{"id":"https://openalex.org/W4413145752","doi":"https://doi.org/10.1109/cvpr52734.2025.02263","title":"LLAVIDAL : A Large LAnguage VIsion Model for Daily Activities of Living","display_name":"LLAVIDAL : A Large LAnguage VIsion Model for Daily Activities of Living","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413145752","doi":"https://doi.org/10.1109/cvpr52734.2025.02263"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.02263","doi":"https://doi.org/10.1109/cvpr52734.2025.02263","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.02263","pdf_url":null,"source":{"id":"https://openalex.org/S4210176548","display_name":"IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings","issn_l":"1063-6919","issn":["1063-6919","2332-564X","2575-7075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2406.09390","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059789621","display_name":"Dominick Reilly","orcid":"https://orcid.org/0009-0005-3959-8032","observed_orcids":["https://orcid.org/0009-0005-3959-8032"]},"institutions":[{"id":"https://openalex.org/I102149020","display_name":"University of North Carolina at Charlotte","ror":"https://ror.org/04dawnj30","country_code":"US","type":"education","lineage":["https://openalex.org/I102149020"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dominick Reilly","raw_affiliation_strings":["UNC Charlotte"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UNC Charlotte","institution_ids":["https://openalex.org/I102149020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064295390","display_name":"Rajatsubhra Chakraborty","orcid":"https://orcid.org/0009-0007-9124-632X","observed_orcids":["https://orcid.org/0009-0007-9124-632X"]},"institutions":[{"id":"https://openalex.org/I102149020","display_name":"University of North Carolina at Charlotte","ror":"https://ror.org/04dawnj30","country_code":"US","type":"education","lineage":["https://openalex.org/I102149020"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rajatsubhra Chakraborty","raw_affiliation_strings":["UNC Charlotte"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UNC Charlotte","institution_ids":["https://openalex.org/I102149020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109733425","display_name":"Arkaprava Sinha","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I102149020","display_name":"University of North Carolina at Charlotte","ror":"https://ror.org/04dawnj30","country_code":"US","type":"education","lineage":["https://openalex.org/I102149020"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arkaprava Sinha","raw_affiliation_strings":["UNC Charlotte"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UNC Charlotte","institution_ids":["https://openalex.org/I102149020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067815083","display_name":"M. Govind","orcid":"https://orcid.org/0009-0003-6381-6293","observed_orcids":["https://orcid.org/0009-0003-6381-6293"]},"institutions":[{"id":"https://openalex.org/I102149020","display_name":"University of North Carolina at Charlotte","ror":"https://ror.org/04dawnj30","country_code":"US","type":"education","lineage":["https://openalex.org/I102149020"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Manish Kumar Govind","raw_affiliation_strings":["UNC Charlotte"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UNC Charlotte","institution_ids":["https://openalex.org/I102149020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100383534","display_name":"Pu Wang","orcid":"https://orcid.org/0000-0003-1988-5016","observed_orcids":["https://orcid.org/0000-0003-1988-5016","https://orcid.org/0000-0001-8121-5385","https://orcid.org/0000-0003-4295-2053","https://orcid.org/0009-0007-9014-8381","https://orcid.org/0009-0009-2417-0913"]},"institutions":[{"id":"https://openalex.org/I102149020","display_name":"University of North Carolina at Charlotte","ror":"https://ror.org/04dawnj30","country_code":"US","type":"education","lineage":["https://openalex.org/I102149020"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pu Wang","raw_affiliation_strings":["UNC Charlotte"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UNC Charlotte","institution_ids":["https://openalex.org/I102149020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037298642","display_name":"Fran\u00e7ois Br\u00e9mond","orcid":"https://orcid.org/0000-0003-2988-2142","observed_orcids":["https://orcid.org/0000-0003-2988-2142"]},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Francois Bremond","raw_affiliation_strings":["Inria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inria","institution_ids":["https://openalex.org/I1326498283"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100733668","display_name":"Le Xue","orcid":"https://orcid.org/0000-0003-2810-770X","observed_orcids":["https://orcid.org/0000-0003-2810-770X"]},"institutions":[{"id":"https://openalex.org/I4210155268","display_name":"Salesforce (United States)","ror":"https://ror.org/057315g56","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155268"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Le Xue","raw_affiliation_strings":["Salesforce AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Salesforce AI Research","institution_ids":["https://openalex.org/I4210155268"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057061455","display_name":"Srijan Das","orcid":"https://orcid.org/0000-0002-3373-6749","observed_orcids":["https://orcid.org/0000-0002-3373-6749"]},"institutions":[{"id":"https://openalex.org/I102149020","display_name":"University of North Carolina at Charlotte","ror":"https://ror.org/04dawnj30","country_code":"US","type":"education","lineage":["https://openalex.org/I102149020"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Srijan Das","raw_affiliation_strings":["UNC Charlotte"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UNC Charlotte","institution_ids":["https://openalex.org/I102149020"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.2509,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.93784,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"24297","last_page":"24308"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5342000126838684,"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":0.5342000126838684,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.46140000224113464,"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/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.0005000000237487257,"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/activities-of-daily-living","display_name":"activities of daily living","score":0.9399999976158142},{"id":"https://openalex.org/keywords/human-object-interaction","display_name":"human-object interaction","score":0.7839999794960022},{"id":"https://openalex.org/keywords/curriculum-learning","display_name":"curriculum learning","score":0.6209999918937683},{"id":"https://openalex.org/keywords/video-description-generation","display_name":"video description generation","score":0.4560000002384186}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6536338329315186},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41307157278060913},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33453530073165894},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3224487006664276}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/cvpr52734.2025.02263","doi":"https://doi.org/10.1109/cvpr52734.2025.02263","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.02263","pdf_url":null,"source":{"id":"https://openalex.org/S4210176548","display_name":"IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings","issn_l":"1063-6919","issn":["1063-6919","2332-564X","2575-7075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2406.09390","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.09390","pdf_url":"https://arxiv.org/pdf/2406.09390","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:HAL:hal-05458698v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-05458698","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"CVPR 2025 - IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE/CVF, Jun 2025, Nashville, United States","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.48550/arxiv.2406.09390","doi":"https://doi.org/10.48550/arxiv.2406.09390","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2406.09390","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2406.09390","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.09390","pdf_url":"https://arxiv.org/pdf/2406.09390","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G6109696027","display_name":"CRII: RI: Understanding Activities of Daily Living in Indoor Scenarios","funder_award_id":"2245652","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4413145752.pdf","grobid_xml":"https://content.openalex.org/works/W4413145752.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W2619947201","https://openalex.org/W4296406182","https://openalex.org/W4308760226","https://openalex.org/W4309396530","https://openalex.org/W4310921506","https://openalex.org/W4361194507","https://openalex.org/W4366850747","https://openalex.org/W4367367040","https://openalex.org/W4386185600","https://openalex.org/W4402670320","https://openalex.org/W4402727272","https://openalex.org/W7108068597","https://openalex.org/W7128773051","https://openalex.org/W7133208266"],"related_works":["https://openalex.org/W4406600693","https://openalex.org/W7166493911","https://openalex.org/W7083819494","https://openalex.org/W4413396256","https://openalex.org/W4415182952","https://openalex.org/W6979322840","https://openalex.org/W7133223216","https://openalex.org/W4380135847","https://openalex.org/W7162779659","https://openalex.org/W4414685219"],"abstract_inverted_index":{"Current":[0],"Large":[1],"Language":[2],"Vision":[3],"Models":[4],"(LLVMs)":[5],"trained":[6],"on":[7,141],"web":[8],"videos":[9],"perform":[10],"well":[11],"in":[12,119,137],"general":[13],"video":[14,45,130],"understanding":[15],"but":[16],"struggle":[17],"with":[18],"fine-grained":[19],"details,":[20],"complex":[21,92],"human-object":[22],"interactions":[23],"(HOI),":[24],"and":[25,48,87,129,151],"view-invariant":[26],"representation":[27],"learning":[28],"essential":[29],"for":[30,65],"Activities":[31],"of":[32,42,102],"Daily":[33],"Living":[34],"(ADL).":[35],"This":[36],"limitation":[37],"stems":[38],"from":[39],"a":[40,62,71,98,111,122],"lack":[41],"specialized":[43],"ADL":[44,67,127,138,148],"instruction-tuning":[46,75],"datasets":[47],"insufficient":[49],"modality":[50],"integration":[51],"to":[52,89,133],"capture":[53],"discriminative":[54],"action":[55],"representations.":[56],"To":[57],"address":[58],"this,":[59],"we":[60,78,109],"propose":[61,110],"semi-automated":[63],"framework":[64],"curating":[66],"datasets,":[68],"creating":[69],"ADL-X,":[70,142],"multiview,":[72],"multimodal":[73],"RGBS":[74],"dataset.":[76],"Additionally,":[77],"introduce":[79],"LLAVIDAL,":[80],"an":[81],"LLVM":[82,135],"integrating":[83],"videos,":[84],"3D":[85],"skeletons,":[86],"HOIs":[88],"model":[90],"ADL\u2019s":[91],"spatiotemporal":[93],"relationships.":[94],"For":[95],"training":[96,115],"LLAVIDAL":[97,143],"simple":[99],"joint":[100],"alignment":[101],"all":[103],"modalities":[104,118],"yields":[105],"suboptimal":[106],"results;":[107],"thus,":[108],"Multimodal":[112],"Progressive":[113],"(MMPro)":[114],"strategy,":[116],"incorporating":[117],"stages":[120],"following":[121],"curriculum.":[123],"We":[124],"also":[125],"establish":[126],"MCQ":[128],"description":[131],"benchmarks":[132],"assess":[134],"performance":[136,146],"tasks.":[139],"Trained":[140],"achieves":[144],"state-of-the-art":[145],"across":[147],"benchmarks.":[149],"Code":[150],"data":[152],"will":[153],"be":[154],"made":[155],"publicly":[156],"available":[157],"at":[158],"https://adl-x.github.io/.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}