387152983"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027332963","display_name":"Katsufumi Inoue","orcid":"https://orcid.org/0000-0001-6073-7264"},"institutions":[{"id":"https://openalex.org/I4387152983","display_name":"Osaka Metropolitan University","ror":"https://ror.org/01hvx5h04","country_code":"JP","type":"education","lineage":["https://openalex.org/I4387152983"]},{"id":"https://openalex.org/I69740276","display_name":"Tokyo Metropolitan University","ror":"https://ror.org/00ws30h19","country_code":"JP","type":"education","lineage":["https://openalex.org/I69740276"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Katsufumi Inoue","raw_affiliation_strings":["Osaka Metropolitan University,Osaka,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Osaka Metropolitan University,Osaka,Japan","institution_ids":["https://openalex.org/I69740276","https://openalex.org/I4387152983"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108603127","display_name":"Michifumi Yoshioka","orcid":null},"institutions":[{"id":"https://openalex.org/I4387152983","display_name":"Osaka Metropolitan University","ror":"https://ror.org/01hvx5h04","country_code":"JP","type":"education","lineage":["https://openalex.org/I4387152983"]},{"id":"https://openalex.org/I69740276","display_name":"Tokyo Metropolitan University","ror":"https://ror.org/00ws30h19","country_code":"JP","type":"education","lineage":["https://openalex.org/I69740276"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Michifumi Yoshioka","raw_affiliation_strings":["Osaka Metropolitan University,Osaka,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Osaka Metropolitan University,Osaka,Japan","institution_ids":["https://openalex.org/I69740276","https://openalex.org/I4387152983"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":0.27167605,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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/T12496","display_name":"Color perception and design","score":0.6413999795913696,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12496","display_name":"Color perception and design","score":0.6413999795913696,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6223000288009644},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5939000248908997},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5922999978065491},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5810999870300293},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.579200029373169},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.5138999819755554},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.4691999852657318},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4578000009059906},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4381999969482422}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7358999848365784},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7343999743461609},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6223000288009644},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6116999983787537},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5939000248908997},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5922999978065491},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5810999870300293},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.579200029373169},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.5138999819755554},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.4691999852657318},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4578000009059906},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4381999969482422},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4083999991416931},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.398499995470047},{"id":"https://openalex.org/C121687571","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Activity recognition","level":2,"score":0.38830000162124634},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3878999948501587},{"id":"https://openalex.org/C14551309","wikidata":"https://www.wikidata.org/wiki/Q4636325","display_name":"3D single-object recognition","level":4,"score":0.37770000100135803},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3700000047683716},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3061000108718872},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.29670000076293945},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2937999963760376},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.2865000069141388},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2822999954223633},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.26759999990463257},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.26339998841285706},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.25780001282691956}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/mva65244.2025.11175067","is_oa":false,"landing_page_url":"https://doi.org/10.23919/mva65244.2025.11175067","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 19th International Conference on Machine Vision and Applications (MVA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2812296864","https://openalex.org/W2952132648","https://openalex.org/W2963524571","https://openalex.org/W3033484447","https://openalex.org/W3140922383","https://openalex.org/W3205786327","https://openalex.org/W3207758636","https://openalex.org/W4214648418","https://openalex.org/W4298633598","https://openalex.org/W4312420092","https://openalex.org/W4312933868","https://openalex.org/W4386072096","https://openalex.org/W4390873707","https://openalex.org/W4392018329","https://openalex.org/W4402753682","https://openalex.org/W4409262774"],"related_works":[],"abstract_inverted_index":{"Recognition":[0],"of":[1,32,62,75,87,93,107],"fine-grained":[2,43],"actions":[3],"involving":[4],"similar":[5],"tools":[6],"and":[7,90],"motions":[8],"in":[9,16,51],"egocentric":[10,52],"videos":[11,54],"is":[12],"a":[13,41],"challenging":[14],"task":[15],"computer":[17],"vision.":[18],"In":[19,99],"general,":[20],"to":[21],"distinguish":[22],"such":[23],"actions,":[24],"humans":[25],"often":[26],"focus":[27],"on":[28],"the":[29,33,63,67,84,88,105,108],"resultant":[30],"state":[31,86],"manipulated":[34],"objects.":[35],"From":[36],"this":[37,100],"perspective,":[38],"we":[39,102],"propose":[40],"novel":[42],"action":[44],"recognition":[45],"method":[46,110],"that":[47,81],"leverages":[48],"object":[49],"states":[50],"cooking":[53],"through":[55],"three":[56],"key":[57,76],"components:":[58],"1)":[59],"precise":[60],"extraction":[61],"region":[64],"containing":[65],"only":[66],"food":[68],"ingredient,":[69],"reducing":[70],"background":[71],"noise;":[72],"2)":[73],"selection":[74],"frames":[77],"(\"End":[78],"State":[79],"frames\")":[80],"clearly":[82],"reflect":[83],"post-action":[85],"object;":[89],"3)":[91],"augmentation":[92],"training":[94],"data":[95],"using":[96],"generated":[97],"images.":[98],"paper,":[101],"empirically":[103],"demonstrate":[104],"effectiveness":[106],"proposed":[109],"with":[111],"our":[112],"own":[113],"dataset.":[114]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}