{"id":"https://openalex.org/W4408537129","doi":"https://doi.org/10.1007/s44267-025-00074-1","title":"Enhancing human-centered dynamic scene understanding via multiple LLMs collaborated reasoning","display_name":"Enhancing human-centered dynamic scene understanding via multiple LLMs collaborated reasoning","publication_year":2025,"publication_date":"2025-03-17","ids":{"openalex":"https://openalex.org/W4408537129","doi":"https://doi.org/10.1007/s44267-025-00074-1"},"language":"en","primary_location":{"id":"doi:10.1007/s44267-025-00074-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44267-025-00074-1","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44267-025-00074-1.pdf","source":{"id":"https://openalex.org/S4387289164","display_name":"Visual Intelligence","issn_l":"2731-9008","issn":["2731-9008","2097-3330"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Visual Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://link.springer.com/content/pdf/10.1007/s44267-025-00074-1.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Hang Zhang","orcid":"https://orcid.org/0009-0002-1203-3363"},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hang Zhang","raw_affiliation_strings":["Singapore University of Technology and Design, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0009-0002-1203-3363","affiliations":[{"raw_affiliation_string":"Singapore University of Technology and Design, Singapore, Singapore","institution_ids":["https://openalex.org/I152815399"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042674424","display_name":"Wenxiao Zhang","orcid":"https://orcid.org/0000-0001-8680-6010"},"institutions":[{"id":"https://openalex.org/I163340411","display_name":"Hohai University","ror":"https://ror.org/01wd4xt90","country_code":"CN","type":"education","lineage":["https://openalex.org/I163340411"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenxiao Zhang","raw_affiliation_strings":["Hohai University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-8680-6010","affiliations":[{"raw_affiliation_string":"Hohai University, Nanjing, China","institution_ids":["https://openalex.org/I163340411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006002393","display_name":"Haoxuan Qu","orcid":"https://orcid.org/0000-0001-5054-3394"},"institutions":[{"id":"https://openalex.org/I67415387","display_name":"Lancaster University","ror":"https://ror.org/04f2nsd36","country_code":"GB","type":"education","lineage":["https://openalex.org/I67415387"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Haoxuan Qu","raw_affiliation_strings":["Lancaster University, Lancaster, UK"],"raw_orcid":"https://orcid.org/0000-0001-5054-3394","affiliations":[{"raw_affiliation_string":"Lancaster University, Lancaster, UK","institution_ids":["https://openalex.org/I67415387"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100361857","display_name":"Jun Liu","orcid":"https://orcid.org/0000-0002-4365-4165"},"institutions":[{"id":"https://openalex.org/I67415387","display_name":"Lancaster University","ror":"https://ror.org/04f2nsd36","country_code":"GB","type":"education","lineage":["https://openalex.org/I67415387"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Jun Liu","raw_affiliation_strings":["Lancaster University, Lancaster, UK"],"raw_orcid":"https://orcid.org/0000-0002-4365-4165","affiliations":[{"raw_affiliation_string":"Lancaster University, Lancaster, UK","institution_ids":["https://openalex.org/I67415387"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100361857"],"corresponding_institution_ids":["https://openalex.org/I67415387"],"apc_list":null,"apc_paid":null,"fwci":9.1863,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.98163705,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"3","issue":"1","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":0.9969000220298767,"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":0.9969000220298767,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9943000078201294,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.9934999942779541,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/computer-science","display_name":"Computer science","score":0.3307730257511139}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3307730257511139}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s44267-025-00074-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44267-025-00074-1","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44267-025-00074-1.pdf","source":{"id":"https://openalex.org/S4387289164","display_name":"Visual Intelligence","issn_l":"2731-9008","issn":["2731-9008","2097-3330"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Visual Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:3c791fa0f62f46a4ab84071b067b56c5","is_oa":true,"landing_page_url":"https://doaj.org/article/3c791fa0f62f46a4ab84071b067b56c5","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Visual Intelligence, Vol 3, Iss 1, Pp 1-11 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s44267-025-00074-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44267-025-00074-1","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44267-025-00074-1.pdf","source":{"id":"https://openalex.org/S4387289164","display_name":"Visual Intelligence","issn_l":"2731-9008","issn":["2731-9008","2097-3330"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Visual Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4408537129.pdf"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W1583837637","https://openalex.org/W2176353499","https://openalex.org/W2186222003","https://openalex.org/W2602856279","https://openalex.org/W2608915011","https://openalex.org/W2623660146","https://openalex.org/W2766666366","https://openalex.org/W2888096830","https://openalex.org/W2914304175","https://openalex.org/W2962995070","https://openalex.org/W2997856838","https://openalex.org/W3014792118","https://openalex.org/W3016522925","https://openalex.org/W3034679267","https://openalex.org/W3042546157","https://openalex.org/W3090476579","https://openalex.org/W3096057444","https://openalex.org/W3097802466","https://openalex.org/W3106121867","https://openalex.org/W3106988096","https://openalex.org/W3135367836","https://openalex.org/W3164894587","https://openalex.org/W3171037368","https://openalex.org/W3186621246","https://openalex.org/W3207158043","https://openalex.org/W4200498145","https://openalex.org/W4221143046","https://openalex.org/W4225323055","https://openalex.org/W4236965008","https://openalex.org/W4248927948","https://openalex.org/W4281761811","https://openalex.org/W4288055698","https://openalex.org/W4313788019","https://openalex.org/W4318718936","https://openalex.org/W4366566341","https://openalex.org/W4376654038","https://openalex.org/W4377372007","https://openalex.org/W4378498608","https://openalex.org/W4378508644","https://openalex.org/W4378675697","https://openalex.org/W4385571689","https://openalex.org/W4390871962","https://openalex.org/W4404782209","https://openalex.org/W6802927479","https://openalex.org/W6803651140"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Abstract":[0],"Human-centered":[1],"dynamic":[2],"scene":[3,30],"understanding":[4],"plays":[5],"a":[6,25,40,94,99,130,148,193],"pivotal":[7],"role":[8],"in":[9,28,63,142,181,221],"enhancing":[10],"the":[11,44,72,107,116,138,143,154,163,172,178,199,212,223,227],"capability":[12],"of":[13,47,76,98,101,109,120,134,214,226],"robotic":[14],"and":[15,50],"autonomous":[16,51],"systems,":[17],"where":[18],"video-based":[19],"human-object":[20],"interaction":[21],"(V-HOI)":[22],"detection":[23,57,65,112],"is":[24],"crucial":[26],"task":[27],"semantic":[29],"understanding,":[31],"which":[32],"aims":[33],"to":[34,42,78,152,156,170,197,205],"comprehensively":[35],"understand":[36],"HOI":[37,81],"relationships":[38],"within":[39],"video":[41],"benefit":[43],"behavioral":[45],"decisions":[46],"mobile":[48],"robots":[49],"driving":[52],"systems.":[53],"Although":[54],"previous":[55],"V-HOI":[56,88,111,139,201,229],"models":[58,113,126],"have":[59],"made":[60],"significant":[61],"advances":[62],"accurate":[64],"on":[66,177],"specific":[67],"datasets,":[68],"they":[69],"still":[70],"lack":[71],"general":[73],"reasoning":[74,91,118,150,158,174,232],"ability":[75,119,204],"humans":[77],"effectively":[79],"induce":[80],"relationships.":[82],"In":[83,162],"this":[84],"study,":[85],"we":[86,146,166,185],"propose":[87],"multi-LLMs":[89,168],"collaborated":[90],"(V-HOI":[92],"MLCR),":[93],"novel":[95],"framework":[96],"consisting":[97],"series":[100],"plug-and-play":[102],"modules":[103],"that":[104],"could":[105],"facilitate":[106],"performance":[108],"current":[110],"by":[114,217],"leveraging":[115],"strong":[117],"different":[121,135,160,179,182],"off-the-shelf":[122],"pre-trained":[123],"large":[124,194],"language":[125],"(LLMs).":[127],"We":[128,210],"design":[129,147,216],"two-stage":[131],"collaboration":[132],"system":[133],"LLMs":[136],"for":[137],"task.":[140],"Specifically,":[141],"first":[144],"stage,":[145,165],"cross-agents":[149],"scheme":[151],"leverage":[153],"LLM":[155],"perform":[157,167],"from":[159,233],"aspects.":[161],"second":[164],"debate":[169],"get":[171],"final":[173],"answer":[175],"based":[176],"knowledge":[180],"LLMs.":[183,209],"Additionally,":[184],"develop":[186],"an":[187],"auxiliary":[188],"training":[189],"strategy":[190],"using":[191],"CLIP,":[192],"vision-language":[195],"model":[196,230],"enhance":[198],"base":[200,228],"models\u2019":[202],"discriminative":[203],"better":[206],"cooperate":[207],"with":[208],"validate":[211],"superiority":[213],"our":[215],"demonstrating":[218],"its":[219],"effectiveness":[220],"improving":[222],"predictive":[224],"accuracy":[225],"through":[231],"multiple":[234],"perspectives.":[235]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":11}],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2025-10-10T00:00:00"}