{"id":"https://openalex.org/W4417101242","doi":"https://doi.org/10.1109/iccv51701.2025.01755","title":"Context Guided Transformer Entropy Modeling for Video Compression","display_name":"Context Guided Transformer Entropy Modeling for Video Compression","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417101242","doi":"https://doi.org/10.1109/iccv51701.2025.01755"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01755","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01755","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":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.01852","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Junlong Tong","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Junlong Tong","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108240542","display_name":"Wei Zhang","orcid":"https://orcid.org/0000-0002-4158-3359"},"institutions":[{"id":"https://openalex.org/I4210110242","display_name":"Digital Science (United States)","ror":"https://ror.org/020h4b682","country_code":"US","type":"company","lineage":["https://openalex.org/I4210110242","https://openalex.org/I4210112888","https://openalex.org/I4210118830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Zhang","raw_affiliation_strings":["Institute of Digital Twin, EIT,Ningbo Key Laboratory of Spatial Intelligence and Digital Derivative"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Digital Twin, EIT,Ningbo Key Laboratory of Spatial Intelligence and Digital Derivative","institution_ids":["https://openalex.org/I4210110242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085787425","display_name":"Yaohui Jin","orcid":"https://orcid.org/0000-0001-6158-6277"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaohui Jin","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102500550","display_name":"Xiaoyu Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210110242","display_name":"Digital Science (United States)","ror":"https://ror.org/020h4b682","country_code":"US","type":"company","lineage":["https://openalex.org/I4210110242","https://openalex.org/I4210112888","https://openalex.org/I4210118830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaoyu Shen","raw_affiliation_strings":["Institute of Digital Twin, EIT,Ningbo Key Laboratory of Spatial Intelligence and Digital Derivative"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Digital Twin, EIT,Ningbo Key Laboratory of Spatial Intelligence and Digital Derivative","institution_ids":["https://openalex.org/I4210110242"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.4377422,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"18885","last_page":"18894"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10741","display_name":"Video Coding and Compression Technologies","score":0.3880999982357025,"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":0.3880999982357025,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.3447999954223633,"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/T11165","display_name":"Image and Video Quality Assessment","score":0.1264999955892563,"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/context-model","display_name":"Context model","score":0.6714000105857849},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.6219000220298767},{"id":"https://openalex.org/keywords/spatial-contextual-awareness","display_name":"Spatial contextual awareness","score":0.5738999843597412},{"id":"https://openalex.org/keywords/conditional-entropy","display_name":"Conditional entropy","score":0.5198000073432922},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.476500004529953},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.38269999623298645},{"id":"https://openalex.org/keywords/entropy-encoding","display_name":"Entropy encoding","score":0.37290000915527344},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.36910000443458557}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6873000264167786},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.6714000105857849},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.6219000220298767},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.5738999843597412},{"id":"https://openalex.org/C101721835","wikidata":"https://www.wikidata.org/wiki/Q813908","display_name":"Conditional entropy","level":3,"score":0.5198000073432922},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4788999855518341},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.476500004529953},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.38269999623298645},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37689998745918274},{"id":"https://openalex.org/C1769480","wikidata":"https://www.wikidata.org/wiki/Q1345239","display_name":"Entropy encoding","level":3,"score":0.37290000915527344},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.36910000443458557},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3411000072956085},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.33410000801086426},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3172999918460846},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31290000677108765},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2924000024795532},{"id":"https://openalex.org/C167981619","wikidata":"https://www.wikidata.org/wiki/Q1685498","display_name":"Cross entropy","level":3,"score":0.2906000018119812},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.27149999141693115},{"id":"https://openalex.org/C196956702","wikidata":"https://www.wikidata.org/wiki/Q6795829","display_name":"Maximum-entropy Markov model","level":5,"score":0.2678999900817871},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.25540000200271606}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01755","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01755","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:2508.01852","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.01852","pdf_url":"https://arxiv.org/pdf/2508.01852","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2508.01852","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.01852","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2508.01852","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.01852","pdf_url":"https://arxiv.org/pdf/2508.01852","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"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":"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":{"Conditional":[0],"entropy":[1,60,132,179,197],"models":[2,30],"effectively":[3],"leverage":[4],"spatio-temporal":[5],"contexts":[6],"to":[7,88,111,126,134,145,163,192],"reduce":[8],"video":[9],"redundancy.":[10],"However,":[11],"incorporating":[12],"temporal":[13,74,81,91],"context":[14,29,46,75,82,109,118],"often":[15],"introduces":[16],"additional":[17],"model":[18,113,177],"complexity":[19],"and":[20,76,130,185],"increases":[21],"computational":[22,98],"cost.":[23],"In":[24],"parallel,":[25],"many":[26],"existing":[27],"spatial":[28,37,78,108,117,154],"lack":[31],"explicit":[32],"modeling":[33,180],"the":[34,42,55,68,114,143,147,152,159,193],"ordering":[35],"of":[36,44,67,116],"dependencies,":[38],"which":[39,62],"may":[40],"limit":[41],"availability":[43],"relevant":[45],"during":[47],"decoding.":[48],"To":[49],"address":[50],"these":[51],"issues,":[52],"we":[53],"propose":[54],"Context":[56],"Guided":[57],"Transformer":[58],"(CGT)":[59],"model,":[61],"estimates":[63],"probability":[64],"mass":[65],"functions":[66],"current":[69],"frame":[70],"conditioned":[71],"on":[72,168],"resampled":[73],"dependency-weighted":[77,107],"context.":[79,170],"A":[80],"resampler":[83],"learns":[84],"predefined":[85],"latent":[86],"queries":[87],"extract":[89],"critical":[90],"information":[92],"using":[93],"transformer":[94],"encoders,":[95],"reducing":[96],"downstream":[97],"overhead.":[99],"Meanwhile,":[100],"a":[101],"teacher-student":[102],"network":[103],"is":[104,161],"designed":[105],"as":[106],"assigner":[110],"explicitly":[112],"dependency":[115],"order.":[119],"The":[120],"teacher":[121],"generates":[122],"an":[123,131,187],"attention":[124],"map":[125,133],"represent":[127],"token":[128],"importance":[129],"reflect":[135],"prediction":[136],"certainty":[137],"from":[138],"randomly":[139],"masked":[140],"inputs,":[141],"guiding":[142],"student":[144,160],"select":[146],"weighted":[148],"top-k":[149],"tokens":[150,166],"with":[151],"highest":[153],"dependency.":[155],"During":[156],"inference,":[157],"only":[158],"used":[162],"predict":[164],"undecoded":[165],"based":[167],"high-dependency":[169],"Experimental":[171],"results":[172],"demonstrate":[173],"that":[174],"our":[175],"CGT":[176],"reduces":[178],"time":[181],"by":[182],"approximately":[183],"65%":[184],"achieves":[186],"11%":[188],"BD-Rate":[189],"reduction":[190],"compared":[191],"previous":[194],"state-of-the-art":[195],"conditional":[196],"model.":[198]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}