{"id":"https://openalex.org/W4417534269","doi":"https://doi.org/10.1109/wacv61042.2026.00195","title":"Seeing is Believing (and Predicting): Context-Aware Multi-Human Behavior Prediction with Vision Language Models","display_name":"Seeing is Believing (and Predicting): Context-Aware Multi-Human Behavior Prediction with Vision Language Models","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4417534269","doi":"https://doi.org/10.1109/wacv61042.2026.00195"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00195","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00195","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2512.15957","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Utsav Panchal","orcid":null},"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":"Utsav Panchal","raw_affiliation_strings":["University of Stuttgart,Institute of Architecture of Application Systems,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Stuttgart,Institute of Architecture of Application Systems,Germany","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yuchen Liu","orcid":null},"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":"Yuchen Liu","raw_affiliation_strings":["University of Stuttgart,Institute of Architecture of Application Systems,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Stuttgart,Institute of Architecture of Application Systems,Germany","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Luigi Palmieri","orcid":null},"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":["Bosch Research,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bosch Research,Germany","institution_ids":["https://openalex.org/I889804353"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ilche Georgievski","orcid":null},"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":"Ilche Georgievski","raw_affiliation_strings":["University of Stuttgart,Institute of Architecture of Application Systems,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Stuttgart,Institute of Architecture of Application Systems,Germany","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"last","author":{"id":null,"display_name":"Marco Aiello","orcid":null},"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,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Stuttgart,Institute of Architecture of Application Systems,Germany","institution_ids":["https://openalex.org/I100066346"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1959","last_page":"1968"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.4212000072002411,"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":0.4212000072002411,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.2387000024318695,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.09759999811649323,"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":0.5490999817848206},{"id":"https://openalex.org/keywords/observer","display_name":"Observer (physics)","score":0.5235999822616577},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5109999775886536},{"id":"https://openalex.org/keywords/human-behavior","display_name":"Human behavior","score":0.48570001125335693},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.41449999809265137},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4016999900341034},{"id":"https://openalex.org/keywords/language-understanding","display_name":"Language understanding","score":0.3935999870300293},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.36090001463890076}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6956999897956848},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6872000098228455},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.554099977016449},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5490999817848206},{"id":"https://openalex.org/C2780704645","wikidata":"https://www.wikidata.org/wiki/Q9251458","display_name":"Observer (physics)","level":2,"score":0.5235999822616577},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5109999775886536},{"id":"https://openalex.org/C117035363","wikidata":"https://www.wikidata.org/wiki/Q3769299","display_name":"Human behavior","level":2,"score":0.48570001125335693},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.41449999809265137},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4016999900341034},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.3935999870300293},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.36090001463890076},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.3587999939918518},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.3449999988079071},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3296999931335449},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.31029999256134033},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.3061999976634979},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.30379998683929443},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2985999882221222},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2890999913215637},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.2630000114440918},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C2986089797","wikidata":"https://www.wikidata.org/wiki/Q6501338","display_name":"Visual attention","level":3,"score":0.2556999921798706},{"id":"https://openalex.org/C200220432","wikidata":"https://www.wikidata.org/wiki/Q7936208","display_name":"Vision science","level":2,"score":0.25529998540878296}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wacv61042.2026.00195","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00195","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2512.15957","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.15957","pdf_url":"https://arxiv.org/pdf/2512.15957","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2512.15957","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.15957","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2512.15957","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.15957","pdf_url":"https://arxiv.org/pdf/2512.15957","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Accurately":[0],"predicting":[1,19],"human":[2,34,97],"behaviors":[3,35],"is":[4],"crucial":[5],"for":[6,82],"mobile":[7],"robots":[8],"operating":[9],"in":[10,21,139],"human-populated":[11],"environments.":[12],"While":[13],"prior":[14],"research":[15],"primarily":[16],"focuses":[17],"on":[18,110],"actions":[20],"single-human":[22],"scenarios":[23],"from":[24,36,60,66,86],"an":[25,87],"egocentric":[26],"view,":[27,89],"several":[28],"robotic":[29],"applications":[30],"require":[31],"understanding":[32],"multiple":[33],"a":[37,50,102],"third-person":[38],"perspective.":[39],"To":[40],"this":[41],"end,":[42],"we":[43,90],"present":[44],"CAMP-VLM":[45,94,130],"(Context-Aware":[46],"Multi-human":[47],"behavior":[48,84,98],"Prediction):":[49],"Vision":[51],"Language":[52],"Model":[53],"(VLM)-based":[54],"framework":[55],"that":[56],"incorporates":[57],"contextual":[58],"features":[59],"visual":[61],"input":[62],"and":[63,105,113,125],"spatial":[64],"awareness":[65],"scene":[67],"graphs":[68],"to":[69,76,116,137],"enhance":[70],"prediction":[71,85,140],"of":[72,79,93],"humans-scene":[73],"interactions.":[74],"Due":[75],"the":[77,107,132],"lack":[78],"suitable":[80],"datasets":[81],"multi-human":[83],"observer":[88],"perform":[91],"fine-tuning":[92],"with":[95],"synthetic":[96,112],"data":[99],"generated":[100],"by":[101,135],"photorealistic":[103],"simulator,":[104],"evaluate":[106],"resulting":[108],"models":[109],"both":[111],"real-world":[114],"sequences":[115],"assess":[117],"their":[118],"generalization":[119],"capabilities.":[120],"Leveraging":[121],"Supervised":[122],"Fine-Tuning":[123],"(SFT)":[124],"Direct":[126],"Preference":[127],"Optimization":[128],"(DPO),":[129],"outperforms":[131],"best-performing":[133],"baseline":[134],"up":[136],"66.9%":[138],"accuracy.":[141]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-12-21T00:00:00"}
