{"id":"https://openalex.org/W4408803784","doi":"https://doi.org/10.1007/978-981-96-3525-2_25","title":"Comparing Apples to\u00a0Oranges: LLM-Powered Multimodal Intention Prediction in\u00a0an\u00a0Object Categorization Task","display_name":"Comparing Apples to\u00a0Oranges: LLM-Powered Multimodal Intention Prediction in\u00a0an\u00a0Object Categorization Task","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4408803784","doi":"https://doi.org/10.1007/978-981-96-3525-2_25"},"language":"en","primary_location":{"id":"doi:10.1007/978-981-96-3525-2_25","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-981-96-3525-2_25","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-981-96-3525-2_25.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"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":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/978-981-96-3525-2_25.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065397477","display_name":"Hassan Ali","orcid":"https://orcid.org/0000-0001-9907-1834"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Hassan Ali","raw_affiliation_strings":["Knowledge Technology, Department of Informatics, University of Hamburg, Hamburg, Germany"],"affiliations":[{"raw_affiliation_string":"Knowledge Technology, Department of Informatics, University of Hamburg, Hamburg, Germany","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046907706","display_name":"Philipp Allgeuer","orcid":"https://orcid.org/0000-0002-2355-0764"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Philipp Allgeuer","raw_affiliation_strings":["Knowledge Technology, Department of Informatics, University of Hamburg, Hamburg, Germany"],"affiliations":[{"raw_affiliation_string":"Knowledge Technology, Department of Informatics, University of Hamburg, Hamburg, Germany","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033486668","display_name":"Stefan Wermter","orcid":"https://orcid.org/0000-0003-1343-4775"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stefan Wermter","raw_affiliation_strings":["Knowledge Technology, Department of Informatics, University of Hamburg, Hamburg, Germany"],"affiliations":[{"raw_affiliation_string":"Knowledge Technology, Department of Informatics, University of Hamburg, Hamburg, Germany","institution_ids":["https://openalex.org/I159176309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5065397477"],"corresponding_institution_ids":["https://openalex.org/I159176309"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":{"value":5000,"currency":"EUR","value_usd":5392},"fwci":18.6368,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.99021991,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"292","last_page":"306"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9980000257492065,"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"}},"topics":[{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9980000257492065,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9923999905586243,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9901999831199646,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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":0.823401689529419},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.8185098171234131},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7048133015632629},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5980515480041504},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.529717206954956},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35222312808036804},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.336331307888031}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.823401689529419},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.8185098171234131},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7048133015632629},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5980515480041504},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.529717206954956},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35222312808036804},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.336331307888031},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-981-96-3525-2_25","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-981-96-3525-2_25","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-981-96-3525-2_25.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"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":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.1007/978-981-96-3525-2_25","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-981-96-3525-2_25","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-981-96-3525-2_25.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"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":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4408803784.pdf"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W3149531584","https://openalex.org/W3188150843","https://openalex.org/W3203663966","https://openalex.org/W3205159809","https://openalex.org/W4304195432","https://openalex.org/W4311000453","https://openalex.org/W4312272452","https://openalex.org/W4384522229","https://openalex.org/W4386939539","https://openalex.org/W4387459515","https://openalex.org/W4387993547","https://openalex.org/W4388145436","https://openalex.org/W4388623928","https://openalex.org/W4389010438","https://openalex.org/W4389282400","https://openalex.org/W4389665836","https://openalex.org/W4390306114","https://openalex.org/W4391417118","https://openalex.org/W4396832345","https://openalex.org/W4401415105","https://openalex.org/W4402754023","https://openalex.org/W4402819134","https://openalex.org/W6600168703","https://openalex.org/W6600804206","https://openalex.org/W6605995128"],"related_works":["https://openalex.org/W2165912799","https://openalex.org/W2735662278","https://openalex.org/W2382615723","https://openalex.org/W4405331580","https://openalex.org/W4311804456","https://openalex.org/W2115592544","https://openalex.org/W2093773434","https://openalex.org/W2732813147","https://openalex.org/W2143460112","https://openalex.org/W2042906257"],"abstract_inverted_index":{"Abstract":[0],"Human":[1],"intention-based":[2],"systems":[3],"enable":[4],"robots":[5,34],"to":[6,12,18,48,88,118],"perceive":[7],"and":[8,16,78,84,108,115],"interpret":[9],"user":[10,70,85,90,110],"actions":[11],"interact":[13],"with":[14,32,58,81,127],"humans":[15],"adapt":[17],"their":[19,113],"behavior":[20],"proactively.":[21],"Therefore,":[22],"intention":[23,51,120],"prediction":[24,121],"is":[25],"pivotal":[26],"in":[27,35,52,92],"creating":[28],"a":[29,53,59,64,93,125,128],"natural":[30],"interaction":[31],"social":[33,129],"human-designed":[36],"environments.":[37],"In":[38],"this":[39],"paper,":[40],"we":[41],"examine":[42],"using":[43],"Large":[44],"Language":[45],"Models":[46],"(LLMs)":[47],"infer":[49],"human":[50],"collaborative":[54],"object":[55],"categorization":[56],"task":[57,126],"physical":[60],"robot.":[61,130],"We":[62],"propose":[63],"novel":[65],"multimodal":[66],"approach":[67],"that":[68],"integrates":[69],"non-verbal":[71,109],"cues,":[72,111],"like":[73],"hand":[74],"gestures,":[75],"body":[76],"poses,":[77],"facial":[79],"expressions,":[80],"environment":[82],"states":[83],"verbal":[86,107],"cues":[87],"predict":[89],"intentions":[91],"hierarchical":[94],"architecture.":[95],"Our":[96],"evaluation":[97],"of":[98],"five":[99],"LLMs":[100],"shows":[101],"the":[102],"potential":[103],"for":[104],"reasoning":[105],"about":[106],"leveraging":[112],"context-understanding":[114],"real-world":[116],"knowledge":[117],"support":[119],"while":[122],"collaborating":[123],"on":[124],"Video:":[131],"https://youtu.be/tBJHfAuzohI":[132]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}
