{"id":"https://openalex.org/W4415536755","doi":"https://doi.org/10.1145/3746027.3762077","title":"LVLM-HBA: Large Vision-Language Model with Cross-Modal Alignment for Human Behavior Analysis","display_name":"LVLM-HBA: Large Vision-Language Model with Cross-Modal Alignment for Human Behavior Analysis","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415536755","doi":"https://doi.org/10.1145/3746027.3762077"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3762077","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3762077","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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/A5048818071","display_name":"Jun Yu","orcid":"https://orcid.org/0000-0002-3197-8103"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Yu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-3197-8103","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032096290","display_name":"Xilong Lu","orcid":"https://orcid.org/0009-0002-4655-6517"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xilong Lu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0002-4655-6517","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120131327","display_name":"Lingsi Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingsi Zhu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0002-6860-2772","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007719477","display_name":"Qiang Ling","orcid":"https://orcid.org/0000-0001-5688-4130"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Ling","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-5688-4130","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":1.4136,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.84744621,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"14156","last_page":"14162"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9994000196456909,"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":0.9994000196456909,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9993000030517578,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9904000163078308,"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/gaze","display_name":"Gaze","score":0.5008000135421753},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.445499986410141},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.44130000472068787},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.39430001378059387},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.35690000653266907},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.3440000116825104},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.3278999924659729},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.3221000134944916},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.314300000667572}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.729200005531311},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.611299991607666},{"id":"https://openalex.org/C2779916870","wikidata":"https://www.wikidata.org/wiki/Q14467155","display_name":"Gaze","level":2,"score":0.5008000135421753},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45879998803138733},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.445499986410141},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.44130000472068787},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.39430001378059387},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.35690000653266907},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.3440000116825104},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.3278999924659729},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3221000134944916},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.314300000667572},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.31290000677108765},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.29260000586509705},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2858999967575073},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2770000100135803},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.26460000872612},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.263700008392334},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.2581999897956848},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.25279998779296875},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.25189998745918274},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3762077","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3762077","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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":20,"referenced_works":["https://openalex.org/W2782668511","https://openalex.org/W2806887026","https://openalex.org/W2981851019","https://openalex.org/W3090449556","https://openalex.org/W3177709384","https://openalex.org/W3205504809","https://openalex.org/W3206879014","https://openalex.org/W4213019189","https://openalex.org/W4285606530","https://openalex.org/W4288099396","https://openalex.org/W4304099116","https://openalex.org/W4312910992","https://openalex.org/W4321101505","https://openalex.org/W4385964683","https://openalex.org/W4385965696","https://openalex.org/W4387968032","https://openalex.org/W4391216149","https://openalex.org/W4403780527","https://openalex.org/W4409366805","https://openalex.org/W4415538282"],"related_works":[],"abstract_inverted_index":{"Bodily":[0],"Behaviour":[1],"Recognition":[2],"(BBR)":[3],"and":[4,61,90,113,131,153,182],"Eye":[5],"Contact":[6],"Detection":[7],"(ECD)":[8],"in":[9,84,141,175],"multi-person":[10],"group":[11,188],"conversations":[12],"are":[13],"critical":[14],"for":[15,185],"understanding":[16,186],"social":[17,176],"dynamics,":[18],"but":[19],"traditional":[20],"methods":[21],"often":[22],"rely":[23],"solely":[24],"on":[25,42,117,129,134],"visual":[26,54],"cues,":[27],"lacking":[28],"integration":[29],"with":[30,155],"semantic":[31],"context.":[32],"To":[33],"address":[34],"this,":[35],"we":[36],"propose":[37],"a":[38,80,180],"novel":[39],"framework":[40,104],"based":[41],"Large":[43],"Vision-Language":[44],"Models":[45],"(LVLMs),":[46],"leveraging":[47],"their":[48],"cross-modal":[49,166],"alignment":[50],"capability":[51],"to":[52,109,150],"fuse":[53],"features":[55],"(e.g.,":[56,64],"body":[57],"postures,":[58],"gaze":[59],"directions)":[60],"linguistic":[62],"semantics":[63],"behavioral":[65],"category":[66],"descriptions).":[67],"A":[68],"parameter-efficient":[69],"tuning":[70],"strategy":[71],"using":[72],"Low-Rank":[73],"Adaptation":[74],"(LoRA)":[75],"is":[76],"adopted,":[77],"adapting":[78],"only":[79],"subset":[81],"of":[82,165,173],"parameters":[83],"both":[85,151],"the":[86,118,159,163,171],"Language":[87],"Model":[88],"(LM)":[89],"Vision":[91],"Transformer":[92],"(ViT)":[93],"modules,":[94],"thus":[95],"retaining":[96],"pre-trained":[97],"knowledge":[98],"while":[99],"reducing":[100],"computational":[101],"costs.":[102],"The":[103],"incorporates":[105],"multi-task":[106],"output":[107],"heads":[108],"simultaneously":[110],"predict":[111],"BBR":[112,130],"ECD":[114],"results.":[115],"Experiments":[116],"MPIIGroupInteraction":[119],"dataset":[120],"demonstrate":[121],"superior":[122],"performance:":[123],"our":[124],"method":[125],"achieves":[126],"0.65":[127],"accuracy":[128,133],"0.82":[132],"ECD,":[135],"outperforming":[136],"state-of-the-art":[137],"approaches":[138],"by":[139],"0.02-0.03":[140],"absolute":[142],"terms.":[143],"Ablation":[144],"studies":[145],"validate":[146],"that":[147],"applying":[148],"LoRA":[149],"LM":[152],"ViT":[154],"optimal":[156],"hyperparameters":[157],"yields":[158],"best":[160],"results,":[161],"confirming":[162],"importance":[164],"synergy.":[167],"This":[168],"work":[169],"highlights":[170],"potential":[172],"LVLMs":[174],"behavior":[177],"analysis,":[178],"providing":[179],"lightweight":[181],"effective":[183],"solution":[184],"complex":[187],"interactions.":[189]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-25T00:00:00"}