{"id":"https://openalex.org/W4414360111","doi":"https://doi.org/10.24963/ijcai.2025/119","title":"Shaping a Stabilized Video by Mitigating Unintended Changes for Concept-Augmented Video Editing","display_name":"Shaping a Stabilized Video by Mitigating Unintended Changes for Concept-Augmented Video Editing","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414360111","doi":"https://doi.org/10.24963/ijcai.2025/119"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/119","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/119","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"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/A5087248222","display_name":"Min Guo","orcid":"https://orcid.org/0000-0002-0052-8329"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingce Guo","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101532408","display_name":"Jingxuan He","orcid":"https://orcid.org/0009-0003-9858-5640"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingxuan He","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011007342","display_name":"Yufei Yin","orcid":"https://orcid.org/0000-0001-9643-4601"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yufei Yin","raw_affiliation_strings":["Hangzhou Dianzi University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hangzhou Dianzi University","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhangye Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhangye Wang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076104260","display_name":"Shengeng Tang","orcid":"https://orcid.org/0000-0001-6313-2543"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengeng Tang","raw_affiliation_strings":["Hefei University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei University of Technology","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060524512","display_name":"Lechao Cheng","orcid":"https://orcid.org/0000-0002-7546-9052"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lechao Cheng","raw_affiliation_strings":["Hefei University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei University of Technology","institution_ids":["https://openalex.org/I16365422"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1062","last_page":"1070"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12720","display_name":"Multimedia Communication and Technology","score":0.986299991607666,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12720","display_name":"Multimedia Communication and Technology","score":0.986299991607666,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.972100019454956,"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/T13999","display_name":"Digital Rights Management and Security","score":0.9693999886512756,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/fidelity","display_name":"Fidelity","score":0.5403000116348267},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4869000017642975},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4740000069141388},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.4433000087738037},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.39410001039505005},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.37529999017715454},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.3610000014305115},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.32910001277923584}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8144999742507935},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.5403000116348267},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4869000017642975},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4740000069141388},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.4433000087738037},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.42660000920295715},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.39410001039505005},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.37529999017715454},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3610000014305115},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.32910001277923584},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3262999951839447},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3190000057220459},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.3093999922275543},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.30869999527931213},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.2856999933719635},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2849999964237213},{"id":"https://openalex.org/C2776240099","wikidata":"https://www.wikidata.org/wiki/Q327018","display_name":"Interrogation","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/119","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/119","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Text-driven":[0],"video":[1],"editing":[2,94],"powered":[3],"by":[4],"generative":[5],"diffusion":[6,83],"models":[7],"holds":[8],"significant":[9],"promise":[10],"for":[11],"applications":[12],"spanning":[13],"film":[14],"production,":[15],"advertising,":[16],"and":[17,96,122,131,149,160],"beyond.":[18],"However,":[19],"the":[20,64,77,82,98,120,133],"limited":[21],"expressiveness":[22],"of":[23,81,100,135],"pre-trained":[24],"word":[25],"embeddings":[26],"often":[27],"restricts":[28],"nuanced":[29],"edits,":[30],"especially":[31],"when":[32,103],"targeting":[33],"novel":[34,45,136],"concepts":[35],"with":[36],"specific":[37],"attributes.":[38],"In":[39],"this":[40],"work,":[41],"we":[42,108],"present":[43],"a":[44,110],"Concept-Augmented":[46],"Textual":[47],"Inversion":[48],"(CATI)":[49],"framework":[50],"that":[51,141],"flexibly":[52],"integrates":[53],"new":[54],"object":[55],"information":[56],"from":[57],"user-provided":[58],"concept":[59,89],"videos.":[60,163],"By":[61],"fine-tuning":[62],"only":[63,146],"V":[65],"(Value)":[66],"projection":[67],"in":[68,157],"attention":[69,79,101],"via":[70],"Low-Rank":[71],"Adaptation":[72],"(LoRA),":[73],"our":[74,142],"approach":[75],"preserves":[76],"original":[78],"distribution":[80],"model":[84],"while":[85],"efficiently":[86],"incorporating":[87],"external":[88],"knowledge.":[90],"To":[91],"further":[92],"stabilize":[93],"results":[95],"mitigate":[97],"issue":[99],"dispersion":[102],"prompt":[104],"keywords":[105],"are":[106],"modified,":[107],"introduce":[109],"Dual":[111],"Prior":[112],"Supervision":[113],"(DPS)":[114],"mechanism.":[115],"DPS":[116],"supervises":[117],"cross-attention":[118],"between":[119],"source":[121,165],"target":[123],"prompts,":[124],"preventing":[125],"undesired":[126],"changes":[127],"to":[128],"non-target":[129],"areas":[130],"improving":[132],"fidelity":[134],"concepts.":[137],"Extensive":[138],"evaluations":[139],"demonstrate":[140],"plug-and-play":[143],"solution":[144],"not":[145],"maintains":[147],"spatial":[148],"temporal":[150],"consistency":[151],"but":[152],"also":[153],"outperforms":[154],"state-of-the-art":[155],"methods":[156],"generating":[158],"lifelike":[159],"stable":[161],"edited":[162],"The":[164],"code":[166],"is":[167],"publicly":[168],"available":[169],"at":[170],"https://guomc9.github.io/STIVE-PAGE/.":[171]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
