{"id":"https://openalex.org/W7131214355","doi":"https://doi.org/10.1109/vcip67698.2025.11396906","title":"Enhanced Inter-frame Dependency Modeling with State Space Models for Neural Video Compression","display_name":"Enhanced Inter-frame Dependency Modeling with State Space Models for Neural Video Compression","publication_year":2025,"publication_date":"2025-12-01","ids":{"openalex":"https://openalex.org/W7131214355","doi":"https://doi.org/10.1109/vcip67698.2025.11396906"},"language":null,"primary_location":{"id":"doi:10.1109/vcip67698.2025.11396906","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vcip67698.2025.11396906","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Visual Communications and Image Processing (VCIP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100409387","display_name":"Linlin Liu","orcid":"https://orcid.org/0000-0002-1058-4551"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Liu","raw_affiliation_strings":["University of Science and Technology of China,MOE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition,Hefei,China,230027"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,MOE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition,Hefei,China,230027","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101223301","display_name":"Chuanbo Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuanbo Tang","raw_affiliation_strings":["University of Science and Technology of China,MOE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition,Hefei,China,230027"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,MOE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition,Hefei,China,230027","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020172017","display_name":"Yifan Bian","orcid":"https://orcid.org/0000-0002-0659-0318"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Bian","raw_affiliation_strings":["University of Science and Technology of China,MOE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition,Hefei,China,230027"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,MOE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition,Hefei,China,230027","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126663163","display_name":"Li Li","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Li","raw_affiliation_strings":["University of Science and Technology of China,MOE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition,Hefei,China,230027"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,MOE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition,Hefei,China,230027","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088681823","display_name":"Di Liu","orcid":"https://orcid.org/0000-0003-0539-9279"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Liu","raw_affiliation_strings":["University of Science and Technology of China,MOE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition,Hefei,China,230027"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,MOE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition,Hefei,China,230027","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.66110517,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.3635999858379364,"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":0.3635999858379364,"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/T10741","display_name":"Video Coding and Compression Technologies","score":0.16869999468326569,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.04690000042319298,"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/dependency","display_name":"Dependency (UML)","score":0.6184999942779541},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.5946999788284302},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.5921000242233276},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5662000179290771},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5325999855995178},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5083000063896179},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.5033000111579895},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4864000082015991},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.41990000009536743},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.39309999346733093}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8101000189781189},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.6184999942779541},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.5946999788284302},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.5921000242233276},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5662000179290771},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5325999855995178},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5306000113487244},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5083000063896179},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.5033000111579895},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4864000082015991},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.41990000009536743},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4050999879837036},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.39309999346733093},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.3873000144958496},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3869999945163727},{"id":"https://openalex.org/C172849965","wikidata":"https://www.wikidata.org/wiki/Q3148875","display_name":"Reference frame","level":3,"score":0.3801000118255615},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3538999855518341},{"id":"https://openalex.org/C106030495","wikidata":"https://www.wikidata.org/wiki/Q1797012","display_name":"Video compression picture types","level":4,"score":0.3522000014781952},{"id":"https://openalex.org/C39394851","wikidata":"https://www.wikidata.org/wiki/Q921594","display_name":"Inter frame","level":4,"score":0.351500004529953},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.3345000147819519},{"id":"https://openalex.org/C75778745","wikidata":"https://www.wikidata.org/wiki/Q342626","display_name":"Lag","level":2,"score":0.3240000009536743},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32359999418258667},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3167000114917755},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3082999885082245},{"id":"https://openalex.org/C204641915","wikidata":"https://www.wikidata.org/wiki/Q7315509","display_name":"Residual frame","level":4,"score":0.30559998750686646},{"id":"https://openalex.org/C125864890","wikidata":"https://www.wikidata.org/wiki/Q1262687","display_name":"Intra-frame","level":3,"score":0.30219998955726624},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.2913999855518341},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C52918065","wikidata":"https://www.wikidata.org/wiki/Q230945","display_name":"State-space representation","level":2,"score":0.2750000059604645},{"id":"https://openalex.org/C25797200","wikidata":"https://www.wikidata.org/wiki/Q828137","display_name":"Compression ratio","level":3,"score":0.2669000029563904},{"id":"https://openalex.org/C57654395","wikidata":"https://www.wikidata.org/wiki/Q1097775","display_name":"Compression artifact","level":5,"score":0.2635999917984009},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/vcip67698.2025.11396906","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vcip67698.2025.11396906","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Visual Communications and Image Processing (VCIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2112796928","https://openalex.org/W2511458122","https://openalex.org/W2769654144","https://openalex.org/W2969260367","https://openalex.org/W3031546776","https://openalex.org/W3202918664","https://openalex.org/W4285483958","https://openalex.org/W4312774595","https://openalex.org/W4386065808","https://openalex.org/W4393153962","https://openalex.org/W4396680731","https://openalex.org/W4402772372","https://openalex.org/W4406861145","https://openalex.org/W4413144445","https://openalex.org/W4413144600","https://openalex.org/W4413146579","https://openalex.org/W4413158162","https://openalex.org/W4413158308","https://openalex.org/W4414110709"],"related_works":[],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"neural":[3],"video":[4],"compression":[5,71],"(NVC)":[6],"has":[7],"achieved":[8],"remarkable":[9],"rate-distortion":[10],"performance,":[11],"surpassing":[12],"traditional":[13],"codecs":[14],"by":[15,80],"leveraging":[16],"learnable":[17],"architectures":[18],"and":[19,56,70,115],"endto-end":[20],"optimization.":[21],"However,":[22],"under":[23],"large":[24],"intra-period":[25,155],"settings,":[26],"most":[27],"NVC":[28],"methods":[29],"still":[30],"lag":[31],"behind":[32],"conventional":[33],"codecs.":[34],"To":[35],"address":[36],"this":[37],"issue,":[38],"we":[39,74,99],"first":[40],"analyze":[41],"the":[42,45,53,57,60,76,87,93,146],"importance":[43],"of":[44,59,95,141],"frame":[46,88],"generator":[47],"in":[48,67,145],"inter-frame":[49],"dependency":[50],"modeling,":[51],"where":[52],"propagated":[54,96],"features":[55,108],"quality":[58,94],"reconstructed":[61],"frames":[62,110,153],"play":[63],"a":[64,101],"critical":[65],"role":[66],"prediction":[68],"accuracy":[69],"efficiency.":[72,129],"Then,":[73],"enhance":[75],"spatiotemporal":[77],"context":[78],"modeling":[79,125],"incorporating":[81],"state":[82],"space":[83],"models":[84],"(SSMs)":[85],"into":[86],"generator,":[89],"aiming":[90],"to":[91,111,157],"improve":[92],"features.":[97],"Specifically,":[98],"introduce":[100],"2D-Selective-Scan":[102],"(SS2D)":[103],"mechanism":[104],"that":[105,133],"aggregates":[106],"global":[107],"across":[109],"construct":[112],"more":[113],"informative":[114],"expressive":[116],"reference":[117],"representations.":[118],"This":[119],"design":[120],"enables":[121],"effective":[122],"long-range":[123],"temporal":[124],"while":[126],"maintaining":[127],"computational":[128],"Experimental":[130],"results":[131],"show":[132],"our":[134],"method":[135],"achieves":[136],"an":[137],"average":[138],"bitrate":[139],"saving":[140],"13.6%":[142],"over":[143],"VTM":[144],"RGB":[147],"color":[148],"space,":[149],"evaluated":[150],"on":[151],"300":[152],"with":[154],"set":[156],"\u22121.":[158]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-02-25T00:00:00"}