{"id":"https://openalex.org/W7162798909","doi":"https://doi.org/10.48550/arxiv.2605.29063","title":"Accelerating HEVC Intra Partitioning via a CNN-Hierarchical Attention Transformer Hybrid","display_name":"Accelerating HEVC Intra Partitioning via a CNN-Hierarchical Attention Transformer Hybrid","publication_year":2026,"publication_date":"2026-05-27","ids":{"openalex":"https://openalex.org/W7162798909","doi":"https://doi.org/10.48550/arxiv.2605.29063"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.29063","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.29063","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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.29063","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137343811","display_name":"Krishna Kumar Sharma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sharma, Krishna Kumar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5031583853","display_name":"Somdyuti Paul","orcid":"https://orcid.org/0000-0002-2762-7263"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Paul, Somdyuti","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10741","display_name":"Video Coding and Compression Technologies","score":0.9304999709129333,"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":0.9304999709129333,"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":0.012799999676644802,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.008700000122189522,"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/encoder","display_name":"Encoder","score":0.628600001335144},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4115999937057495},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.3995000123977661},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.3582000136375427},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.34470000863075256},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.3343999981880188}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7770000100135803},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.628600001335144},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4115999937057495},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.3995000123977661},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3961000144481659},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3652999997138977},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.3582000136375427},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.34470000863075256},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.3343999981880188},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33340001106262207},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.33009999990463257},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.32910001277923584},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3237999975681305},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.3100000023841858},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2964000105857849},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.25929999351501465},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.29063","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.29063","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":"doi:10.48550/arxiv.2605.29063","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.29063","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":false,"raw_source_name":null,"raw_type":"Preprint"},"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":{"The":[0],"recursive":[1],"quad-tree":[2],"partitioning":[3],"in":[4,163],"High":[5],"Efficiency":[6],"Video":[7],"Coding":[8],"(HEVC)":[9],"incurs":[10],"considerable":[11],"computational":[12],"overhead,":[13],"with":[14,122],"exhaustive":[15],"rate-distortion":[16],"optimization":[17],"for":[18,223],"CTU":[19],"partition":[20,30,113],"prediction":[21,31],"consuming":[22],"the":[23,159,176,198,210],"dominant":[24],"share":[25],"of":[26,161,209],"encoding":[27,40],"time.":[28],"Although":[29],"through":[32],"deep":[33],"learning":[34],"has":[35],"emerged":[36],"as":[37,195],"a":[38,87,105,117,123,130],"viable":[39],"accelerator,":[41],"an":[42],"architectural":[43],"dichotomy":[44],"remains":[45],"largely":[46],"unaddressed:":[47],"CNNs":[48],"are":[49,76],"computationally":[50],"efficient":[51,136],"but":[52,82],"spatially":[53],"myopic":[54],"due":[55],"to":[56,63,109,134,152,197],"their":[57],"localized":[58],"effective":[59],"receptive":[60],"fields,":[61],"failing":[62],"capture":[64],"long":[65],"range":[66],"semantic":[67],"relationships":[68],"and":[69,184,192,213],"repetitive":[70],"textures;":[71],"conversely,":[72],"transformer":[73],"based":[74],"architectures":[75],"better":[77],"at":[78,140],"capturing":[79],"global":[80,137],"context":[81],"incur":[83],"prohibitive":[84],"CPU":[85,204],"latency,":[86],"critical":[88],"liability":[89],"that":[90],"impedes":[91],"deployment":[92],"which":[93],"is":[94],"predominantly":[95],"CPU-bound.":[96],"This":[97],"paper":[98],"introduces":[99],"Hybrid":[100],"Fast":[101],"Vision":[102],"Transformer":[103,126],"(HFViT),":[104],"hybrid":[106],"architecture":[107],"designed":[108],"accelerate":[110],"HEVC":[111,165],"intra-mode":[112],"prediction.":[114],"HFViT":[115,162,174],"fuses":[116],"reparameterized":[118],"depthwise-separable":[119],"convolutional":[120],"backbone":[121],"Hierarchical":[124],"Attention":[125],"(HAT)":[127],"mechanism,":[128],"leveraging":[129],"carrier":[131],"token":[132],"scheme":[133],"enable":[135],"information":[138],"propagation":[139],"sub-quadratic":[141],"complexity.":[142],"Post-training":[143],"structural":[144],"fusion":[145],"collapses":[146],"batch":[147],"normalization":[148],"into":[149],"preceding":[150],"layers":[151],"further":[153],"reduce":[154],"latency.":[155],"Comprehensive":[156],"evaluation":[157],"reveals":[158],"efficacy":[160],"accelerating":[164],"intra-encoding":[166],"across":[167],"resolutions.":[168],"On":[169],"standard":[170],"JCT-VC":[171],"test":[172],"sequences,":[173],"reduces":[175],"average":[177],"VMAF":[178],"BD-rate":[179],"penalty":[180],"by":[181,218],"2.4,":[182],"2.6,":[183],"7.9":[185],"percentage":[186],"points":[187],"on":[188,216],"Classes":[189],"A,":[190],"B":[191],"E,":[193],"respectively,":[194],"compared":[196],"competing":[199],"ETH-CNN":[200],"baseline":[201,212],"while":[202],"maintaining":[203],"inference":[205],"latency":[206],"within":[207],"8%":[208],"CNN":[211],"surpassing":[214],"it":[215],"GPU":[217],"40%,":[219],"establishing":[220],"practical":[221],"viability":[222],"real-time":[224],"encoder":[225],"integration.":[226]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-30T00:00:00"}