{"id":"https://openalex.org/W4417438156","doi":"https://doi.org/10.1109/iccv51701.2025.01691","title":"TokensGen: Harnessing Condensed Tokens for Long Video Generation","display_name":"TokensGen: Harnessing Condensed Tokens for Long Video Generation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417438156","doi":"https://doi.org/10.1109/iccv51701.2025.01691"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01691","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01691","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":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.15728","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120836428","display_name":"Wenqi Ouyang","orcid":null},"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":true,"raw_author_name":"Wenqi Ouyang","raw_affiliation_strings":["Nanyang Technological University,S-Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,S-Lab","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100584895","display_name":"Zeqi Xiao","orcid":null},"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":"Zeqi Xiao","raw_affiliation_strings":["Nanyang Technological University,S-Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,S-Lab","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120836429","display_name":"Danni Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Danni Yang","raw_affiliation_strings":["SenseTime Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100698862","display_name":"Yifan Zhou","orcid":"https://orcid.org/0009-0004-6250-8333"},"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":"Yifan Zhou","raw_affiliation_strings":["Nanyang Technological University,S-Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,S-Lab","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100784284","display_name":"Shuai Yang","orcid":"https://orcid.org/0000-0003-3371-2197"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Yang","raw_affiliation_strings":["Wangxuan Institute of Computer Technology, Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wangxuan Institute of Computer Technology, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043951834","display_name":"Lei Yang","orcid":"https://orcid.org/0000-0002-0571-5924"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei Yang","raw_affiliation_strings":["SenseTime Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079767760","display_name":"Jianlou Si","orcid":"https://orcid.org/0000-0002-2029-6588"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianlou Si","raw_affiliation_strings":["SenseTime Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Research","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052549072","display_name":"Xingang Pan","orcid":"https://orcid.org/0000-0002-5825-9467"},"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":"Xingang Pan","raw_affiliation_strings":["Nanyang Technological University,S-Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,S-Lab","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5120836428"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38781841,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"18197","last_page":"18206"},"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":0.8662999868392944,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","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":0.024700000882148743,"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/T11439","display_name":"Video Analysis and Summarization","score":0.018200000748038292,"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/security-token","display_name":"Security token","score":0.7078999876976013},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.49219998717308044},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.48579999804496765},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.436599999666214},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.4180999994277954},{"id":"https://openalex.org/keywords/video-processing","display_name":"Video processing","score":0.39089998602867126},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.3856000006198883},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.3635999858379364},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.3522000014781952}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8555999994277954},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.7078999876976013},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.49219998717308044},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.48579999804496765},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.436599999666214},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.4180999994277954},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.39089998602867126},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.3856000006198883},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3813000023365021},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.3635999858379364},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3522000014781952},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.34950000047683716},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.3287000060081482},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3237000107765198},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.29420000314712524},{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.29109999537467957},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.28940001130104065},{"id":"https://openalex.org/C2986737658","wikidata":"https://www.wikidata.org/wiki/Q30103009","display_name":"Tensor decomposition","level":3,"score":0.2865999937057495},{"id":"https://openalex.org/C113954288","wikidata":"https://www.wikidata.org/wiki/Q186885","display_name":"Timestamp","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.2757999897003174},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.27469998598098755},{"id":"https://openalex.org/C2776449333","wikidata":"https://www.wikidata.org/wiki/Q7928781","display_name":"View synthesis","level":3,"score":0.27059999108314514},{"id":"https://openalex.org/C106030495","wikidata":"https://www.wikidata.org/wiki/Q1797012","display_name":"Video compression picture types","level":4,"score":0.26440000534057617},{"id":"https://openalex.org/C2778739407","wikidata":"https://www.wikidata.org/wiki/Q165372","display_name":"CLIPS","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C146044194","wikidata":"https://www.wikidata.org/wiki/Q5157334","display_name":"Computational photography","level":4,"score":0.2590000033378601},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.2556999921798706},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C128840427","wikidata":"https://www.wikidata.org/wiki/Q1302174","display_name":"Motion compensation","level":2,"score":0.25200000405311584},{"id":"https://openalex.org/C2778598663","wikidata":"https://www.wikidata.org/wiki/Q1407599","display_name":"Video content analysis","level":4,"score":0.2515999972820282}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iccv51701.2025.01691","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01691","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:2507.15728","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.15728","pdf_url":"https://arxiv.org/pdf/2507.15728","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.15728","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.15728","pdf_url":"https://arxiv.org/pdf/2507.15728","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Generating":[0],"consistent":[1],"long":[2,51,173],"videos":[3],"is":[4],"a":[5,36,76,88,104,168],"complex":[6],"challenge:":[7],"while":[8],"diffusion-based":[9],"generative":[10],"models":[11],"generate":[12],"visually":[13],"impressive":[14],"short":[15,77,93,162],"clips,":[16,130],"extending":[17],"them":[18],"to":[19,24,44],"longer":[20],"durations":[21],"often":[22],"leads":[23],"memory":[25],"bottlenecks":[26],"and":[27,66,84,134,148,160,183],"long-term":[28,63,146],"inconsistency.":[29],"In":[30],"this":[31],"paper,":[32],"we":[33,72,100],"propose":[34],"TokensGen,":[35],"novel":[37],"two-stage":[38],"framework":[39],"that":[40,91,109,141],"leverages":[41],"condensed":[42,158],"tokens":[43,112,159],"address":[45],"these":[46],"issues.":[47],"Our":[48],"method":[49,166],"decomposes":[50],"video":[52,78,85,105,163,174],"generation":[53],"into":[54,95],"three":[55],"core":[56],"tasks:":[57],"(1)":[58],"inner-clip":[59],"semantic":[60],"control,":[61,65],"(2)":[62],"consistency":[64,117],"(3)":[67],"inter-clip":[68],"smooth":[69,136],"transition.":[70],"First,":[71],"train":[73],"To2V":[74],"(Token-to-Video),":[75],"diffusion":[79,107],"model":[80],"guided":[81],"by":[82],"text":[83],"tokens,":[86],"with":[87],"Video":[89],"Tokenizer":[90],"condenses":[92],"clips":[94],"semantically":[96],"rich":[97],"tokens.":[98],"Second,":[99],"introduce":[101],"T2To":[102],"(Text-to-Token),":[103],"token":[106],"transformer":[108],"generates":[110],"all":[111],"at":[113,191],"once,":[114],"ensuring":[115],"global":[116],"across":[118],"clips.":[119],"Finally,":[120],"during":[121],"inference,":[122],"an":[123],"adaptive":[124],"FIFO-Diffusion":[125],"strategy":[126],"seamlessly":[127],"connects":[128],"adjacent":[129],"reducing":[131],"boundary":[132],"artifacts":[133],"enhancing":[135],"transitions.":[137],"Experimental":[138],"results":[139],"demonstrate":[140],"our":[142,165,188],"approach":[143],"significantly":[144],"enhances":[145],"temporal":[147],"content":[149],"coherence":[150],"without":[151],"incurring":[152],"prohibitive":[153],"computational":[154],"overhead.":[155],"By":[156],"leveraging":[157],"pre-trained":[161],"models,":[164],"provides":[167],"scalable,":[169],"modular":[170],"solution":[171],"for":[172,179],"generation,":[175],"opening":[176],"new":[177],"possibilities":[178],"storytelling,":[180],"cinematic":[181],"production,":[182],"immersive":[184],"simulations.":[185],"Please":[186],"see":[187],"project":[189],"page":[190],"https://vicky0522.github.io/tokensgen-webpage/":[192],".":[193]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}