{"id":"https://openalex.org/W4416707480","doi":"https://doi.org/10.1109/tvcg.2025.3636949","title":"Zero-Shot Video Translation via Token Warping","display_name":"Zero-Shot Video Translation via Token Warping","publication_year":2025,"publication_date":"2025-11-26","ids":{"openalex":"https://openalex.org/W4416707480","doi":"https://doi.org/10.1109/tvcg.2025.3636949","pmid":"https://pubmed.ncbi.nlm.nih.gov/41296969"},"language":"en","primary_location":{"id":"doi:10.1109/tvcg.2025.3636949","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvcg.2025.3636949","pdf_url":null,"source":{"id":"https://openalex.org/S84775595","display_name":"IEEE Transactions on Visualization and Computer Graphics","issn_l":"1077-2626","issn":["1077-2626","1941-0506","2160-9306"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Visualization and Computer Graphics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://ink.library.smu.edu.sg/sis_research/11050","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109313946","display_name":"Haiming Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Haiming Zhu","raw_affiliation_strings":["School of Computing and Information Systems, Singapore Management University, Singapore"],"raw_orcid":"https://orcid.org/0009-0008-4885-6322","affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems, Singapore Management University, Singapore","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003836412","display_name":"Yangyang Xu","orcid":"https://orcid.org/0000-0002-3383-4349"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yangyang Xu","raw_affiliation_strings":["School of Intelligence Science and Engineering, Harbin Institute of Technology, Shenzhen, China","School of Intelligence Science and Engineering, Harbin Institute of Technology (Shenzhen), China"],"raw_orcid":"https://orcid.org/0000-0002-3383-4349","affiliations":[{"raw_affiliation_string":"School of Intelligence Science and Engineering, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"School of Intelligence Science and Engineering, Harbin Institute of Technology (Shenzhen), China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050817770","display_name":"Jun Yu","orcid":"https://orcid.org/0000-0003-1922-7283"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Yu","raw_affiliation_strings":["School of Intelligence Science and Engineering, Harbin Institute of Technology, Shenzhen, China","School of Intelligence Science and Engineering, Harbin Institute of Technology (Shenzhen), China"],"raw_orcid":"https://orcid.org/0000-0003-1922-7283","affiliations":[{"raw_affiliation_string":"School of Intelligence Science and Engineering, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"School of Intelligence Science and Engineering, Harbin Institute of Technology (Shenzhen), China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056103024","display_name":"Shengfeng He","orcid":"https://orcid.org/0000-0002-3802-4644"},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Shengfeng He","raw_affiliation_strings":["School of Computing and Information Systems, Singapore Management University, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-3802-4644","affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems, Singapore Management University, Singapore","institution_ids":["https://openalex.org/I79891267"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5109313946"],"corresponding_institution_ids":["https://openalex.org/I79891267"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35296081,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":"2","first_page":"1582","last_page":"1592"},"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":0.9584000110626221,"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":0.9584000110626221,"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":0.02239999920129776,"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/T11448","display_name":"Face recognition and analysis","score":0.002199999988079071,"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/image-warping","display_name":"Image warping","score":0.8212000131607056},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5557000041007996},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5127000212669373},{"id":"https://openalex.org/keywords/view-synthesis","display_name":"View synthesis","score":0.47749999165534973},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.424699991941452},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.4214000105857849},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4180999994277954},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.39489999413490295}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8896999955177307},{"id":"https://openalex.org/C157202957","wikidata":"https://www.wikidata.org/wiki/Q1659609","display_name":"Image warping","level":2,"score":0.8212000131607056},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5557000041007996},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5515999794006348},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5127000212669373},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4830000102519989},{"id":"https://openalex.org/C2776449333","wikidata":"https://www.wikidata.org/wiki/Q7928781","display_name":"View synthesis","level":3,"score":0.47749999165534973},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.424699991941452},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.4214000105857849},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4180999994277954},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.39489999413490295},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.39480000734329224},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3677000105381012},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3474000096321106},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3249000012874603},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.2953999936580658},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2915000021457672},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.2721000015735626},{"id":"https://openalex.org/C2779757391","wikidata":"https://www.wikidata.org/wiki/Q6002292","display_name":"Image translation","level":3,"score":0.26589998602867126},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C153715457","wikidata":"https://www.wikidata.org/wiki/Q254183","display_name":"Augmented reality","level":2,"score":0.2556000053882599}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tvcg.2025.3636949","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvcg.2025.3636949","pdf_url":null,"source":{"id":"https://openalex.org/S84775595","display_name":"IEEE Transactions on Visualization and Computer Graphics","issn_l":"1077-2626","issn":["1077-2626","1941-0506","2160-9306"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Visualization and Computer Graphics","raw_type":"journal-article"},{"id":"pmid:41296969","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41296969","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on visualization and computer graphics","raw_type":null},{"id":"pmh:oai:ink.library.smu.edu.sg:sis_research-12051","is_oa":true,"landing_page_url":"https://ink.library.smu.edu.sg/sis_research/11050","pdf_url":null,"source":{"id":"https://openalex.org/S4306401925","display_name":"Singapore Management University Institutional Knowledge (InK) (Singapore Management University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79891267","host_organization_name":"Singapore Management University","host_organization_lineage":["https://openalex.org/I79891267"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://doi.org/10.1109/TVCG.2025.3636949","raw_type":"Journal Article"}],"best_oa_location":{"id":"pmh:oai:ink.library.smu.edu.sg:sis_research-12051","is_oa":true,"landing_page_url":"https://ink.library.smu.edu.sg/sis_research/11050","pdf_url":null,"source":{"id":"https://openalex.org/S4306401925","display_name":"Singapore Management University Institutional Knowledge (InK) (Singapore Management University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79891267","host_organization_name":"Singapore Management University","host_organization_lineage":["https://openalex.org/I79891267"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://doi.org/10.1109/TVCG.2025.3636949","raw_type":"Journal Article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2073371311","display_name":null,"funder_award_id":"JCYJ20250604145532041","funder_id":"https://openalex.org/F4320316880","funder_display_name":"Natural Science Foundation of Shenzhen City"},{"id":"https://openalex.org/G7039621881","display_name":null,"funder_award_id":"62502117","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320312071","display_name":"Ministry of Education, Libya","ror":"https://ror.org/02w030k33"},{"id":"https://openalex.org/F4320316880","display_name":"Natural Science Foundation of Shenzhen City","ror":null},{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"},{"id":"https://openalex.org/F4320320751","display_name":"Ministry of Education - Singapore","ror":"https://ror.org/01kcva023"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2963734522","https://openalex.org/W3034950620","https://openalex.org/W3156080566","https://openalex.org/W3215023725","https://openalex.org/W4302275890","https://openalex.org/W4312314586","https://openalex.org/W4312388283","https://openalex.org/W4312933868","https://openalex.org/W4313887289","https://openalex.org/W4386076532","https://openalex.org/W4386113271","https://openalex.org/W4388519998","https://openalex.org/W4389539288","https://openalex.org/W4390871723","https://openalex.org/W4390871782","https://openalex.org/W4390872556","https://openalex.org/W4390872681","https://openalex.org/W4390873054","https://openalex.org/W4390873135","https://openalex.org/W4390873195","https://openalex.org/W4390874580","https://openalex.org/W4391807605","https://openalex.org/W4393148505","https://openalex.org/W4396712511","https://openalex.org/W4400818431","https://openalex.org/W4402703121","https://openalex.org/W4402716124","https://openalex.org/W4402727429","https://openalex.org/W4403888488","https://openalex.org/W4404520905","https://openalex.org/W4405786180","https://openalex.org/W4407351351","https://openalex.org/W4413146321","https://openalex.org/W4413147048"],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,65,76,79,115,119,129,140,147,158,175],"revolution":[2],"of":[3,67,78,118],"generative":[4],"AI,":[5],"video-related":[6],"tasks":[7],"have":[8],"been":[9],"widely":[10],"studied.":[11],"However,":[12],"current":[13,141],"state-of-the-art":[14,217],"video":[15,43,47,210],"models":[16,21],"still":[17],"lag":[18],"behind":[19],"image":[20],"in":[22,57,82,154,227],"visual":[23],"quality":[24],"and":[25,54,69,87,134,160,194,221],"user":[26],"control":[27],"over":[28],"generated":[29],"content.":[30],"In":[31,90],"this":[32],"paper,":[33],"we":[34,150],"introduce":[35],"TokenWarping,":[36],"a":[37],"novel":[38],"framework":[39,185],"for":[40],"temporally":[41,181],"coherent":[42,182],"translation.":[44,183],"Existing":[45],"diffusion-based":[46],"editing":[48,202],"approaches":[49],"rely":[50],"solely":[51],"on":[52,174,208],"key":[53,159],"value":[55,135,161],"patches":[56,81,162],"self-attention":[58,176],"to":[59,127],"ensure":[60],"temporal":[61,88,99,164],"consistency,":[62],"often":[63],"sacrificing":[64],"preservation":[66],"local":[68],"structural":[70],"regions.":[71],"Critically,":[72],"these":[73,122],"methods":[74,218],"overlook":[75],"significance":[77],"query":[80,148],"achieving":[83],"accurate":[84],"feature":[85,152],"aggregation":[86,153],"coherence.":[89],"contrast,":[91],"TokenWarping":[92,215],"leverages":[93],"complementary":[94],"token":[95,169],"priors":[96],"by":[97,107],"constructing":[98],"correlations":[100],"across":[101,166],"different":[102],"frames.":[103,167],"Our":[104,184],"method":[105],"begins":[106],"extracting":[108],"optical":[109,123],"flows":[110,124],"from":[111],"source":[112],"videos.":[113],"During":[114],"denoising":[116],"process":[117],"diffusion":[120],"model,":[121],"are":[125,225],"used":[126],"warp":[128],"previous":[130],"frame's":[131,142],"query,":[132],"key,":[133],"patches,":[136,149],"aligning":[137],"them":[138],"with":[139,199],"patches.":[143],"By":[144],"directly":[145],"warping":[146,157,170],"enhance":[151],"self-attention,":[155],"while":[156],"ensures":[163],"consistency":[165],"This":[168],"imposes":[171],"explicit":[172],"constraints":[173],"layer":[177],"outputs,":[178],"effectively":[179],"ensuring":[180],"does":[186],"not":[187],"require":[188],"any":[189],"additional":[190],"training":[191],"or":[192],"fine-tuning":[193],"can":[195],"be":[196],"seamlessly":[197],"integrated":[198],"existing":[200],"text-to-image":[201],"methods.":[203],"We":[204],"conduct":[205],"extensive":[206],"experiments":[207],"various":[209],"translation":[211],"tasks,":[212],"demonstrating":[213],"that":[214],"surpasses":[216],"both":[219],"qualitatively":[220],"quantitatively.":[222],"Video":[223],"demonstrations":[224],"available":[226],"supplementary":[228],"materials.":[229]},"counts_by_year":[],"updated_date":"2026-02-09T05:59:30.833894","created_date":"2025-11-27T00:00:00"}
