{"id":"https://openalex.org/W4408352437","doi":"https://doi.org/10.1109/icassp49660.2025.10890689","title":"OV-HHIR: Open Vocabulary Human Interaction Recognition Using Cross-modal Integration of Large Language Models","display_name":"OV-HHIR: Open Vocabulary Human Interaction Recognition Using Cross-modal Integration of Large Language Models","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352437","doi":"https://doi.org/10.1109/icassp49660.2025.10890689"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890689","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890689","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5090096476","display_name":"Lala Shakti Swarup Ray","orcid":"https://orcid.org/0000-0002-7133-0205"},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Lala Shakti Swarup Ray","raw_affiliation_strings":["German Research Center for Artificial Intelligence (DFKI),Germany"],"affiliations":[{"raw_affiliation_string":"German Research Center for Artificial Intelligence (DFKI),Germany","institution_ids":["https://openalex.org/I33256026"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059956294","display_name":"Bo Zhou","orcid":"https://orcid.org/0000-0002-8976-5960"},"institutions":[{"id":"https://openalex.org/I4387152675","display_name":"Rheinland-Pf\u00e4lzische Technische Universit\u00e4t Kaiserslautern-Landau","ror":"https://ror.org/01qrts582","country_code":null,"type":"education","lineage":["https://openalex.org/I4387152675"]},{"id":"https://openalex.org/I2802076133","display_name":"University of Koblenz and Landau","ror":"https://ror.org/01j9f6752","country_code":"DE","type":"education","lineage":["https://openalex.org/I2802076133"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bo Zhou","raw_affiliation_strings":["RPTU Kaiserslautern-Landau,Department of Computer Science,Germany"],"affiliations":[{"raw_affiliation_string":"RPTU Kaiserslautern-Landau,Department of Computer Science,Germany","institution_ids":["https://openalex.org/I2802076133","https://openalex.org/I4387152675"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057986515","display_name":"Sungho Suh","orcid":"https://orcid.org/0000-0003-3723-1980"},"institutions":[{"id":"https://openalex.org/I2802076133","display_name":"University of Koblenz and Landau","ror":"https://ror.org/01j9f6752","country_code":"DE","type":"education","lineage":["https://openalex.org/I2802076133"]},{"id":"https://openalex.org/I4387152675","display_name":"Rheinland-Pf\u00e4lzische Technische Universit\u00e4t Kaiserslautern-Landau","ror":"https://ror.org/01qrts582","country_code":null,"type":"education","lineage":["https://openalex.org/I4387152675"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sungho Suh","raw_affiliation_strings":["RPTU Kaiserslautern-Landau,Department of Computer Science,Germany"],"affiliations":[{"raw_affiliation_string":"RPTU Kaiserslautern-Landau,Department of Computer Science,Germany","institution_ids":["https://openalex.org/I2802076133","https://openalex.org/I4387152675"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063453660","display_name":"Paul Lukowicz","orcid":"https://orcid.org/0000-0003-0320-6656"},"institutions":[{"id":"https://openalex.org/I2802076133","display_name":"University of Koblenz and Landau","ror":"https://ror.org/01j9f6752","country_code":"DE","type":"education","lineage":["https://openalex.org/I2802076133"]},{"id":"https://openalex.org/I4387152675","display_name":"Rheinland-Pf\u00e4lzische Technische Universit\u00e4t Kaiserslautern-Landau","ror":"https://ror.org/01qrts582","country_code":null,"type":"education","lineage":["https://openalex.org/I4387152675"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Paul Lukowicz","raw_affiliation_strings":["RPTU Kaiserslautern-Landau,Department of Computer Science,Germany"],"affiliations":[{"raw_affiliation_string":"RPTU Kaiserslautern-Landau,Department of Computer Science,Germany","institution_ids":["https://openalex.org/I2802076133","https://openalex.org/I4387152675"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5090096476"],"corresponding_institution_ids":["https://openalex.org/I33256026"],"apc_list":null,"apc_paid":null,"fwci":5.7199,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.94905572,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9498000144958496,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9498000144958496,"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/T12031","display_name":"Speech and dialogue systems","score":0.935699999332428,"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":0.7782799005508423},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6235707402229309},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6055906414985657},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4924534261226654},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4376106262207031},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.41662928462028503},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.32499271631240845},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.24010562896728516}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7782799005508423},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6235707402229309},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6055906414985657},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4924534261226654},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4376106262207031},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41662928462028503},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32499271631240845},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.24010562896728516},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890689","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890689","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5699999928474426,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W2058256495","https://openalex.org/W2094016507","https://openalex.org/W2163292664","https://openalex.org/W2167626157","https://openalex.org/W2803001816","https://openalex.org/W2944006115","https://openalex.org/W3106615203","https://openalex.org/W3119567997","https://openalex.org/W3121523901","https://openalex.org/W3126694748","https://openalex.org/W4312757522","https://openalex.org/W4388660710","https://openalex.org/W4389519587","https://openalex.org/W4390874575","https://openalex.org/W4392866655","https://openalex.org/W4393149524","https://openalex.org/W4395028953","https://openalex.org/W4400648811","https://openalex.org/W4402753598","https://openalex.org/W4404007800","https://openalex.org/W4404892967","https://openalex.org/W4410987571","https://openalex.org/W6784333009","https://openalex.org/W6796581206","https://openalex.org/W6809664228","https://openalex.org/W6810874553","https://openalex.org/W6849177959","https://openalex.org/W6850625674","https://openalex.org/W6852276098","https://openalex.org/W6852699137","https://openalex.org/W6852796095","https://openalex.org/W6853111301","https://openalex.org/W6854866820","https://openalex.org/W6855970221","https://openalex.org/W6862397664","https://openalex.org/W6870122244","https://openalex.org/W6955071965"],"related_works":["https://openalex.org/W2349784553","https://openalex.org/W3022596247","https://openalex.org/W2601444686","https://openalex.org/W4307058054","https://openalex.org/W4292238148","https://openalex.org/W4323660495","https://openalex.org/W2385319785","https://openalex.org/W2900827440","https://openalex.org/W3167549738","https://openalex.org/W2381983017"],"abstract_inverted_index":{"Understanding":[0],"human-to-human":[1,67,105],"interactions,":[2],"especially":[3],"in":[4,89,151],"contexts":[5],"like":[6],"public":[7,113],"security":[8],"surveillance,":[9],"is":[10],"critical":[11],"for":[12,137,143],"monitoring":[13],"and":[14,28,38,57,85,110,132,146,153],"maintaining":[15],"safety.":[16],"Traditional":[17],"activity":[18],"recognition":[19,69],"systems":[20,47,131,150],"are":[21,55],"limited":[22],"by":[23,108],"fixed":[24,97],"vocabularies,":[25],"predefined":[26],"labels,":[27],"rigid":[29],"interaction":[30,68,106,115],"categories":[31],"that":[32,72,124],"often":[33],"rely":[34],"on":[35],"choreographed":[36],"videos":[37],"overlook":[39],"concurrent":[40],"interactive":[41],"groups.":[42],"These":[43],"limitations":[44],"make":[45],"such":[46],"less":[48],"adaptable":[49,147],"to":[50,77,95],"real-world":[51],"scenarios,":[52],"where":[53],"interactions":[54,88],"diverse":[56],"unpredictable.":[58],"In":[59],"this":[60],"paper,":[61],"we":[62,100],"propose":[63],"an":[64],"open":[65],"vocabulary":[66],"(OV-HHIR)":[70],"framework":[71],"leverages":[73],"large":[74],"language":[75,135],"models":[76,136],"generate":[78],"open-ended":[79],"textual":[80],"descriptions":[81],"of":[82],"both":[83],"seen":[84],"unseen":[86],"human":[87,114],"open-world":[90],"settings":[91],"without":[92],"being":[93],"confined":[94],"a":[96,102,118],"vocabulary.":[98],"Additionally,":[99],"create":[101],"comprehensive,":[103],"large-scale":[104],"dataset":[107],"standardizing":[109],"combining":[111],"existing":[112,133],"datasets":[116],"into":[117],"unified":[119],"benchmark.":[120],"Extensive":[121],"experiments":[122],"demonstrate":[123],"our":[125],"method":[126],"outperforms":[127],"traditional":[128],"fixed-vocabulary":[129],"classification":[130],"cross-modal":[134],"video":[138],"understanding,":[139],"setting":[140],"the":[141],"stage":[142],"more":[144],"intelligent":[145],"visual":[148],"understanding":[149],"surveillance":[152],"beyond.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-19T19:40:27.379048","created_date":"2025-10-10T00:00:00"}