{"id":"https://openalex.org/W4415821931","doi":"https://doi.org/10.1109/ro-man63969.2025.11217803","title":"Context-Aware Human Behavior Prediction Using Multimodal Large Language Models: Challenges and Insights","display_name":"Context-Aware Human Behavior Prediction Using Multimodal Large Language Models: Challenges and Insights","publication_year":2025,"publication_date":"2025-08-25","ids":{"openalex":"https://openalex.org/W4415821931","doi":"https://doi.org/10.1109/ro-man63969.2025.11217803"},"language":null,"primary_location":{"id":"doi:10.1109/ro-man63969.2025.11217803","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ro-man63969.2025.11217803","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 34th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5103016287","display_name":"Yuchen Liu","orcid":"https://orcid.org/0000-0001-9217-1795"},"institutions":[{"id":"https://openalex.org/I889804353","display_name":"Robert Bosch (Germany)","ror":"https://ror.org/01fe0jt45","country_code":"DE","type":"company","lineage":["https://openalex.org/I889804353"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Yuchen Liu","raw_affiliation_strings":["Robert Bosch GmbH,Corporate Sector Research and Advance Engineering,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robert Bosch GmbH,Corporate Sector Research and Advance Engineering,Germany","institution_ids":["https://openalex.org/I889804353"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120235810","display_name":"Lino Lerch","orcid":null},"institutions":[{"id":"https://openalex.org/I196349391","display_name":"Universit\u00e4t Ulm","ror":"https://ror.org/032000t02","country_code":"DE","type":"education","lineage":["https://openalex.org/I196349391"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Lino Lerch","raw_affiliation_strings":["Ulm University,Visual Computing Group,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ulm University,Visual Computing Group,Germany","institution_ids":["https://openalex.org/I196349391"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017989436","display_name":"Luigi Palmieri","orcid":"https://orcid.org/0000-0002-4908-5434"},"institutions":[{"id":"https://openalex.org/I889804353","display_name":"Robert Bosch (Germany)","ror":"https://ror.org/01fe0jt45","country_code":"DE","type":"company","lineage":["https://openalex.org/I889804353"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Luigi Palmieri","raw_affiliation_strings":["Robert Bosch GmbH,Corporate Sector Research and Advance Engineering,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robert Bosch GmbH,Corporate Sector Research and Advance Engineering,Germany","institution_ids":["https://openalex.org/I889804353"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046610614","display_name":"Andrey Rudenko","orcid":"https://orcid.org/0000-0002-2181-3444"},"institutions":[{"id":"https://openalex.org/I889804353","display_name":"Robert Bosch (Germany)","ror":"https://ror.org/01fe0jt45","country_code":"DE","type":"company","lineage":["https://openalex.org/I889804353"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Andrey Rudenko","raw_affiliation_strings":["Robert Bosch GmbH,Corporate Sector Research and Advance Engineering,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robert Bosch GmbH,Corporate Sector Research and Advance Engineering,Germany","institution_ids":["https://openalex.org/I889804353"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101622191","display_name":"Sebastian Koch","orcid":"https://orcid.org/0009-0007-5777-3206"},"institutions":[{"id":"https://openalex.org/I889804353","display_name":"Robert Bosch (Germany)","ror":"https://ror.org/01fe0jt45","country_code":"DE","type":"company","lineage":["https://openalex.org/I889804353"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sebastian Koch","raw_affiliation_strings":["Robert Bosch GmbH,Corporate Sector Research and Advance Engineering,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robert Bosch GmbH,Corporate Sector Research and Advance Engineering,Germany","institution_ids":["https://openalex.org/I889804353"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061059879","display_name":"Timo Ropinski","orcid":"https://orcid.org/0000-0002-7857-5512"},"institutions":[{"id":"https://openalex.org/I196349391","display_name":"Universit\u00e4t Ulm","ror":"https://ror.org/032000t02","country_code":"DE","type":"education","lineage":["https://openalex.org/I196349391"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Timo Ropinski","raw_affiliation_strings":["Ulm University,Visual Computing Group,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ulm University,Visual Computing Group,Germany","institution_ids":["https://openalex.org/I196349391"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077212321","display_name":"Marco Aiello","orcid":"https://orcid.org/0000-0002-0764-2124"},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Marco Aiello","raw_affiliation_strings":["University of Stuttgart,Institute of Architecture of Application Systems,Service Computing Department,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Stuttgart,Institute of Architecture of Application Systems,Service Computing Department,Germany","institution_ids":["https://openalex.org/I100066346"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1151","last_page":"1158"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.590399980545044,"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":0.590399980545044,"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/T10028","display_name":"Topic Modeling","score":0.050999999046325684,"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"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.04740000143647194,"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/generalization","display_name":"Generalization","score":0.6753000020980835},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6402000188827515},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.5688999891281128},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.435699999332428},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.37860000133514404},{"id":"https://openalex.org/keywords/human-behavior","display_name":"Human behavior","score":0.3476000130176544},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.3361999988555908},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3321000039577484}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7423999905586243},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6798999905586243},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6753000020980835},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6665999889373779},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6402000188827515},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.5688999891281128},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.435699999332428},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.37860000133514404},{"id":"https://openalex.org/C117035363","wikidata":"https://www.wikidata.org/wiki/Q3769299","display_name":"Human behavior","level":2,"score":0.3476000130176544},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.3361999988555908},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3321000039577484},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3174000084400177},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.30219998955726624},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.296099990606308},{"id":"https://openalex.org/C121687571","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Activity recognition","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.2865000069141388},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2822999954223633},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.2565000057220459},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ro-man63969.2025.11217803","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ro-man63969.2025.11217803","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 34th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2059993653","https://openalex.org/W2424778531","https://openalex.org/W2810685774","https://openalex.org/W2941818575","https://openalex.org/W2963001155","https://openalex.org/W2963570630","https://openalex.org/W2982275673","https://openalex.org/W3033920763","https://openalex.org/W3109597949","https://openalex.org/W3197128667","https://openalex.org/W3205786327","https://openalex.org/W4283780626","https://openalex.org/W4298128166","https://openalex.org/W4313182738","https://openalex.org/W4380372542","https://openalex.org/W4401415105","https://openalex.org/W4402508433","https://openalex.org/W4402670262","https://openalex.org/W4402969043","https://openalex.org/W4403446304","https://openalex.org/W4413146669","https://openalex.org/W4413945106","https://openalex.org/W4415743520"],"related_works":[],"abstract_inverted_index":{"Predicting":[0],"human":[1,47,116,127,168],"behavior":[2,117],"in":[3,35,52,78,166,170],"shared":[4],"environments":[5],"is":[6,154],"crucial":[7],"for":[8,83,90,114],"safe":[9],"and":[10,27,49,72,99,143,161],"efficient":[11],"human-robot":[12],"interaction.":[13],"Traditional":[14],"data-driven":[15],"methods":[16],"to":[17,44,62,96,134,156],"that":[18,131,149],"end":[19],"are":[20,60],"pre-trained":[21,112],"on":[22],"domain-specific":[23],"datasets,":[24],"activity":[25,128],"types,":[26],"prediction":[28,84,129],"horizons.":[29],"In":[30,55,102],"contrast,":[31],"the":[32,150,171],"recent":[33],"breakthroughs":[34],"Large":[36],"Language":[37],"Models":[38],"(LLMs)":[39],"promise":[40],"open-ended":[41],"cross-domain":[42],"generalization":[43],"describe":[45],"various":[46,66,136],"activities":[48],"make":[50],"predictions":[51],"any":[53],"context.":[54],"particular,":[56],"Multimodal":[57],"LLMs":[58],"(MLLMs)":[59],"able":[61,155],"integrate":[63],"information":[64],"from":[65,86],"sources,":[67],"achieving":[68],"more":[69],"contextual":[70],"awareness":[71],"improved":[73],"scene":[74],"understanding.":[75],"The":[76],"difficulty":[77],"applying":[79,111],"general-purpose":[80],"MLLMs":[81,113],"directly":[82],"stems":[85],"their":[87],"limited":[88],"capacity":[89],"processing":[91],"large":[92],"input":[93,138],"sequences,":[94],"sensitivity":[95],"prompt":[97],"design,":[98],"expensive":[100],"fine-tuning.":[101],"this":[103,120],"paper,":[104],"we":[105,122],"present":[106],"a":[107,124],"systematic":[108],"analysis":[109],"of":[110],"context-aware":[115],"prediction.":[118],"To":[119],"end,":[121],"introduce":[123],"modular":[125],"multimodal":[126],"framework":[130,152],"allows":[132],"us":[133],"benchmark":[135],"MLLMs,":[137],"variations,":[139],"In-Context":[140],"Learning":[141],"(ICL),":[142],"autoregressive":[144],"techniques.":[145],"Our":[146],"evaluation":[147],"indicates":[148],"best-performing":[151],"configuration":[153],"reach":[157],"92.8%":[158],"semantic":[159],"similarity":[160],"66.1%":[162],"exact":[163],"label":[164],"accuracy":[165],"predicting":[167],"behaviors":[169],"target":[172],"frame.":[173],"Project":[174],"webpage:":[175],"https://cap-mllm.github.io/":[176]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-03T00:00:00"}