{"id":"https://openalex.org/W4415311833","doi":"https://doi.org/10.48550/arxiv.2506.14404","title":"Causally Steered Diffusion for Automated Video Counterfactual Generation","display_name":"Causally Steered Diffusion for Automated Video Counterfactual Generation","publication_year":2025,"publication_date":"2025-06-17","ids":{"openalex":"https://openalex.org/W4415311833","doi":"https://doi.org/10.48550/arxiv.2506.14404"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2506.14404","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.14404","pdf_url":"https://arxiv.org/pdf/2506.14404","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"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.14404","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Spyrou, Nikos","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Spyrou, Nikos","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020902651","display_name":"Athanasios Vlontzos","orcid":"https://orcid.org/0000-0002-7672-2574","observed_orcids":["https://orcid.org/0000-0002-7672-2574"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vlontzos, Athanasios","raw_affiliation_strings":["Monzo Bank , UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Monzo Bank , UK","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004335886","display_name":"Paraskevas Pegios","orcid":"https://orcid.org/0009-0005-1471-4850","observed_orcids":["https://orcid.org/0009-0005-1471-4850"]},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Pegios, Paraskevas","raw_affiliation_strings":["Pioneer Centre for AI , Denmark","Technical University of Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pioneer Centre for AI , Denmark","institution_ids":[]},{"raw_affiliation_string":"Technical University of Denmark","institution_ids":["https://openalex.org/I96673099"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007179145","display_name":"\u0398\u03c9\u03bc\u03ac\u03c2 \u039c\u03b5\u03bb\u03af\u03c3\u03c4\u03b1\u03c2","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Melistas, Thomas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093925777","display_name":"Nefeli Gkouti","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gkouti, Nefeli","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050734738","display_name":"Yannis Panagakis","orcid":"https://orcid.org/0000-0003-0153-5210","observed_orcids":["https://orcid.org/0000-0003-0153-5210"]},"institutions":[{"id":"https://openalex.org/I200777214","display_name":"National and Kapodistrian University of Athens","ror":"https://ror.org/04gnjpq42","country_code":"GR","type":"education","lineage":["https://openalex.org/I200777214"]},{"id":"https://openalex.org/I4210156054","display_name":"Athena Research and Innovation Center In Information Communication & Knowledge Technologies","ror":"https://ror.org/0576by029","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210156054"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Panagakis, Yannis","raw_affiliation_strings":["Archimedes , Athena Research Center , Greece","National & Kapodistrian University of Athens , Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Archimedes , Athena Research Center , Greece","institution_ids":["https://openalex.org/I4210156054"]},{"raw_affiliation_string":"National & Kapodistrian University of Athens , Greece","institution_ids":["https://openalex.org/I200777214"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040046846","display_name":"Giorgos Papanastasiou","orcid":"https://orcid.org/0000-0002-1939-296X","observed_orcids":["https://orcid.org/0000-0002-1939-296X"]},"institutions":[{"id":"https://openalex.org/I110002522","display_name":"University of Essex","ror":"https://ror.org/02nkf1q06","country_code":"GB","type":"education","lineage":["https://openalex.org/I110002522"]},{"id":"https://openalex.org/I4210156054","display_name":"Athena Research and Innovation Center In Information Communication & Knowledge Technologies","ror":"https://ror.org/0576by029","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210156054"]}],"countries":["GB","GR"],"is_corresponding":false,"raw_author_name":"Papanastasiou, Giorgos","raw_affiliation_strings":["Archimedes , Athena Research Center , Greece","The University of Essex , UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Archimedes , Athena Research Center , Greece","institution_ids":["https://openalex.org/I4210156054"]},{"raw_affiliation_string":"The University of Essex , UK","institution_ids":["https://openalex.org/I110002522"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054437456","display_name":"Sotirios A. Tsaftaris","orcid":"https://orcid.org/0000-0002-8795-9294","observed_orcids":["https://orcid.org/0000-0002-8795-9294"]},"institutions":[{"id":"https://openalex.org/I4210156054","display_name":"Athena Research and Innovation Center In Information Communication & Knowledge Technologies","ror":"https://ror.org/0576by029","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210156054"]},{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB","GR"],"is_corresponding":false,"raw_author_name":"Tsaftaris, Sotirios A.","raw_affiliation_strings":["Archimedes , Athena Research Center , Greece","The University of Edinburgh , UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Archimedes , Athena Research Center , Greece","institution_ids":["https://openalex.org/I4210156054"]},{"raw_affiliation_string":"The University of Edinburgh , UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":1.0,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":1.0,"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/T12357","display_name":"Digital Media Forensic Detection","score":9.999999747378752e-05,"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":0.0,"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/latent-diffusion-models","display_name":"latent diffusion models","score":0.8080000281333923},{"id":"https://openalex.org/keywords/out-of-distribution-prediction","display_name":"out-of-distribution prediction","score":0.9190000295639038},{"id":"https://openalex.org/keywords/causal-diagrams","display_name":"causal graphs","score":0.8479999899864197},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.796999990940094},{"id":"https://openalex.org/keywords/prompt-optimization","display_name":"prompt optimization","score":0.7590000033378601}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7595000267028809},{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.6632999777793884},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.6141999959945679},{"id":"https://openalex.org/C71889745","wikidata":"https://www.wikidata.org/wiki/Q1783264","display_name":"Counterfactual conditional","level":3,"score":0.5288000106811523},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.524399995803833},{"id":"https://openalex.org/C103910844","wikidata":"https://www.wikidata.org/wiki/Q2631256","display_name":"Video quality","level":3,"score":0.4560999870300293},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44519999623298645},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4372999966144562},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.42730000615119934},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.37560001015663147},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.3580999970436096},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.3513999879360199},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3393000066280365},{"id":"https://openalex.org/C175652121","wikidata":"https://www.wikidata.org/wiki/Q4379351","display_name":"Causal consistency","level":5,"score":0.3273000121116638},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.3165999948978424},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.2989000082015991},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.29789999127388},{"id":"https://openalex.org/C2780310081","wikidata":"https://www.wikidata.org/wiki/Q1154312","display_name":"Video editing","level":2,"score":0.29089999198913574},{"id":"https://openalex.org/C114227958","wikidata":"https://www.wikidata.org/wiki/Q7631422","display_name":"Subjective video quality","level":4,"score":0.28929999470710754},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.28870001435279846},{"id":"https://openalex.org/C163504300","wikidata":"https://www.wikidata.org/wiki/Q2364925","display_name":"Causal structure","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.2648000121116638},{"id":"https://openalex.org/C64357122","wikidata":"https://www.wikidata.org/wiki/Q1149766","display_name":"Causality (physics)","level":2,"score":0.2630999982357025}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2506.14404","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.14404","pdf_url":"https://arxiv.org/pdf/2506.14404","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":"doi:10.48550/arxiv.2506.14404","doi":"https://doi.org/10.48550/arxiv.2506.14404","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.14404","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:2506.14404","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.14404","pdf_url":"https://arxiv.org/pdf/2506.14404","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/G1977019300","display_name":"Causality in Healthcare AI Hub","funder_award_id":"EP/Y028856/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G6276162139","display_name":null,"funder_award_id":"MIS 5154714","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G7471596932","display_name":"From trivial representations to learning concepts in AI by exploiting unique data","funder_award_id":"EP/X017680/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320314731","display_name":"UK Research and Innovation","ror":"https://ror.org/001aqnf71"},{"id":"https://openalex.org/F4320320005","display_name":"Royal Academy of Engineering","ror":"https://ror.org/0526snb40"},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"},{"id":"https://openalex.org/F7311471023","display_name":"NextGenerationEU","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415311833.pdf","grobid_xml":"https://content.openalex.org/works/W4415311833.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W4297750695","https://openalex.org/W4307076412","https://openalex.org/W4327810158","https://openalex.org/W4383472654","https://openalex.org/W4385327921","https://openalex.org/W4400600549","https://openalex.org/W4404355292","https://openalex.org/W4405655761","https://openalex.org/W4406567840","https://openalex.org/W4409093780","https://openalex.org/W4413157704","https://openalex.org/W4414530357","https://openalex.org/W6928827059"],"related_works":["https://openalex.org/W7127434863","https://openalex.org/W7119705465","https://openalex.org/W4414820714","https://openalex.org/W7128386780","https://openalex.org/W4417136242","https://openalex.org/W4416258227","https://openalex.org/W4392929670","https://openalex.org/W7164848156","https://openalex.org/W7214354761","https://openalex.org/W4403487431"],"abstract_inverted_index":{"Adapting":[0],"text-to-image":[1],"(T2I)":[2],"latent":[3,104],"diffusion":[4],"models":[5],"(LDMs)":[6],"to":[7,25,109,132,143,201,215],"video":[8,27,58,135,155,175,207,221],"editing":[9,136,208],"has":[10,212],"shown":[11],"strong":[12],"visual":[13,194],"fidelity":[14],"and":[15,84,138,158,165,230],"controllability,":[16],"but":[17],"challenges":[18],"remain":[19],"in":[20,77,113,223],"maintaining":[21],"causal":[22,70,79,163,183,187],"relationships":[23,44,75],"inherent":[24],"the":[26,74,86,103,107,114,133,178],"data":[28],"generating":[29],"process.":[30],"Edits":[31],"affecting":[32],"causally":[33,53,122,173],"dependent":[34],"attributes":[35],"often":[36],"generate":[37,216],"unrealistic":[38],"or":[39,147,193],"misleading":[40],"outcomes":[41],"if":[42],"these":[43,91],"are":[45],"ignored.":[46],"In":[47],"this":[48],"work,":[49],"we":[50],"introduce":[51],"a":[52,78,94],"faithful":[54,174],"framework":[55,211],"for":[56],"counterfactual":[57],"generation,":[59],"formulated":[60],"as":[61,162,227],"an":[62],"Out-of-Distribution":[63],"(OOD)":[64],"prediction":[65],"problem.":[66],"We":[67,149],"embed":[68],"prior":[69],"knowledge":[71],"by":[72,89],"encoding":[73],"specified":[76],"graph":[80],"into":[81],"text":[82],"prompts":[83,92],"guide":[85],"generation":[87,120],"process":[88],"optimizing":[90],"using":[93,153],"vision-language":[95],"model":[96],"(VLM)-based":[97],"textual":[98],"loss.":[99],"This":[100],"loss":[101],"encourages":[102],"space":[105],"of":[106,116],"LDMs":[108],"capture":[110],"OOD":[111],"variations":[112],"form":[115],"counterfactuals,":[117],"effectively":[118],"steering":[119],"toward":[121],"meaningful":[123],"alternatives.":[124],"The":[125],"proposed":[126],"framework,":[127],"dubbed":[128],"CSVC,":[129],"is":[130],"agnostic":[131],"underlying":[134],"system":[137],"does":[139],"not":[140],"require":[141],"access":[142],"its":[144,202],"internal":[145],"mechanisms":[146],"fine-tuning.":[148],"evaluate":[150],"our":[151,210],"approach":[152],"standard":[154],"quality":[156,195],"metrics":[157],"counterfactual-specific":[159],"criteria,":[160],"such":[161,226],"effectiveness":[164,188],"minimality.":[166],"Experimental":[167],"results":[168],"show":[169],"that":[170],"CSVC":[171],"generates":[172],"counterfactuals":[176],"within":[177],"LDM":[179],"distribution":[180],"via":[181],"prompt-based":[182],"steering,":[184],"achieving":[185],"state-of-the-art":[186],"without":[189],"compromising":[190],"temporal":[191],"consistency":[192],"on":[196],"real-world":[197],"facial":[198],"videos.":[199],"Due":[200],"compatibility":[203],"with":[204],"any":[205],"black-box":[206],"system,":[209],"significant":[213],"potential":[214],"realistic":[217],"'what":[218],"if'":[219],"hypothetical":[220],"scenarios":[222],"diverse":[224],"areas":[225],"digital":[228],"media":[229],"healthcare.":[231]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":3}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-18T00:00:00"}