{"id":"https://openalex.org/W7160213447","doi":"https://doi.org/10.1111/cgf.70420","title":"SAGE: Structure\u2010Aware Generative Video Transitions between Diverse Clips","display_name":"SAGE: Structure\u2010Aware Generative Video Transitions between Diverse Clips","publication_year":2026,"publication_date":"2026-04-30","ids":{"openalex":"https://openalex.org/W7160213447","doi":"https://doi.org/10.1111/cgf.70420"},"language":"en","primary_location":{"id":"doi:10.1111/cgf.70420","is_oa":true,"landing_page_url":"https://doi.org/10.1111/cgf.70420","pdf_url":null,"source":{"id":"https://openalex.org/S67831204","display_name":"Computer Graphics Forum","issn_l":"0167-7055","issn":["0167-7055","1467-8659"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Graphics Forum","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1111/cgf.70420","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135190772","display_name":"Mia Kan","orcid":"https://orcid.org/0009-0007-5590-6706"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mia Kan","raw_affiliation_strings":["University College London"],"raw_orcid":"https://orcid.org/0009-0007-5590-6706","affiliations":[{"raw_affiliation_string":"University College London","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100729744","display_name":"Yilin Liu","orcid":"https://orcid.org/0000-0001-7336-1956"},"institutions":[{"id":"https://openalex.org/I1286353243","display_name":"Autodesk (United States)","ror":"https://ror.org/00pkt4594","country_code":"US","type":"company","lineage":["https://openalex.org/I1286353243"]},{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Yilin Liu","raw_affiliation_strings":["Autodesk Research","University College London"],"raw_orcid":"https://orcid.org/0000-0001-7336-1956","affiliations":[{"raw_affiliation_string":"Autodesk Research","institution_ids":["https://openalex.org/I1286353243"]},{"raw_affiliation_string":"University College London","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074690539","display_name":"Miloy J.Mitra","orcid":null},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]},{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Niloy J. Mitra","raw_affiliation_strings":["Adobe Research","University College London"],"raw_orcid":"https://orcid.org/0000-0002-2597-0914","affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]},{"raw_affiliation_string":"University College London","institution_ids":["https://openalex.org/I45129253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":3710,"currency":"USD","value_usd":3710},"apc_paid":{"value":3710,"currency":"USD","value_usd":3710},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.52771036,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.7221999764442444,"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":0.7221999764442444,"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":0.11749999970197678,"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"}},{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.037300001829862595,"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/generative-grammar","display_name":"Generative grammar","score":0.8065999746322632},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.7315000295639038},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.6111999750137329},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5986999869346619},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.487199991941452},{"id":"https://openalex.org/keywords/generative-design","display_name":"Generative Design","score":0.4855000078678131},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4447000026702881},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.41830000281333923}],"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/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.8065999746322632},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.7315000295639038},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.6111999750137329},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5986999869346619},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5115000009536743},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.487199991941452},{"id":"https://openalex.org/C184408114","wikidata":"https://www.wikidata.org/wiki/Q1502022","display_name":"Generative Design","level":3,"score":0.4855000078678131},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4447000026702881},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.41830000281333923},{"id":"https://openalex.org/C194232998","wikidata":"https://www.wikidata.org/wiki/Q1606712","display_name":"Transition (genetics)","level":3,"score":0.3928000032901764},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.384799987077713},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.36090001463890076},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.3513000011444092},{"id":"https://openalex.org/C160174412","wikidata":"https://www.wikidata.org/wiki/Q873806","display_name":"Thumbnail","level":3,"score":0.3368000090122223},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.3027999997138977},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.28450000286102295},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.27559998631477356},{"id":"https://openalex.org/C50637493","wikidata":"https://www.wikidata.org/wiki/Q1136781","display_name":"Morphing","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.26030001044273376},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.2556999921798706},{"id":"https://openalex.org/C2778739407","wikidata":"https://www.wikidata.org/wiki/Q165372","display_name":"CLIPS","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1111/cgf.70420","is_oa":true,"landing_page_url":"https://doi.org/10.1111/cgf.70420","pdf_url":null,"source":{"id":"https://openalex.org/S67831204","display_name":"Computer Graphics Forum","issn_l":"0167-7055","issn":["0167-7055","1467-8659"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Graphics Forum","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1111/cgf.70420","is_oa":true,"landing_page_url":"https://doi.org/10.1111/cgf.70420","pdf_url":null,"source":{"id":"https://openalex.org/S67831204","display_name":"Computer Graphics Forum","issn_l":"0167-7055","issn":["0167-7055","1467-8659"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Graphics Forum","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F7525545622","display_name":"Adobe Research","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2010986468","https://openalex.org/W2065749455","https://openalex.org/W2949258649","https://openalex.org/W3004324868","https://openalex.org/W4312623579","https://openalex.org/W4390872683","https://openalex.org/W4390874575","https://openalex.org/W4402704536","https://openalex.org/W4402727507","https://openalex.org/W4413146268","https://openalex.org/W4413158080","https://openalex.org/W4414894542"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Video":[1],"transitions":[2,128,163],"aim":[3],"to":[4,87,174],"synthesize":[5],"intermediate":[6],"frames":[7],"between":[8,164],"two":[9],"clips,":[10],"but":[11,44],"na\u00efve":[12],"approaches":[13],"such":[14,79],"as":[15,80,104],"linear":[16],"blending":[17],"introduce":[18],"artifacts":[19],"that":[20,111,145],"limit":[21],"professional":[22],"use":[23],"or":[24,55],"break":[25],"temporal":[26,53],"coherence.":[27],"Traditional":[28],"techniques":[29],"(cross\u2010fades,":[30],"morphing,":[31],"frame":[32],"interpolation)":[33],"and":[34,64,83,90,119,133,150,158],"recent":[35],"generative":[36,123,153],"inbetweening":[37],"methods":[38],"can":[39],"produce":[40],"high\u2010quality":[41],"plausible":[42],"intermediates,":[43],"they":[45],"struggle":[46],"with":[47,122,135],"bridging":[48],"diverse":[49,165,188],"clips":[50],"involving":[51,187],"large":[52],"gaps":[54],"significant":[56],"semantic":[57],"differences,":[58],"leaving":[59],"a":[60,105],"gap":[61],"for":[62,161],"content\u2010aware":[63],"visually":[65],"coherent":[66],"transitions.":[67],"We":[68],"address":[69],"this":[70],"challenge":[71],"by":[72],"drawing":[73],"on":[74,94,155],"artistic":[75],"workflows,":[76],"distilling":[77],"strategies":[78],"aligning":[81],"silhouettes":[82],"interpolating":[84],"salient":[85],"features":[86],"preserve":[88],"structure":[89],"perceptual":[91],"continuity.":[92],"Building":[93],"these":[95],"strategies,":[96],"we":[97],"propose":[98],"SAGE":[99,146],"(Structure\u2010Aware":[100],"Generative":[101],"vidEo":[102],"transitions)":[103],"simple":[106,168],"yet":[107],"effective":[108],"zeroshot":[109],"approach":[110],"combines":[112],"structural":[113],"guidance,":[114],"provided":[115],"via":[116,193],"line":[117],"maps":[118],"motion":[120],"flow,":[121],"synthesis,":[124],"enabling":[125],"smooth,":[126],"motion\u2010consistent":[127],"without":[129],"fine\u2010tuning.":[130],"Extensive":[131],"experiments":[132],"comparison":[134],"current":[136],"alternatives,":[137],"namely":[138],"[RKT*22,":[139],"ZCL*24,":[140],"ZZX*24,":[141],"JHM*25,":[142],"ZRW*25],":[143],"demonstrate":[144],"outperforms":[147],"both":[148],"classical":[149],"the":[151,172,194],"latest":[152],"baselines":[154],"quantitative":[156],"metrics":[157],"user":[159],"studies":[160],"producing":[162],"clips.":[166,189],"The":[167],"method":[169],"effectively":[170],"bypasses":[171],"need":[173],"acquire":[175],"suitable":[176],"training":[177],"data,":[178],"which":[179],"is":[180,191],"particularly":[181],"difficult":[182],"in":[183],"our":[184],"creative":[185],"setting":[186],"Code":[190],"available":[192],"project":[195],"page":[196],"at":[197],"https://kan32501.github.io/sage.github.io/":[198],".":[199]},"counts_by_year":[],"updated_date":"2026-06-18T08:10:14.011955","created_date":"2026-05-05T00:00:00"}