{"id":"https://openalex.org/W4404987757","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1817","title":"Self-Correcting Text-to-Video Generation with Misalignment Detection and Localized Refinement","display_name":"Self-Correcting Text-to-Video Generation with Misalignment Detection and Localized Refinement","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4404987757","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1817"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.1817","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1817","pdf_url":"https://aclanthology.org/2026.findings-acl.1817.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.1817.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049930385","display_name":"Daeun Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daeun Lee","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054456399","display_name":"Jaehong Yoon","orcid":"https://orcid.org/0000-0002-9653-9590"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jaehong Yoon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101760065","display_name":"Jaemin Cho","orcid":"https://orcid.org/0000-0003-1148-5413"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jaemin Cho","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5114987911","display_name":"Mohit Bansal","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohit Bansal","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":20.1596,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.96229624,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"36464","last_page":"36489"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.975600004196167,"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/T11439","display_name":"Video Analysis and Summarization","score":0.975600004196167,"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/T12290","display_name":"Human Motion and Animation","score":0.9460999965667725,"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/computer-science","display_name":"Computer science","score":0.5627965331077576}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5627965331077576}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.1817","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1817","pdf_url":"https://aclanthology.org/2026.findings-acl.1817.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2411.15115","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.15115","pdf_url":"https://arxiv.org/pdf/2411.15115","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":"pmh:oai:arXiv.org:2411.15115","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2411.15115","pdf_url":"https://arxiv.org/pdf/2411.15115","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.2411.15115","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2411.15115","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.1817","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1817","pdf_url":"https://aclanthology.org/2026.findings-acl.1817.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2921176242","display_name":null,"funder_award_id":"W911NF2110220","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G5599941371","display_name":null,"funder_award_id":"N00014-23-1-2356","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G580734012","display_name":"AI Institute for Engaged Learning","funder_award_id":"2112635","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7357862116","display_name":null,"funder_award_id":"N66001-19-2-4031","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G8215844777","display_name":null,"funder_award_id":"N66001-19","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404987757.pdf","grobid_xml":"https://content.openalex.org/works/W4404987757.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Recent":[0],"text-to-video":[1],"(T2V)":[2],"diffusion":[3],"models":[4],"have":[5],"made":[6],"remarkable":[7],"progress":[8],"in":[9],"generating":[10],"high-quality":[11],"videos.However,":[12],"they":[13],"often":[14],"struggle":[15],"to":[16],"align":[17],"with":[18,83,92,147],"complex":[19],"text":[20],"prompts,":[21],"particularly":[22],"when":[23],"multiple":[24],"objects,":[25],"attributes,":[26],"or":[27],"spatial":[28],"relations":[29],"are":[30],"specified.We":[31],"introduce":[32],"VIDEOREPAIR,":[33],"the":[34,166],"first":[35],"self-correcting,":[36],"training-free,":[37],"and":[38,49,113,120,138,145,169],"model-agnostic":[39],"video":[40],"refinement":[41,81,101],"framework":[42],"that":[43,57,66],"automatically":[44,93],"detects":[45],"finegrained":[46],"text-video":[47],"misalignments":[48],"performs":[50],"targeted,":[51],"localized":[52,122],"corrections.Our":[53],"key":[54],"insight":[55],"is":[56],"even":[58],"misaligned":[59,98,118],"videos":[60],"usually":[61],"contain":[62],"correctly":[63,105],"generated":[64,94,106,140],"regions":[65,110,128],"should":[67],"be":[68],"preserved":[69,137],"rather":[70],"than":[71],"regenerated.Building":[72],"on":[73],"this":[74],"observation,":[75],"VIDEOREPAIR":[76,152],"proposes":[77],"a":[78],"novel":[79],"region-preserving":[80],"strategy":[82],"three":[84],"stages:":[85],"(i)":[86],"misalignment":[87],"detection,":[88],"where":[89],"MLLM-based":[90],"evaluation":[91,95],"questions":[96],"identifies":[97],"regions;":[99],"(ii)":[100],"planning,":[102],"which":[103,124],"preserves":[104],"entities,":[107],"segments":[108],"their":[109],"across":[111,159],"frames,":[112],"constructs":[114],"targeted":[115],"prompts":[116],"for":[117],"areas;":[119],"(iii)":[121],"refinement,":[123],"selectively":[125],"regenerates":[126],"problematic":[127],"while":[129],"preserving":[130],"faithful":[131],"content":[132],"through":[133],"joint":[134],"optimization":[135],"of":[136,171],"newly":[139],"areas.On":[141],"two":[142],"benchmarks,":[143],"EvalCrafter":[144],"T2V-CompBench":[146],"four":[148],"recent":[149,157],"T2V":[150],"backbones,":[151],"achieves":[153],"substantial":[154],"improvements":[155],"over":[156],"baselines":[158],"diverse":[160],"alignment":[161],"metrics.Comprehensive":[162],"ablations":[163],"further":[164],"demonstrate":[165],"efficiency,":[167],"robustness,":[168],"interpretability":[170],"our":[172],"framework.":[173]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2025-10-10T00:00:00"}