{"id":"https://openalex.org/W7212230767","doi":"https://doi.org/10.1109/tip.2026.3730842","title":"Video-Causal State Space Model (VCSSM) for Video Analysis","display_name":"Video-Causal State Space Model (VCSSM) for Video Analysis","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7212230767","doi":"https://doi.org/10.1109/tip.2026.3730842","pmid":"https://pubmed.ncbi.nlm.nih.gov/42726632"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2026.3730842","doi":"https://doi.org/10.1109/tip.2026.3730842","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3730842","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","ccf-a","cwts-core","dongbi-a","doyens","jufo-3","ki-jl-2","medline","norway-2","poland-200","russia-white-list-1","vabb-shw"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","pubmed"],"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/A5041300663","display_name":"Matthew Korban","orcid":"https://orcid.org/0009-0008-4610-9390","observed_orcids":["https://orcid.org/0009-0008-4610-9390"]},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew Korban","raw_affiliation_strings":["University of Virginia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Virginia","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081562360","display_name":"Peter A. Youngs","orcid":"https://orcid.org/0000-0002-1711-1749","observed_orcids":["https://orcid.org/0000-0002-1711-1749"]},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Youngs","raw_affiliation_strings":["University of Virginia"],"raw_orcid":"https://orcid.org/0000-0002-1711-1749","affiliations":[{"raw_affiliation_string":"University of Virginia","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034452294","display_name":"Scott T. Acton","orcid":"https://orcid.org/0000-0003-3288-1255","observed_orcids":["https://orcid.org/0000-0003-3288-1255"]},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Scott T. Acton","raw_affiliation_strings":["University of Virginia"],"raw_orcid":"https://orcid.org/0000-0003-3288-1255","affiliations":[{"raw_affiliation_string":"University of Virginia","institution_ids":["https://openalex.org/I51556381"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I51556381"],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":null,"first_page":"10226","last_page":"10240"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9976000189781189,"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":0.9976000189781189,"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":0.0003000000142492354,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.00019999999494757503,"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/directed-acyclic-graphs","display_name":"directed acyclic graphs","score":0.8899999856948853},{"id":"https://openalex.org/keywords/video-understanding","display_name":"video understanding","score":0.5630000233650208},{"id":"https://openalex.org/keywords/human-action-recognition","display_name":"human action recognition","score":0.8939999938011169},{"id":"https://openalex.org/keywords/temporal-modeling","display_name":"temporal modeling","score":0.7360000014305115},{"id":"https://openalex.org/keywords/counterfactual-thinking","display_name":"counterfactual reasoning","score":0.8130000233650208},{"id":"https://openalex.org/keywords/distribution-shift-robustness","display_name":"distribution shift robustness","score":0.8119999766349792},{"id":"https://openalex.org/keywords/interpretability","display_name":"interpretability","score":0.8009999990463257},{"id":"https://openalex.org/keywords/sequence-prediction","display_name":"sequence prediction","score":0.40799999237060547}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6351000070571899},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5719000101089478},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5127000212669373},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.392300009727478},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3637999892234802},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.35010001063346863},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.3472000062465668},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.34450000524520874},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.3043999969959259},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.29490000009536743},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.28619998693466187},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.28040000796318054},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.2775999903678894},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26969999074935913},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.26739999651908875},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2667999863624573},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.2639999985694885},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C106516650","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm design","level":2,"score":0.2535000145435333},{"id":"https://openalex.org/C52918065","wikidata":"https://www.wikidata.org/wiki/Q230945","display_name":"State-space representation","level":2,"score":0.2526000142097473},{"id":"https://openalex.org/C117090137","wikidata":"https://www.wikidata.org/wiki/Q7927977","display_name":"Video post-processing","level":5,"score":0.250900000333786}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2026.3730842","doi":"https://doi.org/10.1109/tip.2026.3730842","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3730842","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","ccf-a","cwts-core","dongbi-a","doyens","jufo-3","ki-jl-2","medline","norway-2","poland-200","russia-white-list-1","vabb-shw"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:42726632","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42726632","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2117663940","https://openalex.org/W2143891888","https://openalex.org/W2225156818","https://openalex.org/W2740437707","https://openalex.org/W3115431207","https://openalex.org/W3135588948","https://openalex.org/W3147387781","https://openalex.org/W3177141386","https://openalex.org/W3191973673","https://openalex.org/W4241115065","https://openalex.org/W4312312750","https://openalex.org/W4312658081","https://openalex.org/W4386057769","https://openalex.org/W4386065852","https://openalex.org/W4386076398","https://openalex.org/W4386076522","https://openalex.org/W4390872366","https://openalex.org/W4392406336","https://openalex.org/W4393067897","https://openalex.org/W4399938881","https://openalex.org/W4403842425","https://openalex.org/W4404724811","https://openalex.org/W4409356433","https://openalex.org/W4409423766","https://openalex.org/W4409916884","https://openalex.org/W4412893567","https://openalex.org/W4414404693","https://openalex.org/W4415593579","https://openalex.org/W4415795608","https://openalex.org/W4415798267","https://openalex.org/W4417091809","https://openalex.org/W7133239857"],"related_works":["https://openalex.org/W4415593579","https://openalex.org/W7167220482","https://openalex.org/W7139919685","https://openalex.org/W7127190855","https://openalex.org/W2737491036","https://openalex.org/W4403780663","https://openalex.org/W7162306214","https://openalex.org/W4417517804","https://openalex.org/W4415695976","https://openalex.org/W4415541258"],"abstract_inverted_index":{"We":[0,77],"propose":[1],"a":[2,14,19,43,135],"Video":[3],"Causal":[4],"State":[5],"Space":[6],"Model":[7],"(VCSSM)":[8],"for":[9],"video":[10,36,120,140],"understanding.":[11,141],"VCSSM":[12,48,79,108],"integrates":[13],"learned":[15],"causal":[16,68,117],"graph":[17,46],"into":[18],"latent":[20,39],"state-space":[21,60],"dynamics":[22],"model,":[23],"enabling":[24],"the":[25,67,86],"explicit":[26],"modeling":[27,52],"of":[28],"cause-and-effect":[29],"relationships":[30],"over":[31],"time.":[32],"By":[33],"representing":[34],"underlying":[35],"factors":[37],"as":[38,90,92],"states":[40],"linked":[41],"by":[42],"directed":[44],"acyclic":[45],"(DAG),":[47],"achieves":[49],"interpretable":[50],"temporal":[51],"and":[53,75,95,115,128],"improved":[54],"robustness":[55],"to":[56,112,131],"distribution":[57],"shifts.":[58],"The":[59,122],"formulation":[61],"ensures":[62],"efficient":[63],"sequential":[64],"prediction,":[65],"while":[66],"structure":[69],"yields":[70],"clear":[71],"reasoning":[72,118],"about":[73,119],"interventions":[74],"counterfactuals.":[76],"validate":[78],"on":[80],"standard":[81],"action":[82],"recognition":[83],"benchmarks,":[84],"including":[85],"large-scale":[87],"Kinetics-700":[88],"dataset,":[89],"well":[91],"HMDB-51,":[93],"UCF-101,HAR,":[94],"CoPhy,":[96],"where":[97],"our":[98],"method":[99],"significantly":[100],"outperforms":[101],"state-of-the-art":[102],"approaches":[103],"in":[104,110,139],"accuracy.":[105],"In":[106],"particular,":[107],"excels":[109],"generalizing":[111],"new":[113],"contexts":[114],"facilitating":[116],"events.":[121],"proposed":[123],"framework":[124],"demonstrates":[125],"superior":[126],"performance":[127],"interpretability":[129],"compared":[130],"prior":[132],"methods,":[133],"marking":[134],"substantial":[136],"step":[137],"forward":[138]},"counts_by_year":[],"updated_date":"2026-10-08T09:06:37.294493","created_date":"2026-09-12T00:00:00"}