{"id":"https://openalex.org/W4415317815","doi":"https://doi.org/10.1109/iccv51701.2025.02071","title":"ResidualViT for Efficient Temporally Dense Video Encoding","display_name":"ResidualViT for Efficient Temporally Dense Video Encoding","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4415317815","doi":"https://doi.org/10.1109/iccv51701.2025.02071"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02071","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02071","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/2509.13255","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008305562","display_name":"Mattia Soldan","orcid":"https://orcid.org/0000-0003-0413-8165"},"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"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Mattia Soldan","raw_affiliation_strings":["KAUST, King Abdullah University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAUST, King Abdullah University of Science and Technology","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022774523","display_name":"Fabian Caba Heilbron","orcid":"https://orcid.org/0000-0002-3129-1985"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fabian Caba Heilbron","raw_affiliation_strings":["Adobe Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024763828","display_name":"Bernard Ghanem","orcid":"https://orcid.org/0000-0002-5534-587X"},"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"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Bernard Ghanem","raw_affiliation_strings":["KAUST, King Abdullah University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAUST, King Abdullah University of Science and Technology","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025398783","display_name":"Josef \u0160ivic","orcid":"https://orcid.org/0000-0002-2554-5301"},"institutions":[{"id":"https://openalex.org/I4210152232","display_name":"Institute of Informatics of the Slovak Academy of Sciences","ror":"https://ror.org/04jgqpc26","country_code":"SK","type":"facility","lineage":["https://openalex.org/I207624831","https://openalex.org/I4210152232"]},{"id":"https://openalex.org/I44504214","display_name":"Czech Technical University in Prague","ror":"https://ror.org/03kqpb082","country_code":"CZ","type":"education","lineage":["https://openalex.org/I44504214"]}],"countries":["CZ","SK"],"is_corresponding":false,"raw_author_name":"Josef Sivic","raw_affiliation_strings":["CIIRC CTU, Czech Institute of Informatics, Robotics and Cybernetics at the Czech Technical University in Prague"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CIIRC CTU, Czech Institute of Informatics, Robotics and Cybernetics at the Czech Technical University in Prague","institution_ids":["https://openalex.org/I4210152232","https://openalex.org/I44504214"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053907649","display_name":"Bryan Russell","orcid":"https://orcid.org/0000-0001-8656-543X"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bryan Russell","raw_affiliation_strings":["Adobe Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"22305","last_page":"22315"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10741","display_name":"Video Coding and Compression Technologies","score":0.9990000128746033,"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"}},"topics":[{"id":"https://openalex.org/T10741","display_name":"Video Coding and Compression Technologies","score":0.9990000128746033,"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"}},{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9988999962806702,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9987999796867371,"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/redundancy","display_name":"Redundancy (engineering)","score":0.5963000059127808},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5562999844551086},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5289000272750854},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.4796999990940094},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.43810001015663147},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.3959999978542328},{"id":"https://openalex.org/keywords/temporal-resolution","display_name":"Temporal resolution","score":0.387800008058548},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.3675999939441681}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7976999878883362},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.5963000059127808},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5562999844551086},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5443999767303467},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5289000272750854},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.4796999990940094},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.43810001015663147},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3959999978542328},{"id":"https://openalex.org/C119666444","wikidata":"https://www.wikidata.org/wiki/Q5977280","display_name":"Temporal resolution","level":2,"score":0.387800008058548},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3675999939441681},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33550000190734863},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.3174000084400177},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30660000443458557},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.3061000108718872},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30410000681877136},{"id":"https://openalex.org/C3261483","wikidata":"https://www.wikidata.org/wiki/Q119565","display_name":"Frame rate","level":2,"score":0.2913999855518341},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2831999957561493},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.2759000062942505},{"id":"https://openalex.org/C77277458","wikidata":"https://www.wikidata.org/wiki/Q1969246","display_name":"Temporal database","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2533999979496002},{"id":"https://openalex.org/C57654395","wikidata":"https://www.wikidata.org/wiki/Q1097775","display_name":"Compression artifact","level":5,"score":0.2531000077724457},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2524999976158142}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02071","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02071","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:2509.13255","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.13255","pdf_url":"https://arxiv.org/pdf/2509.13255","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2509.13255","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.13255","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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2509.13255","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.13255","pdf_url":"https://arxiv.org/pdf/2509.13255","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":null,"license_id":null,"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":[],"abstract_inverted_index":{"Several":[0],"video":[1,9],"understanding":[2],"tasks,":[3],"such":[4],"as":[5],"natural":[6],"language":[7],"temporal":[8,11,27,41,76,96],"grounding,":[10],"activity":[12],"localization,":[13],"and":[14,101,150,156,169],"audio":[15],"description":[16],"generation,":[17],"require":[18],"\"temporally":[19],"dense\"":[20],"reasoning":[21],"over":[22],"frames":[23,100],"sampled":[24],"at":[25],"high":[26],"resolution.":[28],"However,":[29],"computing":[30,56],"frame-level":[31,85,135],"features":[32,57,136],"for":[33,58],"these":[34],"tasks":[35,149],"is":[36],"computationally":[37],"expensive":[38],"given":[39],"the":[40,53,74,134,138,182,185],"resolution":[42],"requirements.":[43],"In":[44],"this":[45],"paper,":[46],"we":[47,63,126,143],"make":[48],"three":[49],"contributions":[50],"to":[51,80,132,167,175],"reduce":[52],"cost":[54,165],"of":[55,120,137,184],"temporally":[59,83,114],"dense":[60,84],"tasks.":[61],"First,":[62],"introduce":[64],"a":[65,103,121,128],"vision":[66],"transformer":[67],"(ViT)":[68],"architecture,":[69],"dubbed":[70],"ResidualViT,":[71],"that":[72,94,107],"leverages":[73],"large":[75],"redundancy":[77],"in":[78,153,163,171],"videos":[79],"efficiently":[81],"compute":[82],"features.":[86],"Our":[87],"architecture":[88],"incorporates":[89],"(i)":[90],"learnable":[91],"residual":[92],"connections":[93],"ensure":[95],"consistency":[97],"across":[98,147],"consecutive":[99],"(ii)":[102],"token":[104],"reduction":[105],"module":[106],"enhances":[108],"processing":[109],"speed":[110,173],"by":[111],"selectively":[112],"discarding":[113],"redundant":[115],"information":[116],"while":[117,179],"reusing":[118],"weights":[119],"pretrained":[122],"foundation":[123,140,187],"model.":[124,141,188],"Second,":[125],"propose":[127],"lightweight":[129],"distillation":[130],"strategy":[131],"approximate":[133],"original":[139,186],"Finally,":[142],"evaluate":[144],"our":[145],"approach":[146],"four":[148],"five":[151],"datasets,":[152],"both":[154],"zero-shot":[155],"fully":[157],"supervised":[158],"settings,":[159],"demonstrating":[160],"significant":[161],"reductions":[162],"computational":[164],"(up":[166,174],"60%)":[168],"improvements":[170],"inference":[172],"2.5x":[176],"faster),":[177],"all":[178],"closely":[180],"approximating":[181],"accuracy":[183]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-18T00:00:00"}