{"id":"https://openalex.org/W4388191714","doi":"https://doi.org/10.1145/3581783.3611960","title":"Neural Video Compression with Spatio-Temporal Cross-Covariance Transformers","display_name":"Neural Video Compression with Spatio-Temporal Cross-Covariance Transformers","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4388191714","doi":"https://doi.org/10.1145/3581783.3611960"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3611960","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611960","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/20.500.11850/645526","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064120901","display_name":"Zhenghao Chen","orcid":"https://orcid.org/0000-0003-0155-4462"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Zhenghao Chen","raw_affiliation_strings":["The University of Sydney, Sydney, NSW, Australia"],"affiliations":[{"raw_affiliation_string":"The University of Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087400952","display_name":"Lucas Relic","orcid":"https://orcid.org/0000-0003-2109-9823"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Lucas Relic","raw_affiliation_strings":["ETH Z\u00fcrich, Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018016935","display_name":"Roberto Gerson de Albuquerque Azevedo","orcid":"https://orcid.org/0000-0001-5473-506X"},"institutions":[{"id":"https://openalex.org/I4210137357","display_name":"Walt Disney (Switzerland)","ror":"https://ror.org/04h1x1p54","country_code":"CH","type":"company","lineage":["https://openalex.org/I4210137357","https://openalex.org/I4210142140"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Roberto Azevedo","raw_affiliation_strings":["DisneyResearch|Studios, Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"DisneyResearch|Studios, Zurich, Switzerland","institution_ids":["https://openalex.org/I4210137357"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100354651","display_name":"Yang Zhang","orcid":"https://orcid.org/0000-0002-2381-6067"},"institutions":[{"id":"https://openalex.org/I4210137357","display_name":"Walt Disney (Switzerland)","ror":"https://ror.org/04h1x1p54","country_code":"CH","type":"company","lineage":["https://openalex.org/I4210137357","https://openalex.org/I4210142140"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Yang Zhang","raw_affiliation_strings":["DisneyResearch|Studios, Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"DisneyResearch|Studios, Zurich, Switzerland","institution_ids":["https://openalex.org/I4210137357"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033076979","display_name":"Markus Gro\u00df","orcid":"https://orcid.org/0009-0003-9324-779X"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Markus Gross","raw_affiliation_strings":["ETH Z\u00fcrich, Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082181536","display_name":"Dong Xu","orcid":"https://orcid.org/0000-0003-2775-9730"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Dong Xu","raw_affiliation_strings":["The University of Hong Kong, Hong Kong SAR, Hong Kong"],"affiliations":[{"raw_affiliation_string":"The University of Hong Kong, Hong Kong SAR, Hong Kong","institution_ids":["https://openalex.org/I177725633","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100643784","display_name":"Luping Zhou","orcid":"https://orcid.org/0000-0001-8762-2424"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Luping Zhou","raw_affiliation_strings":["The University of Sydney, Sydney, NSW, Australia"],"affiliations":[{"raw_affiliation_string":"The University of Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052388616","display_name":"Christopher Schroers","orcid":"https://orcid.org/0000-0003-1473-1878"},"institutions":[{"id":"https://openalex.org/I4210137357","display_name":"Walt Disney (Switzerland)","ror":"https://ror.org/04h1x1p54","country_code":"CH","type":"company","lineage":["https://openalex.org/I4210137357","https://openalex.org/I4210142140"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Christopher Schroers","raw_affiliation_strings":["DisneyResearch|Studios, Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"DisneyResearch|Studios, Zurich, Switzerland","institution_ids":["https://openalex.org/I4210137357"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5064120901"],"corresponding_institution_ids":["https://openalex.org/I129604602"],"apc_list":null,"apc_paid":null,"fwci":1.6851,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.8668663,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"8543","last_page":"8551"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.9997000098228455,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9997000098228455,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9995999932289124,"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/T11105","display_name":"Advanced Image Processing Techniques","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"}}],"keywords":[{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.6723161339759827},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6206709742546082},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4484283924102783},{"id":"https://openalex.org/keywords/covariance","display_name":"Covariance","score":0.4339388310909271},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41574621200561523},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.36693572998046875},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.35982316732406616},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14335405826568604},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12554848194122314},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.12288889288902283},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.08319622278213501}],"concepts":[{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.6723161339759827},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6206709742546082},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4484283924102783},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.4339388310909271},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41574621200561523},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36693572998046875},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35982316732406616},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14335405826568604},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12554848194122314},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.12288889288902283},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.08319622278213501},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3581783.3611960","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611960","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:www.research-collection.ethz.ch:20.500.11850/645526","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11850/645526","pdf_url":null,"source":{"id":"https://openalex.org/S4306402302","display_name":"Repository for Publications and Research Data (ETH Zurich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I35440088","host_organization_name":"ETH Zurich","host_organization_lineage":["https://openalex.org/I35440088"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"MM '23: Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"info:eu-repo/semantics/acceptedVersion"},{"id":"doi:10.3929/ethz-b-000645526","is_oa":true,"landing_page_url":"https://doi.org/10.3929/ethz-b-000645526","pdf_url":null,"source":{"id":"https://openalex.org/S7407051236","display_name":"ETH Z\u00fcrich Research Collection","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"article-journal"}],"best_oa_location":{"id":"pmh:oai:www.research-collection.ethz.ch:20.500.11850/645526","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11850/645526","pdf_url":null,"source":{"id":"https://openalex.org/S4306402302","display_name":"Repository for Publications and Research Data (ETH Zurich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I35440088","host_organization_name":"ETH Zurich","host_organization_lineage":["https://openalex.org/I35440088"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"MM '23: Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"info:eu-repo/semantics/acceptedVersion"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W2105581333","https://openalex.org/W2140196014","https://openalex.org/W2146395539","https://openalex.org/W2511458122","https://openalex.org/W2548527721","https://openalex.org/W2769654144","https://openalex.org/W2963149687","https://openalex.org/W2965631471","https://openalex.org/W2969260367","https://openalex.org/W2987947587","https://openalex.org/W2992051623","https://openalex.org/W3018065762","https://openalex.org/W3020741905","https://openalex.org/W3034469748","https://openalex.org/W3034802763","https://openalex.org/W3035195755","https://openalex.org/W3098284407","https://openalex.org/W3102015846","https://openalex.org/W3108139283","https://openalex.org/W3110286842","https://openalex.org/W3138516171","https://openalex.org/W3173272744","https://openalex.org/W3202918664","https://openalex.org/W3203234039","https://openalex.org/W3207918547","https://openalex.org/W3212865599","https://openalex.org/W4210274484","https://openalex.org/W4225672218","https://openalex.org/W4225872410","https://openalex.org/W4281668669","https://openalex.org/W4283028628","https://openalex.org/W4285483958","https://openalex.org/W4295312788","https://openalex.org/W4312774595","https://openalex.org/W4312785369","https://openalex.org/W4313058111","https://openalex.org/W4387967955","https://openalex.org/W6802036239","https://openalex.org/W6839976848"],"related_works":["https://openalex.org/W2788344745","https://openalex.org/W2062336688","https://openalex.org/W2910677864","https://openalex.org/W2046078371","https://openalex.org/W2383820648","https://openalex.org/W4245445763","https://openalex.org/W3162209258","https://openalex.org/W2054128830","https://openalex.org/W4319736142","https://openalex.org/W2148213881"],"abstract_inverted_index":{"Although":[0],"existing":[1],"neural":[2],"video":[3,182],"compression~(NVC)":[4],"methods":[5],"have":[6],"achieved":[7],"significant":[8],"success,":[9],"most":[10],"of":[11,123,153],"them":[12],"focus":[13],"on":[14,133,179],"improving":[15],"either":[16],"temporal":[17,53],"or":[18,30],"spatial":[19,55],"information":[20,56],"separately.":[21],"They":[22],"generally":[23],"use":[24],"simple":[25],"operations":[26,38,85],"such":[27,37,155],"as":[28,156],"concatenation":[29],"subtraction":[31],"to":[32,47],"utilize":[33],"this":[34],"information,":[35],"while":[36,127],"only":[39],"partially":[40],"exploit":[41],"spatio-temporal":[42,79,110,125],"redundancies.":[43],"This":[44],"work":[45],"aims":[46],"effectively":[48],"and":[49,54,86,161],"jointly":[50],"leverage":[51],"robust":[52],"by":[57,82],"proposing":[58],"a":[59,77,87,137],"new":[60],"3D-based":[61],"transformer":[62],"module:":[63],"Spatio-Temporal":[64],"Cross-Covariance":[65],"Transformer":[66],"(ST-XCT).":[67],"The":[68],"ST-XCT":[69],"module":[70],"combines":[71],"two":[72],"individual":[73],"extracted":[74],"features":[75,111],"into":[76,112,148],"joint":[78],"feature,":[80],"followed":[81],"3D":[83],"convolutional":[84],"novel":[88,138],"spatio-temporal-aware":[89],"cross-covariance":[90,97],"attention":[91,98],"mechanism.":[92],"Unlike":[93],"conventional":[94],"transformers,":[95],"the":[96,103,109,124,129],"mechanism":[99],"is":[100],"applied":[101],"across":[102],"feature":[104,157],"channels":[105],"without":[106],"breaking":[107],"down":[108],"local":[113],"tokens.":[114],"Such":[115],"design":[116],"allows":[117],"for":[118],"modeling":[119],"global":[120],"cross-channel":[121],"correlations":[122],"context":[126],"lowering":[128],"computational":[130],"requirement.":[131],"Based":[132],"ST-XCT,":[134],"we":[135],"introduce":[136],"transformer-based":[139],"end-to-end":[140],"optimized":[141],"NVC":[142,173],"framework.":[143],"ST-XCT-based":[144,172],"modules":[145],"are":[146],"integrated":[147],"various":[149,180],"key":[150],"coding":[151],"components":[152],"NVC,":[154],"extraction,":[158],"frame":[159],"reconstruction,":[160],"entropy":[162],"modeling,":[163],"demonstrating":[164],"its":[165],"generalizability.":[166],"Extensive":[167],"experiments":[168],"show":[169],"that":[170],"our":[171],"proposal":[174],"achieves":[175],"state-of-the-art":[176],"compression":[177],"performances":[178],"standard":[181],"benchmark":[183],"datasets.":[184]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}