{"id":"https://openalex.org/W4416749305","doi":"https://doi.org/10.1109/access.2025.3637990","title":"Adaptive Multimodal Graph Reasoning With Foundation Models for Fine-Grained Action Recognition","display_name":"Adaptive Multimodal Graph Reasoning With Foundation Models for Fine-Grained Action Recognition","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416749305","doi":"https://doi.org/10.1109/access.2025.3637990"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3637990","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3637990","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"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":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3637990","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Fatemeh Ziaeetabar","orcid":"https://orcid.org/0000-0003-1159-3588"},"institutions":[{"id":"https://openalex.org/I23946033","display_name":"University of Tehran","ror":"https://ror.org/05vf56z40","country_code":"IR","type":"education","lineage":["https://openalex.org/I23946033"]}],"countries":["IR"],"is_corresponding":true,"raw_author_name":"Fatemeh Ziaeetabar","raw_affiliation_strings":["School of Mathematics, Statistics and Computer Science, College of Science, University of Tehran, Tehran, Iran","College of Science, School of Mathematics, Statistics and Computer Science, University of Tehran, Tehran, Iran"],"raw_orcid":"https://orcid.org/0000-0003-1159-3588","affiliations":[{"raw_affiliation_string":"School of Mathematics, Statistics and Computer Science, College of Science, University of Tehran, Tehran, Iran","institution_ids":["https://openalex.org/I23946033"]},{"raw_affiliation_string":"College of Science, School of Mathematics, Statistics and Computer Science, University of Tehran, Tehran, Iran","institution_ids":["https://openalex.org/I23946033"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048510214","display_name":"Florentin Woergoetter","orcid":"https://orcid.org/0000-0001-8206-9738"},"institutions":[{"id":"https://openalex.org/I4210087171","display_name":"Bernstein Center for Computational Neuroscience G\u00f6ttingen","ror":"https://ror.org/003g6b432","country_code":"DE","type":"government","lineage":["https://openalex.org/I4210087171","https://openalex.org/I4210092532"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Florentin W\u00f6rg\u00f6tter","raw_affiliation_strings":["Department for Computational Neuroscience, Bernstein Center for Computational Neuroscience, III Physikalisches Institut-Biophysik, Georg-Agust-Universität Göttingen, Göttingen, Germany","Department for Computational Neuroscience, III Physikalisches Institut-Biophysik, Bernstein Center for Computational Neuroscience, Georg-Agust-Universität Göttingen, Göttingen, Germany"],"raw_orcid":"https://orcid.org/0000-0001-8206-9738","affiliations":[{"raw_affiliation_string":"Department for Computational Neuroscience, Bernstein Center for Computational Neuroscience, III Physikalisches Institut-Biophysik, Georg-Agust-Universität Göttingen, Göttingen, Germany","institution_ids":["https://openalex.org/I4210087171"]},{"raw_affiliation_string":"Department for Computational Neuroscience, III Physikalisches Institut-Biophysik, Bernstein Center for Computational Neuroscience, Georg-Agust-Universität Göttingen, Göttingen, Germany","institution_ids":["https://openalex.org/I4210087171"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I23946033"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.0875,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.83926955,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"13","issue":null,"first_page":"201990","last_page":"202009"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.792900025844574,"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":0.792900025844574,"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":0.15760000050067902,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.005200000014156103,"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/encode","display_name":"ENCODE","score":0.6201000213623047},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5680000185966492},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.4927999973297119},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4674000144004822},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4334000051021576},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.4244000017642975},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.3912000060081482}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8464999794960022},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.6201000213623047},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5680000185966492},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5485000014305115},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.4927999973297119},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4674000144004822},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4334000051021576},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.4244000017642975},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.3912000060081482},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.3630000054836273},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3601999878883362},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.35839998722076416},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3529999852180481},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.3046000003814697},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.28049999475479126},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2621999979019165},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.26080000400543213}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3637990","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3637990","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"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":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:c5c8b28d3982451898dc0749fc5fd250","is_oa":true,"landing_page_url":"https://doaj.org/article/c5c8b28d3982451898dc0749fc5fd250","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 201990-202009 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3637990","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3637990","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"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":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4082008846","display_name":null,"funder_award_id":"454648639-SFB","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G7781466142","display_name":null,"funder_award_id":"Project-ID 454648639 - SFB 1528 (Project Z02)","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Foundation":[0],"models":[1,145],"have":[2],"ushered":[3],"in":[4],"a":[5,27,33,107],"new":[6],"era":[7],"for":[8,38,44,97,150],"multimodal":[9,69],"video":[10],"understanding":[11],"by":[12,115],"enabling":[13],"the":[14,50,140],"extraction":[15],"of":[16,52,142],"rich":[17],"spatiotemporal":[18],"and":[19,42,76,79,84,99,152],"semantic":[20,85],"representations.":[21],"In":[22],"this":[23,113],"work,":[24],"we":[25,130],"introduce":[26],"novel":[28],"graph-based":[29,148],"framework":[30],"that":[31,132],"integrates":[32],"vision-language":[34],"foundation,":[35],"leveraging":[36],"VideoMAE":[37],"dynamic":[39,147],"visual":[40],"encoding":[41],"BERT":[43],"contextual":[45],"text":[46],"representation,":[47],"to":[48],"address":[49],"challenge":[51],"recognizing":[53],"fine-grained":[54],"bimanual":[55],"manipulation":[56],"actions.":[57],"Departing":[58],"from":[59],"conventional":[60],"static":[61],"graph":[62,70,88],"architectures,":[63],"our":[64,133],"approach":[65],"constructs":[66],"an":[67],"adaptive":[68],"where":[71],"nodes":[72],"represent":[73],"frames,":[74],"objects,":[75],"textual":[77],"annotations,":[78],"edges":[80],"encode":[81],"spatial,":[82],"temporal,":[83],"relationships.":[86],"These":[87],"structures":[89],"evolve":[90],"dynamically":[91],"based":[92,119],"on":[93,120,126],"learned":[94],"interactions,":[95],"allowing":[96],"flexible":[98],"context-aware":[100],"reasoning.":[101],"A":[102],"task-specific":[103],"attention":[104],"mechanism":[105],"within":[106],"Graph":[108],"Attention":[109],"Network":[110],"further":[111],"enhances":[112],"reasoning":[114,149],"modulating":[116],"edge":[117],"importance":[118],"action":[121,154],"semantics.":[122],"Through":[123],"extensive":[124],"evaluations":[125],"diverse":[127],"benchmark":[128],"datasets,":[129],"demonstrate":[131],"method":[134],"consistently":[135],"outperforms":[136],"state-of-the-art":[137],"baselines,":[138],"underscoring":[139],"effectiveness":[141],"combining":[143],"foundation":[144],"with":[146],"robust":[151],"generalizable":[153],"recognition.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-11-28T00:00:00"}