{"id":"https://openalex.org/W4413146224","doi":"https://doi.org/10.1109/cvpr52734.2025.02140","title":"VidSeg: Training-free Video Semantic Segmentation based on Diffusion Models","display_name":"VidSeg: Training-free Video Semantic Segmentation based on Diffusion Models","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413146224","doi":"https://doi.org/10.1109/cvpr52734.2025.02140"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.02140","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.02140","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"type":"article","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/A5100391185","display_name":"Qian Wang","orcid":"https://orcid.org/0009-0007-5396-1410"},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]},{"id":"https://openalex.org/I4210099236","display_name":"Kootenay Association for Science & Technology","ror":"https://ror.org/011pv9p44","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210099236"]}],"countries":["CA","SA"],"is_corresponding":true,"raw_author_name":"Qian Wang","raw_affiliation_strings":["KAUST"],"affiliations":[{"raw_affiliation_string":"KAUST","institution_ids":["https://openalex.org/I4210099236","https://openalex.org/I71920554"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033942292","display_name":"Abdelrahman Eldesokey","orcid":"https://orcid.org/0000-0003-3292-7153"},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]},{"id":"https://openalex.org/I4210099236","display_name":"Kootenay Association for Science & Technology","ror":"https://ror.org/011pv9p44","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210099236"]}],"countries":["CA","SA"],"is_corresponding":false,"raw_author_name":"Abdelrahman Eldesokey","raw_affiliation_strings":["KAUST"],"affiliations":[{"raw_affiliation_string":"KAUST","institution_ids":["https://openalex.org/I4210099236","https://openalex.org/I71920554"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017462023","display_name":"Mohit Mendiratta","orcid":null},"institutions":[{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Mohit Mendiratta","raw_affiliation_strings":["Max Planck Institute for Informatics"],"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Informatics","institution_ids":["https://openalex.org/I4210109712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064046791","display_name":"Fangneng Zhan","orcid":"https://orcid.org/0000-0003-1502-6847"},"institutions":[{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Fangneng Zhan","raw_affiliation_strings":["Max Planck Institute for Informatics"],"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Informatics","institution_ids":["https://openalex.org/I4210109712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084928022","display_name":"Adam Kortylewski","orcid":"https://orcid.org/0000-0002-9146-4403"},"institutions":[{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Adam Kortylewski","raw_affiliation_strings":["Max Planck Institute for Informatics"],"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Informatics","institution_ids":["https://openalex.org/I4210109712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020664641","display_name":"Christian Theobalt","orcid":"https://orcid.org/0000-0001-6104-6625"},"institutions":[{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christian Theobalt","raw_affiliation_strings":["Max Planck Institute for Informatics"],"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Informatics","institution_ids":["https://openalex.org/I4210109712"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076768552","display_name":"Peter Wonka","orcid":"https://orcid.org/0000-0003-0627-9746"},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]},{"id":"https://openalex.org/I4210099236","display_name":"Kootenay Association for Science & Technology","ror":"https://ror.org/011pv9p44","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210099236"]}],"countries":["CA","SA"],"is_corresponding":false,"raw_author_name":"Peter Wonka","raw_affiliation_strings":["KAUST"],"affiliations":[{"raw_affiliation_string":"KAUST","institution_ids":["https://openalex.org/I4210099236","https://openalex.org/I71920554"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100391185"],"corresponding_institution_ids":["https://openalex.org/I4210099236","https://openalex.org/I71920554"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23876565,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"22985","last_page":"22994"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9986000061035156,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9986000061035156,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9869999885559082,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9866999983787537,"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/computer-science","display_name":"Computer science","score":0.7805805206298828},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6142215728759766},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6024940013885498},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5112829208374023},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.4378277361392975},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4115140438079834},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.39672374725341797}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7805805206298828},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6142215728759766},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6024940013885498},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5112829208374023},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.4378277361392975},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4115140438079834},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39672374725341797},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.02140","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.02140","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.4099999964237213,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W4412817058","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W2495260952","https://openalex.org/W1522196789"],"abstract_inverted_index":{"We":[0,125],"introduce":[1,111],"the":[2,41,90,100,134,138],"first":[3],"training-free":[4],"approach":[5],"for":[6,115],"Video":[7],"Semantic":[8],"Segmentation":[9],"(VSS)":[10],"based":[11,117,132],"on":[12,48,57,83,118,133],"pre-trained":[13,119],"diffusion":[14,25,123,135],"models,":[15],"termed":[16],"VidSeg.":[17],"A":[18],"growing":[19],"research":[20],"direction":[21],"attempts":[22],"to":[23,27,72,85,89,143,145],"employ":[24],"models":[26],"perform":[28],"downstream":[29],"vision":[30],"tasks":[31,50,59],"by":[32],"exploiting":[33],"their":[34,81],"deep":[35],"understanding":[36],"of":[37,43,92,95],"image":[38,65,120],"semantics.":[39],"Yet,":[40],"majority":[42],"these":[44,162],"approaches":[45,68],"have":[46],"focused":[47],"image-related":[49],"like":[51],"semantic":[52,66],"segmentation,":[53],"with":[54],"less":[55],"emphasis":[56],"video":[58,101,122],"such":[60],"as":[61],"VSS.":[62],"Ideally,":[63],"diffusion-based":[64],"segmentation":[67,154],"can":[69],"be":[70,86],"applied":[71],"videos":[73,84],"in":[74,99,176],"a":[75,112,128,167],"frame-by-frame":[76],"manner.":[77],"However,":[78],"we":[79,106,165],"find":[80],"performance":[82],"subpar":[87],"due":[88],"absence":[91],"any":[93],"modeling":[94],"temporal":[96],"information":[97],"inherent":[98],"data.":[102],"To":[103,160],"this":[104,108],"end,":[105],"tackle":[107],"problem":[109],"and":[110,121],"framework":[113],"tailored":[114],"VSS":[116],"models.":[124],"propose":[126,166],"building":[127],"scene":[129,146],"context":[130,149],"model":[131,139,150],"features,":[136],"where":[137],"is":[140],"autoregressively":[141],"updated":[142],"adapt":[144],"changes.":[147],"This":[148],"predicts":[151],"per-frame":[152],"coarse":[153],"maps":[155,163],"that":[156,171],"are":[157],"temporally":[158],"consistent.":[159],"refine":[161],"further,":[164],"correspondence-based":[168],"refinement":[169],"strategy":[170],"aggregates":[172],"predictions":[173],"temporally,":[174],"resulting":[175],"more":[177],"confi-":[178]},"counts_by_year":[],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}