{"id":"https://openalex.org/W4417125630","doi":"https://doi.org/10.1145/3757377.3763896","title":"Cut2Next: Generating Next Shot via In-Context Tuning","display_name":"Cut2Next: Generating Next Shot via In-Context Tuning","publication_year":2025,"publication_date":"2025-12-08","ids":{"openalex":"https://openalex.org/W4417125630","doi":"https://doi.org/10.1145/3757377.3763896"},"language":null,"primary_location":{"id":"doi:10.1145/3757377.3763896","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3757377.3763896","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SIGGRAPH Asia 2025 Conference Papers","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3757377.3763896","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101697054","display_name":"Jingwen He","orcid":"https://orcid.org/0000-0001-9021-1167"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jingwen He","raw_affiliation_strings":["Chinese University of Hong Kong, Hongkong, China"],"raw_orcid":"https://orcid.org/0000-0001-9021-1167","affiliations":[{"raw_affiliation_string":"Chinese University of Hong Kong, Hongkong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hongbo Liu","orcid":"https://orcid.org/0009-0008-0753-1652"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongbo Liu","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0008-0753-1652","affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017834956","display_name":"J.H. Li","orcid":"https://orcid.org/0009-0007-1785-8133"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jiajun Li","raw_affiliation_strings":["The Hong Kong University of Science and Technology, Hongkong, China"],"raw_orcid":"https://orcid.org/0009-0007-1785-8133","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology, Hongkong, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101830887","display_name":"Ziqi Huang","orcid":"https://orcid.org/0000-0001-8008-5873"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ziqi Huang","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-8008-5873","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100748135","display_name":"Yu Qiao","orcid":"https://orcid.org/0000-0002-1889-2567"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiao Yu","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-1889-2567","affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087818121","display_name":"Wanli Ouyang","orcid":"https://orcid.org/0000-0002-9163-2761"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Wanli Ouyang","raw_affiliation_strings":["Chinese University of Hong Kong, Hongkong, China"],"raw_orcid":"https://orcid.org/0000-0002-9163-2761","affiliations":[{"raw_affiliation_string":"Chinese University of Hong Kong, Hongkong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100406050","display_name":"Ziwei Liu","orcid":"https://orcid.org/0000-0002-4220-5958"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ziwei Liu","raw_affiliation_strings":["Nanyang Technological University (NTU), Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-4220-5958","affiliations":[{"raw_affiliation_string":"Nanyang Technological University (NTU), Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"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":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"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":0.4796999990940094,"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":0.4796999990940094,"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":0.11580000072717667,"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/T10799","display_name":"Data Visualization and Analytics","score":0.055799998342990875,"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/narrative","display_name":"Narrative","score":0.489300012588501},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.482699990272522},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.4666000008583069},{"id":"https://openalex.org/keywords/sophistication","display_name":"Sophistication","score":0.46050000190734863},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.45509999990463257},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.41839998960494995},{"id":"https://openalex.org/keywords/one-shot","display_name":"One shot","score":0.41370001435279846},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.39410001039505005},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.3797000050544739}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7408999800682068},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5031999945640564},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.489300012588501},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.482699990272522},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.4666000008583069},{"id":"https://openalex.org/C168725872","wikidata":"https://www.wikidata.org/wiki/Q991663","display_name":"Sophistication","level":2,"score":0.46050000190734863},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.45509999990463257},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.41839998960494995},{"id":"https://openalex.org/C2992734406","wikidata":"https://www.wikidata.org/wiki/Q413267","display_name":"One shot","level":2,"score":0.41370001435279846},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4018000066280365},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.39410001039505005},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.3797000050544739},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.34880000352859497},{"id":"https://openalex.org/C136085584","wikidata":"https://www.wikidata.org/wiki/Q910289","display_name":"Overlay","level":2,"score":0.34860000014305115},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.3456999957561493},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3330000042915344},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3255000114440918},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.2921999990940094},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.2831000089645386},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.28119999170303345},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.25929999351501465},{"id":"https://openalex.org/C47350684","wikidata":"https://www.wikidata.org/wiki/Q5157306","display_name":"Computational creativity","level":3,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3757377.3763896","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3757377.3763896","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SIGGRAPH Asia 2025 Conference Papers","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3757377.3763896","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3757377.3763896","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SIGGRAPH Asia 2025 Conference Papers","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W3095481265","https://openalex.org/W3201594678","https://openalex.org/W4214745154","https://openalex.org/W4386072096","https://openalex.org/W4390872297","https://openalex.org/W4390873195","https://openalex.org/W4400818431","https://openalex.org/W4402727699","https://openalex.org/W4404965692","https://openalex.org/W4413147739","https://openalex.org/W4415795847"],"related_works":[],"abstract_inverted_index":{"Effective":[0],"multi-shot":[1],"generation":[2],"demands":[3],"purposeful,":[4],"film-like":[5],"transitions":[6],"and":[7,46,104,114,133,151,159,171,191,203],"strict":[8],"cinematic":[9,48,74,193],"continuity.":[10,75],"Current":[11],"methods,":[12],"however,":[13],"often":[14],"prioritize":[15],"basic":[16],"visual":[17,169],"consistency,":[18],"neglecting":[19],"crucial":[20],"editing":[21,69,106,189],"patterns":[22,70,190],"(e.g.,":[23],"shot/reverse":[24],"shot,":[25],"cutaways)":[26],"that":[27,37,64],"drive":[28],"narrative":[29,44],"flow":[30],"for":[31,162,181,184],"compelling":[32],"storytelling.":[33],"This":[34,95],"yields":[35],"outputs":[36],"may":[38],"be":[39],"visually":[40],"coherent":[41,205],"but":[42],"lack":[43],"sophistication":[45],"true":[47],"integrity.":[49],"To":[50],"bridge":[51],"this,":[52],"we":[53],"introduce":[54,160],"Next":[55],"Shot":[56],"Generation":[57],"(NSG):":[58],"synthesizing":[59],"a":[60,80,90,178],"subsequent,":[61],"high-quality":[62],"shot":[63],"critically":[65],"conforms":[66],"to":[67,100,121,187,198],"professional":[68],"while":[71],"upholding":[72],"rigorous":[73],"Our":[76],"framework,":[77],"Cut2Next,":[78,182],"leverages":[79],"Diffusion":[81],"Transformer":[82],"(DiT).":[83],"It":[84],"employs":[85],"in-context":[86],"tuning":[87],"guided":[88],"by":[89],"novel":[91],"Hierarchical":[92,134],"Multi-Prompting":[93],"strategy.":[94],"strategy":[96],"uses":[97],"Relational":[98],"Prompts":[99,109],"define":[101],"overall":[102,192],"context":[103],"inter-shot":[105],"styles.":[107],"Individual":[108],"then":[110],"specify":[111],"per-shot":[112],"content":[113],"cinematographic":[115],"attributes.":[116],"Together,":[117],"these":[118,140],"guide":[119],"Cut2Next":[120,166],"generate":[122,199],"cinematically":[123,204],"appropriate":[124],"next":[125],"shots.":[126,207],"Architectural":[127],"innovations,":[128],"Context-Aware":[129],"Condition":[130],"Injection":[131],"(CACI)":[132],"Attention":[135],"Mask":[136],"(HAM),":[137],"further":[138],"integrate":[139],"diverse":[141],"signals":[142],"without":[143],"introducing":[144],"new":[145],"parameters.":[146],"We":[147],"construct":[148],"RawCuts":[149],"(large-scale)":[150],"CuratedCuts":[152],"(refined)":[153],"datasets,":[154],"both":[155],"with":[156],"hierarchical":[157],"prompts,":[158],"CutBench":[161],"evaluation.":[163],"Experiments":[164],"show":[165],"excels":[167],"in":[168],"consistency":[170],"text":[172],"fidelity.":[173],"Crucially,":[174],"user":[175],"studies":[176],"reveal":[177],"strong":[179],"preference":[180],"particularly":[183],"its":[185,196],"adherence":[186],"intended":[188],"continuity,":[194],"validating":[195],"ability":[197],"high-quality,":[200],"narratively":[201],"expressive,":[202],"subsequent":[206]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-12-08T00:00:00"}