{"id":"https://openalex.org/W4404649993","doi":"https://doi.org/10.1109/iccv51701.2025.01974","title":"Principles of Visual Tokens for Efficient Video Understanding","display_name":"Principles of Visual Tokens for Efficient Video Understanding","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4404649993","doi":"https://doi.org/10.1109/iccv51701.2025.01974"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01974","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01974","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://nottingham-repository.worktribe.com/file/52562381/1/Principles%20of%20Visual%20Tokens%20for%20Efficient%20Video%20Understanding","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041898142","display_name":"Xinyue Hao","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xinyue Hao","raw_affiliation_strings":["University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100785866","display_name":"Gen Li","orcid":"https://orcid.org/0000-0001-6636-1106"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Gen Li","raw_affiliation_strings":["University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041351493","display_name":"Shreyank N Gowda","orcid":"https://orcid.org/0000-0002-4975-0705"},"institutions":[{"id":"https://openalex.org/I142263535","display_name":"University of Nottingham","ror":"https://ror.org/01ee9ar58","country_code":"GB","type":"education","lineage":["https://openalex.org/I142263535"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Shreyank N Gowda","raw_affiliation_strings":["University of Nottingham"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Nottingham","institution_ids":["https://openalex.org/I142263535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020686179","display_name":"Robert B. Fisher","orcid":"https://orcid.org/0000-0001-6860-9371"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Robert B. Fisher","raw_affiliation_strings":["University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079026336","display_name":"Jonathan Huang","orcid":"https://orcid.org/0000-0002-3428-9952"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jonathan Huang","raw_affiliation_strings":["Scaled Foundations"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Scaled Foundations","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035108037","display_name":"Anurag Arnab","orcid":"https://orcid.org/0000-0002-5216-4838"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Anurag Arnab","raw_affiliation_strings":["Google DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210090411"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076169111","display_name":"Laura Sevilla-Lara","orcid":"https://orcid.org/0000-0001-8276-0094"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Laura Sevilla-Lara","raw_affiliation_strings":["University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"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":0.00120835,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"21254","last_page":"21264"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9901000261306763,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9901000261306763,"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":0.9842000007629395,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9771000146865845,"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":0.5786693096160889},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36277279257774353},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3513525724411011},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.339202344417572},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.33732354640960693}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5786693096160889},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36277279257774353},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3513525724411011},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.339202344417572},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33732354640960693}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/iccv51701.2025.01974","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01974","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:nottingham-repository.worktribe.com:52562381","is_oa":true,"landing_page_url":"https://nottingham-repository.worktribe.com/file/52562381/1/Principles%20of%20Visual%20Tokens%20for%20Efficient%20Video%20Understanding","pdf_url":null,"source":{"id":"https://openalex.org/S4306402483","display_name":"Repository@Nottingham (University of Nottingham)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I142263535","host_organization_name":"University of Nottingham","host_organization_lineage":["https://openalex.org/I142263535"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Presentation / Conference Contribution"},{"id":"pmh:oai:arXiv.org:2411.13626","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.13626","pdf_url":"https://arxiv.org/pdf/2411.13626","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2411.13626","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2411.13626","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:nottingham-repository.worktribe.com:52562381","is_oa":true,"landing_page_url":"https://nottingham-repository.worktribe.com/file/52562381/1/Principles%20of%20Visual%20Tokens%20for%20Efficient%20Video%20Understanding","pdf_url":null,"source":{"id":"https://openalex.org/S4306402483","display_name":"Repository@Nottingham (University of Nottingham)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I142263535","host_organization_name":"University of Nottingham","host_organization_lineage":["https://openalex.org/I142263535"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Presentation / Conference Contribution"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407"],"abstract_inverted_index":{"Video":[0],"understanding":[1],"has":[2,32],"made":[3],"huge":[4],"strides":[5],"in":[6,48,157],"recent":[7],"years,":[8],"relying":[9],"largely":[10],"on":[11,126],"the":[12,50,53,67,89,99,121,158,179],"power":[13],"of":[14,52,69,88,91,101,120,144,161],"transformers.":[15],"As":[16],"this":[17,74,82],"architecture":[18],"is":[19,25],"notoriously":[20],"expensive":[21],"and":[22,42,55,84,114,128,149,155,174],"video":[23,135],"data":[24],"highly":[26],"redundant,":[27],"research":[28],"into":[29],"improving":[30],"efficiency":[31],"become":[33],"particularly":[34],"relevant.":[35],"Some":[36],"creative":[37],"solutions":[38],"include":[39],"token":[40],"selection":[41],"merging.":[43],"While":[44],"most":[45,62,108,119],"methods":[46,63],"succeed":[47],"reducing":[49],"cost":[51],"model":[54],"maintaining":[56],"accuracy,":[57],"an":[58],"interesting":[59],"pattern":[60],"arises:":[61],"do":[64],"not":[65],"outperform":[66],"baseline":[68],"randomly":[70],"discarding":[71],"tokens.":[72,93],"In":[73],"paper":[75],"we":[76,96],"take":[77],"a":[78,104,116,133,141],"closer":[79],"look":[80],"at":[81],"phenomenon":[83],"observe":[85,97],"5":[86],"principles":[87],"nature":[90],"visual":[92],"For":[94],"example,":[95],"that":[98,138,169],"value":[100],"tokens":[102,109,145],"follows":[103],"clear":[105],"Pareto-distribution":[106],"where":[107],"have":[110],"remarkably":[111],"low":[112],"value,":[113],"just":[115],"few":[117],"carry":[118],"perceptual":[122],"information.":[123],"We":[124],"build":[125],"these":[127],"further":[129],"insights":[130],"to":[131],"propose":[132],"lightweight":[134],"model,":[136],"LITE,":[137],"can":[139],"select":[140],"small":[142],"number":[143],"effectively,":[146],"outperforming":[147],"state-of-the-art":[148],"existing":[150],"baselines":[151],"across":[152,172],"datasets":[153,173],"(Kinetics-400":[154],"Something-Something-V2)":[156],"challenging":[159],"trade-off":[160],"computation":[162],"(GFLOPs)":[163],"vs":[164],"accuracy.":[165],"Experiments":[166],"also":[167],"show":[168],"LITE":[170],"generalizes":[171],"even":[175],"other":[176],"tasks":[177],"without":[178],"need":[180],"for":[181],"retraining.":[182]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}