{"id":"https://openalex.org/W4404343454","doi":"https://doi.org/10.1109/iccv51701.2025.02156","title":"ReferevErything: Towards Segmenting Everything we can Speak of in Videos","display_name":"ReferevErything: Towards Segmenting Everything we can Speak of in Videos","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4404343454","doi":"https://doi.org/10.1109/iccv51701.2025.02156"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02156","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02156","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":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2410.23287","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114634193","display_name":"Anurag Bagchi","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anurag Bagchi","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076213540","display_name":"Zhipeng Bao","orcid":"https://orcid.org/0009-0008-9898-3741"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhipeng Bao","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102952938","display_name":"Yu-Xiong Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu-Xiong Wang","raw_affiliation_strings":["University of Illinois Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040760890","display_name":"Pavel Tokmakov","orcid":"https://orcid.org/0000-0003-2043-6242"},"institutions":[{"id":"https://openalex.org/I4391768151","display_name":"Toyota Research Institute","ror":"https://ror.org/04fpkc108","country_code":null,"type":"facility","lineage":["https://openalex.org/I4210125472","https://openalex.org/I4391768151"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Pavel Tokmakov","raw_affiliation_strings":["Toyota Research Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toyota Research Institute","institution_ids":["https://openalex.org/I4391768151"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075246991","display_name":"Martial Hebert","orcid":"https://orcid.org/0000-0003-4566-5930"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Martial Hebertly","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00097597,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"23221","last_page":"23231"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.5297999978065491,"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/T11439","display_name":"Video Analysis and Summarization","score":0.5297999978065491,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.4977000057697296,"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/market-segmentation","display_name":"Market segmentation","score":0.5840200185775757},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.42097219824790955},{"id":"https://openalex.org/keywords/advertising","display_name":"Advertising","score":0.40965938568115234},{"id":"https://openalex.org/keywords/aesthetics","display_name":"Aesthetics","score":0.39210245013237},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3814682066440582},{"id":"https://openalex.org/keywords/internet-privacy","display_name":"Internet privacy","score":0.34471312165260315},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.2992221713066101},{"id":"https://openalex.org/keywords/marketing","display_name":"Marketing","score":0.2327335774898529}],"concepts":[{"id":"https://openalex.org/C125308379","wikidata":"https://www.wikidata.org/wiki/Q363057","display_name":"Market segmentation","level":2,"score":0.5840200185775757},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.42097219824790955},{"id":"https://openalex.org/C112698675","wikidata":"https://www.wikidata.org/wiki/Q37038","display_name":"Advertising","level":1,"score":0.40965938568115234},{"id":"https://openalex.org/C107038049","wikidata":"https://www.wikidata.org/wiki/Q35986","display_name":"Aesthetics","level":1,"score":0.39210245013237},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3814682066440582},{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.34471312165260315},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.2992221713066101},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.2327335774898529}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02156","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02156","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:2410.23287","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.23287","pdf_url":"https://arxiv.org/pdf/2410.23287","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2410.23287","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2410.23287","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2410.23287","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.23287","pdf_url":"https://arxiv.org/pdf/2410.23287","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":["https://openalex.org/W4391375266","https://openalex.org/W2908364646","https://openalex.org/W2275271759","https://openalex.org/W2014532210","https://openalex.org/W2053295099","https://openalex.org/W4239263688","https://openalex.org/W1992760298","https://openalex.org/W2049517942","https://openalex.org/W2767629806","https://openalex.org/W2319899002"],"abstract_inverted_index":{"We":[0,143],"present":[1],"REM,":[2],"a":[3,7,84],"framework":[4],"for":[5,109],"segmenting":[6],"wide":[8],"range":[9],"of":[10,53,87,140],"concepts":[11],"in":[12,105,148],"video":[13,30,149],"that":[14,146],"can":[15,72,91],"be":[16],"described":[17],"through":[18],"natural":[19],"language.":[20],"Our":[21,45],"method":[22],"leverages":[23],"the":[24,51,54,120,138],"universal":[25],"visual-language":[26],"mapping":[27],"learned":[28],"by":[29,36,58,130],"diffusion":[31],"models":[32],"on":[33,39,83,117,122],"Internet-scale":[34],"data":[35],"fine-tuning":[37],"them":[38,129],"small-scale":[40],"Referring":[41,110],"Object":[42],"Segmentation":[43,113],"datasets.":[44],"key":[46],"insight":[47],"is":[48],"to":[49,65,94,132],"preserve":[50],"entirety":[52],"generative":[55,141],"model's":[56],"architecture":[57],"shifting":[59],"its":[60],"objective":[61],"from":[62],"predicting":[63,66],"noise":[64],"mask":[67],"latents.":[68],"The":[69],"resulting":[70],"model":[71],"accurately":[73],"segment":[74],"rare":[75],"and":[76],"unseen":[77],"objects,":[78],"despite":[79],"only":[80],"being":[81],"trained":[82],"limited":[85],"set":[86],"categories.":[88],"Additionally,":[89],"it":[90],"effortlessly":[92],"generalize":[93],"non-object":[95],"dynamic":[96],"concepts,":[97],"such":[98],"as":[99,103],"smoke":[100],"or":[101],"raindrops,":[102],"demonstrated":[104],"our":[106],"new":[107],"benchmark":[108],"Video":[111],"Process":[112],"(Ref-VPS).":[114],"REM":[115],"performs":[116],"par":[118],"with":[119],"state-of-the-art":[121],"in-domain":[123],"datasets,":[124],"like":[125],"Ref-DAVIS,":[126],"while":[127],"outperforming":[128],"up":[131],"12":[133],"IoU":[134],"points":[135],"out-of-domain,":[136],"leveraging":[137],"power":[139],"pre-training.":[142],"also":[144],"show":[145],"advancements":[147],"generation":[150],"directly":[151],"improve":[152],"segmentation.":[153]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}