{"id":"https://openalex.org/W4416852231","doi":"https://doi.org/10.1109/iccv51701.2025.01143","title":"What Changed and What Could Have Changed? State-Change Counterfactuals for Procedure-Aware Video Representation Learning","display_name":"What Changed and What Could Have Changed? State-Change Counterfactuals for Procedure-Aware Video Representation Learning","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416852231","doi":"https://doi.org/10.1109/iccv51701.2025.01143"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01143","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01143","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","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/2503.21055","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028936255","display_name":"Chi-Hsi Kung","orcid":null},"institutions":[{"id":"https://openalex.org/I592451","display_name":"Indiana University","ror":"https://ror.org/01kg8sb98","country_code":"US","type":"education","lineage":["https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chi-Hsi Kung","raw_affiliation_strings":["Indiana University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indiana University","institution_ids":["https://openalex.org/I592451"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107950099","display_name":"F. Ramirez","orcid":"https://orcid.org/0000-0002-7178-0484"},"institutions":[{"id":"https://openalex.org/I592451","display_name":"Indiana University","ror":"https://ror.org/01kg8sb98","country_code":"US","type":"education","lineage":["https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Frangil Ramirez","raw_affiliation_strings":["Indiana University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indiana University","institution_ids":["https://openalex.org/I592451"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011642798","display_name":"Juhyung Ha","orcid":"https://orcid.org/0000-0002-6596-5116"},"institutions":[{"id":"https://openalex.org/I592451","display_name":"Indiana University","ror":"https://ror.org/01kg8sb98","country_code":"US","type":"education","lineage":["https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Juhyung Ha","raw_affiliation_strings":["Indiana University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indiana University","institution_ids":["https://openalex.org/I592451"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100348274","display_name":"Yi-Ting Chen","orcid":"https://orcid.org/0009-0000-6537-8926"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yi-Ting Chen","raw_affiliation_strings":["National Yang-Ming Chiao-Tung University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Yang-Ming Chiao-Tung University","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110629562","display_name":"David Crandall","orcid":null},"institutions":[{"id":"https://openalex.org/I592451","display_name":"Indiana University","ror":"https://ror.org/01kg8sb98","country_code":"US","type":"education","lineage":["https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Crandall","raw_affiliation_strings":["Indiana University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indiana University","institution_ids":["https://openalex.org/I592451"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112904753","display_name":"Yi\u2013Hsuan Tsai","orcid":"https://orcid.org/0000-0003-2107-4300"},"institutions":[{"id":"https://openalex.org/I4210120337","display_name":"Azienda Trasporti Milanesi (Italy)","ror":"https://ror.org/02qs5ar77","country_code":"IT","type":"company","lineage":["https://openalex.org/I4210120337"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Yi-Hsuan Tsai","raw_affiliation_strings":["Atmanity Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Atmanity Inc","institution_ids":["https://openalex.org/I4210120337"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.43309941,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12294","last_page":"12306"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.8662999868392944,"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":0.8662999868392944,"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":0.0722000002861023,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.012900000438094139,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.7574999928474426},{"id":"https://openalex.org/keywords/counterfactual-conditional","display_name":"Counterfactual conditional","score":0.7470999956130981},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6593000292778015},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6388000249862671},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5192999839782715},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.3919000029563904},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.3709999918937683},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.36730000376701355}],"concepts":[{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.7574999928474426},{"id":"https://openalex.org/C71889745","wikidata":"https://www.wikidata.org/wiki/Q1783264","display_name":"Counterfactual conditional","level":3,"score":0.7470999956130981},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7174999713897705},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6593000292778015},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6388000249862671},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6359000205993652},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5192999839782715},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4343000054359436},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3919000029563904},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.3709999918937683},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.36730000376701355},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.367000013589859},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.35019999742507935},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.35010001063346863},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.32519999146461487},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3172000050544739},{"id":"https://openalex.org/C5065155","wikidata":"https://www.wikidata.org/wiki/Q1185775","display_name":"Frame problem","level":2,"score":0.30660000443458557},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.29440000653266907},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.287200003862381},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2773999869823456},{"id":"https://openalex.org/C40506919","wikidata":"https://www.wikidata.org/wiki/Q7452469","display_name":"Sequence learning","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.2689000070095062},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.26499998569488525},{"id":"https://openalex.org/C183759332","wikidata":"https://www.wikidata.org/wiki/Q343680","display_name":"Action learning","level":4,"score":0.2581999897956848}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01143","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01143","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2503.21055","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.21055","pdf_url":"https://arxiv.org/pdf/2503.21055","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,"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.2503.21055","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.21055","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,"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:2503.21055","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.21055","pdf_url":"https://arxiv.org/pdf/2503.21055","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,"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":[{"id":"https://openalex.org/G549193807","display_name":null,"funder_award_id":"113-2628-E-A49-022,114-2628-E-A49-007","funder_id":"https://openalex.org/F2461203286","funder_display_name":"National Science and Technology Council"},{"id":"https://openalex.org/G5643777851","display_name":null,"funder_award_id":"DRL-2112635","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F2461203286","display_name":"National Science and Technology Council","ror":"https://ror.org/02kv4zf79"},{"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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Understanding":[0],"a":[1],"procedural":[2],"activity":[3],"requires":[4],"modeling":[5,40],"both":[6],"how":[7,14],"action":[8,23,129,133,141],"steps":[9],"transform":[10],"the":[11,20,41,51,105,110,146,149],"scene,":[12],"and":[13,112,140,153,156],"evolving":[15],"scene":[16],"transformations":[17],"can":[18],"influence":[19],"sequence":[21],"of":[22,44,114,148],"steps,":[24],"even":[25],"those":[26],"that":[27,86],"are":[28],"accidental":[29],"or":[30],"erroneous.":[31],"Existing":[32],"work":[33],"has":[34,47],"studied":[35],"procedure-aware":[36,61,125],"video":[37,62,79],"representations":[38],"by":[39,65,70,95],"temporal":[42,128],"order":[43],"actions,":[45],"but":[46],"not":[48],"explicitly":[49],"learned":[50],"state":[52],"changes":[53],"(scene":[54],"transformations).":[55],"In":[56],"this":[57],"work,":[58],"we":[59,82],"study":[60],"representation":[63],"learning":[64],"incorporating":[66],"state-change":[67,84,151],"descriptions":[68,152],"generated":[69],"Large":[71],"Language":[72],"Models":[73],"(LLMs)":[74],"as":[75],"supervision":[76],"signals":[77],"for":[78],"encoders.":[80],"Moreover,":[81],"generate":[83],"counterfactuals":[85],"simulate":[87],"hypothesized":[88],"failure":[89],"outcomes,":[90],"allowing":[91],"models":[92],"to":[93,108],"learn":[94],"imagining":[96],"unseen":[97],"\"What":[98],"if\"":[99],"scenarios.":[100],"This":[101],"counterfactual":[102],"reasoning":[103],"facilitates":[104],"model's":[106],"ability":[107],"understand":[109],"cause":[111],"effect":[113],"each":[115],"step":[116],"in":[117],"an":[118],"activity.":[119],"We":[120],"conduct":[121],"extensive":[122],"experiments":[123],"on":[124,160],"tasks,":[126],"including":[127],"segmentation,":[130],"error":[131],"detection,":[132],"phase":[134],"classification,":[135],"frame":[136],"retrieval,":[137,139],"multi-instance":[138],"recognition.":[142],"Our":[143],"results":[144],"demonstrate":[145],"effectiveness":[147],"proposed":[150],"their":[154],"counterfactuals,":[155],"achieve":[157],"significant":[158],"improvements":[159],"multiple":[161],"tasks.":[162]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}