{"id":"https://openalex.org/W4413018430","doi":"https://doi.org/10.1109/fg61629.2025.11099276","title":"ActRecognition-GPT: Utilizing Multimodal Large Language Models for Spatiotemporal Action Recognition in Nursery Videos","display_name":"ActRecognition-GPT: Utilizing Multimodal Large Language Models for Spatiotemporal Action Recognition in Nursery Videos","publication_year":2025,"publication_date":"2025-05-26","ids":{"openalex":"https://openalex.org/W4413018430","doi":"https://doi.org/10.1109/fg61629.2025.11099276"},"language":"en","primary_location":{"id":"doi:10.1109/fg61629.2025.11099276","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fg61629.2025.11099276","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 19th International Conference on Automatic Face and Gesture Recognition (FG)","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/A5009660351","display_name":"Kenta Watanabe","orcid":"https://orcid.org/0000-0002-3357-7207"},"institutions":[{"id":"https://openalex.org/I14396692","display_name":"Tokyo University of Information Sciences","ror":"https://ror.org/044bdx604","country_code":"JP","type":"education","lineage":["https://openalex.org/I14396692"]},{"id":"https://openalex.org/I161296585","display_name":"Tokyo University of Science","ror":"https://ror.org/05sj3n476","country_code":"JP","type":"education","lineage":["https://openalex.org/I161296585"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Kenta Watanabe","raw_affiliation_strings":["The University of Tokyo,Graduate School of Information Science and Technology,Department of Information and Communication Engineering,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Graduate School of Information Science and Technology,Department of Information and Communication Engineering,Tokyo,Japan","institution_ids":["https://openalex.org/I14396692","https://openalex.org/I161296585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000354904","display_name":"Shuntaro Masuda","orcid":"https://orcid.org/0009-0008-2490-9557"},"institutions":[{"id":"https://openalex.org/I14396692","display_name":"Tokyo University of Information Sciences","ror":"https://ror.org/044bdx604","country_code":"JP","type":"education","lineage":["https://openalex.org/I14396692"]},{"id":"https://openalex.org/I161296585","display_name":"Tokyo University of Science","ror":"https://ror.org/05sj3n476","country_code":"JP","type":"education","lineage":["https://openalex.org/I161296585"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shuntaro Masuda","raw_affiliation_strings":["The University of Tokyo,Graduate School of Information Science and Technology,Department of Information and Communication Engineering,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Graduate School of Information Science and Technology,Department of Information and Communication Engineering,Tokyo,Japan","institution_ids":["https://openalex.org/I14396692","https://openalex.org/I161296585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101476674","display_name":"Ling Xiao","orcid":"https://orcid.org/0000-0002-4650-8841"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ling Xiao","raw_affiliation_strings":["Hokkaido University,Graduate School of Information Science,Sapporo,Japan"],"affiliations":[{"raw_affiliation_string":"Hokkaido University,Graduate School of Information Science,Sapporo,Japan","institution_ids":["https://openalex.org/I205349734"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048624196","display_name":"Toshihiko Yamasaki","orcid":"https://orcid.org/0000-0002-1784-2314"},"institutions":[{"id":"https://openalex.org/I14396692","display_name":"Tokyo University of Information Sciences","ror":"https://ror.org/044bdx604","country_code":"JP","type":"education","lineage":["https://openalex.org/I14396692"]},{"id":"https://openalex.org/I161296585","display_name":"Tokyo University of Science","ror":"https://ror.org/05sj3n476","country_code":"JP","type":"education","lineage":["https://openalex.org/I161296585"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Toshihiko Yamasaki","raw_affiliation_strings":["The University of Tokyo,Graduate School of Information Science and Technology,Department of Information and Communication Engineering,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Graduate School of Information Science and Technology,Department of Information and Communication Engineering,Tokyo,Japan","institution_ids":["https://openalex.org/I14396692","https://openalex.org/I161296585"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5009660351"],"corresponding_institution_ids":["https://openalex.org/I14396692","https://openalex.org/I161296585"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22979764,"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":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9345999956130981,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9345999956130981,"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/action-recognition","display_name":"Action recognition","score":0.7851625680923462},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7715615630149841},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5563995838165283},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5276326537132263},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4716609716415405},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.368291437625885}],"concepts":[{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.7851625680923462},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7715615630149841},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5563995838165283},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5276326537132263},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4716609716415405},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.368291437625885},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fg61629.2025.11099276","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fg61629.2025.11099276","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 19th International Conference on Automatic Face and Gesture Recognition (FG)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322832","display_name":"University of Tokyo","ror":"https://ror.org/057zh3y96"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1983364832","https://openalex.org/W2061773916","https://openalex.org/W2618799552","https://openalex.org/W2798472916","https://openalex.org/W2799794396","https://openalex.org/W2963037989","https://openalex.org/W2964220823","https://openalex.org/W2990503944","https://openalex.org/W3034572008","https://openalex.org/W3112065721","https://openalex.org/W3172990466","https://openalex.org/W3195209314","https://openalex.org/W4312509322","https://openalex.org/W4380149082","https://openalex.org/W4381468426","https://openalex.org/W4386076625","https://openalex.org/W4386113242","https://openalex.org/W4390874107","https://openalex.org/W4402716047","https://openalex.org/W4402716381","https://openalex.org/W4402727142","https://openalex.org/W4410706693","https://openalex.org/W6780707248","https://openalex.org/W6801567822","https://openalex.org/W6863925186","https://openalex.org/W6867851394","https://openalex.org/W6869462129"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Spatiotemporal":[0],"action":[1],"recognition":[2,89],"in":[3,158],"nursery":[4,151],"videos":[5],"is":[6,133],"essential":[7,135],"for":[8,137],"intelligent":[9],"childcare":[10],"systems":[11],"that":[12,54],"can":[13],"automatically":[14],"monitor":[15],"children\u2019s":[16],"behaviors,":[17,92],"detect":[18],"safety":[19],"risks,":[20],"and":[21,35,74,78,107,141],"generate":[22],"accurate":[23],"activity":[24],"logs":[25],"without":[26,127],"increasing":[27],"caregivers\u2019":[28],"burden.":[29],"However,":[30],"occlusions,":[31],"dynamic":[32],"multi-person":[33],"interactions,":[34],"subtle":[36],"distinctions":[37],"between":[38],"similar":[39],"actions":[40],"present":[41],"significant":[42,156],"challenges.":[43],"To":[44],"address":[45],"these":[46],"challenges,":[47],"we":[48],"introduce":[49],"ActRecognition-GPT,":[50],"a":[51,149,155],"multimodal":[52,64],"framework":[53],"combines":[55],"visual":[56,95,171],"object":[57],"detection":[58],"with":[59,173],"the":[60,84,112,139,166],"reasoning":[61],"capability":[62],"of":[63,90,115,144,168],"large":[65],"language":[66],"models":[67],"(MLLMs).":[68],"By":[69],"assigning":[70],"unique":[71],"person":[72],"IDs":[73],"incorporating":[75],"both":[76],"spatial":[77],"temporal":[79,175],"context":[80],"through":[81],"structured":[82,170],"prompts,":[83],"model":[85],"achieves":[86],"temporally":[87],"consistent":[88],"individual":[91],"even":[93],"under":[94],"ambiguity":[96],"or":[97,124],"occlusion.":[98],"Moreover,":[99],"predefined":[100],"vocabularies":[101],"are":[102],"used":[103],"to":[104,119,121],"constrain":[105],"generation":[106],"reduce":[108],"semantic":[109],"drift.":[110],"Crucially,":[111],"open-vocabulary":[113],"nature":[114],"MLLMs":[116],"enables":[117],"ActRecognition-GPT":[118],"generalize":[120],"previously":[122],"unseen":[123],"ambiguous":[125],"scenarios":[126],"requiring":[128],"extensive":[129],"labeled":[130],"data,":[131],"which":[132],"an":[134],"property":[136],"modeling":[138],"diverse":[140],"evolving":[142],"behaviors":[143],"children.":[145],"Experimental":[146],"results":[147],"on":[148],"real-world":[150],"video":[152],"dataset":[153],"demonstrate":[154],"improvement":[157],"mean":[159],"Average":[160],"Precision":[161],"over":[162],"single-frame":[163],"baselines,":[164],"validating":[165],"effectiveness":[167],"combining":[169],"inputs":[172],"LLM-based":[174],"reasoning.":[176]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}