{"id":"https://openalex.org/W4404569834","doi":"https://doi.org/10.1109/iccv51701.2025.02043","title":"Everything is a Video: Unifying Modalities Through Next-Frame Prediction","display_name":"Everything is a Video: Unifying Modalities Through Next-Frame Prediction","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4404569834","doi":"https://doi.org/10.1109/iccv51701.2025.02043"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02043","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02043","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2411.10503","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046869230","display_name":"G. Thomas Hudson","orcid":"https://orcid.org/0000-0003-3562-3593"},"institutions":[{"id":"https://openalex.org/I190082696","display_name":"Durham University","ror":"https://ror.org/01v29qb04","country_code":"GB","type":"education","lineage":["https://openalex.org/I190082696"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"G. Thomas Hudson","raw_affiliation_strings":["Durham University,Department of Computer Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Durham University,Department of Computer Sciences","institution_ids":["https://openalex.org/I190082696"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056453144","display_name":"Dean L. Slack","orcid":null},"institutions":[{"id":"https://openalex.org/I190082696","display_name":"Durham University","ror":"https://ror.org/01v29qb04","country_code":"GB","type":"education","lineage":["https://openalex.org/I190082696"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dean Slack","raw_affiliation_strings":["Durham University,Department of Computer Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Durham University,Department of Computer Sciences","institution_ids":["https://openalex.org/I190082696"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000549094","display_name":"Thomas Winterbottom","orcid":null},"institutions":[{"id":"https://openalex.org/I190082696","display_name":"Durham University","ror":"https://ror.org/01v29qb04","country_code":"GB","type":"education","lineage":["https://openalex.org/I190082696"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Thomas Winterbottom","raw_affiliation_strings":["Durham University,Department of Computer Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Durham University,Department of Computer Sciences","institution_ids":["https://openalex.org/I190082696"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109726032","display_name":"Jamie Sterling","orcid":null},"institutions":[{"id":"https://openalex.org/I190082696","display_name":"Durham University","ror":"https://ror.org/01v29qb04","country_code":"GB","type":"education","lineage":["https://openalex.org/I190082696"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jamie Sterling","raw_affiliation_strings":["Durham University,Department of Computer Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Durham University,Department of Computer Sciences","institution_ids":["https://openalex.org/I190082696"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073544000","display_name":"Chenghao Xiao","orcid":"https://orcid.org/0000-0001-7623-8232"},"institutions":[{"id":"https://openalex.org/I190082696","display_name":"Durham University","ror":"https://ror.org/01v29qb04","country_code":"GB","type":"education","lineage":["https://openalex.org/I190082696"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Chenghao Xiao","raw_affiliation_strings":["Durham University,Department of Computer Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Durham University,Department of Computer Sciences","institution_ids":["https://openalex.org/I190082696"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079074868","display_name":"Junjie Shentu","orcid":null},"institutions":[{"id":"https://openalex.org/I190082696","display_name":"Durham University","ror":"https://ror.org/01v29qb04","country_code":"GB","type":"education","lineage":["https://openalex.org/I190082696"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Junjie Shentu","raw_affiliation_strings":["Durham University,Department of Computer Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Durham University,Department of Computer Sciences","institution_ids":["https://openalex.org/I190082696"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017619842","display_name":"Noura Al Moubayed","orcid":"https://orcid.org/0000-0001-8942-355X"},"institutions":[{"id":"https://openalex.org/I190082696","display_name":"Durham University","ror":"https://ror.org/01v29qb04","country_code":"GB","type":"education","lineage":["https://openalex.org/I190082696"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Noura Al Moubayed","raw_affiliation_strings":["Durham University,Department of Computer Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Durham University,Department of Computer Sciences","institution_ids":["https://openalex.org/I190082696"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00075033,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"22004","last_page":"22013"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9871000051498413,"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":0.9871000051498413,"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/T11309","display_name":"Music and Audio Processing","score":0.9108999967575073,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/modalities","display_name":"Modalities","score":0.7159595489501953},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5698603391647339},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5462198257446289},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3437209129333496},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.17591992020606995},{"id":"https://openalex.org/keywords/sociology","display_name":"Sociology","score":0.11106786131858826},{"id":"https://openalex.org/keywords/social-science","display_name":"Social science","score":0.05392056703567505}],"concepts":[{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.7159595489501953},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5698603391647339},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5462198257446289},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3437209129333496},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.17591992020606995},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.11106786131858826},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.05392056703567505}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/iccv51701.2025.02043","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02043","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:2411.10503","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.10503","pdf_url":"https://arxiv.org/pdf/2411.10503","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"pmh:oai:durham-repository.worktribe.com:4666319","is_oa":true,"landing_page_url":"https://durham-repository.worktribe.com/4666319/1/Accepted%20Conference%20Paper","pdf_url":"https://durham-repository.worktribe.com/preview/4666484/4666319AAM.pdf","source":{"id":"https://openalex.org/S4306400188","display_name":"Durham Research Online (Durham University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I190082696","host_organization_name":"Durham University","host_organization_lineage":["https://openalex.org/I190082696"],"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":"acceptedVersion"},{"id":"pmh:oai:durham-repository.worktribe.com:4666319","is_oa":true,"landing_page_url":"https://durham-repository.worktribe.com/output/4666319","pdf_url":null,"source":{"id":"https://openalex.org/S4306400188","display_name":"Durham Research Online (Durham University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I190082696","host_organization_name":"Durham University","host_organization_lineage":["https://openalex.org/I190082696"],"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":"acceptedVersion"},{"id":"doi:10.48550/arxiv.2411.10503","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2411.10503","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2411.10503","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.10503","pdf_url":"https://arxiv.org/pdf/2411.10503","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4404569834.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2185469136","https://openalex.org/W2011264131","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4306353150","https://openalex.org/W2026860389"],"abstract_inverted_index":{"Multimodal":[0],"learning,":[1],"which":[2,41],"involves":[3],"integrating":[4],"information":[5],"from":[6],"various":[7,165],"modalities":[8,98,119,149],"such":[9],"as":[10,109],"text,":[11],"images,":[12],"audio,":[13],"and":[14,28,37,45,107,120,140],"video,":[15,114],"is":[16,128],"pivotal":[17],"for":[18,170],"numerous":[19],"complex":[20],"tasks":[21,51,84],"like":[22],"visual":[23],"question":[24],"answering,":[25],"cross-modal":[26],"retrieval,":[27],"caption":[29],"generation.":[30],"Traditional":[31],"approaches":[32],"rely":[33],"on":[34,130],"modality-specific":[35,100],"encoders":[36],"late":[38],"fusion":[39],"techniques,":[40],"can":[42,158],"hinder":[43],"scalability":[44],"flexibility":[46],"when":[47],"adapting":[48],"to":[49,75,80,95,146],"new":[50],"or":[52],"modalities.":[53],"To":[54],"address":[55],"these":[56],"limitations,":[57],"we":[58],"introduce":[59],"a":[60,86,92,113,131],"novel":[61],"framework":[62],"that":[63,155],"extends":[64],"the":[65,143,168],"concept":[66],"of":[67,118,133],"task":[68,156],"reformulation":[69,157],"beyond":[70],"natural":[71],"language":[72],"processing":[73],"(NLP)":[74],"multimodal":[76,83,161,173],"learning.":[77],"We":[78,153],"propose":[79],"reformulate":[81],"diverse":[82],"into":[85],"unified":[87],"next-frame":[88],"prediction":[89],"problem,":[90],"allowing":[91],"single":[93],"model":[94,162],"handle":[96],"different":[97],"without":[99],"components.":[101],"This":[102],"method":[103],"treats":[104],"all":[105],"inputs":[106],"outputs":[108],"sequential":[110],"frames":[111],"in":[112],"enabling":[115],"seamless":[116],"integration":[117],"effective":[121],"knowledge":[122],"transfer":[123],"across":[124,148,164],"tasks.":[125],"Our":[126],"approach":[127],"evaluated":[129],"range":[132],"tasks,":[134,166],"including":[135],"text-to-text,":[136],"image-to-text,":[137],"video-to-video,":[138],"video-to-text,":[139],"audio-to-text,":[141],"demonstrating":[142],"model's":[144],"ability":[145],"generalize":[147],"with":[150],"minimal":[151],"adaptation.":[152],"show":[154],"significantly":[159],"simplify":[160],"design":[163],"laying":[167],"groundwork":[169],"more":[171],"generalized":[172],"foundation":[174],"models.":[175]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
