{"id":"https://openalex.org/W4206355076","doi":"https://doi.org/10.1109/tip.2021.3138300","title":"End-to-End Rate-Distortion Optimized Learned Hierarchical Bi-Directional Video Compression","display_name":"End-to-End Rate-Distortion Optimized Learned Hierarchical Bi-Directional Video Compression","publication_year":2021,"publication_date":"2021-12-31","ids":{"openalex":"https://openalex.org/W4206355076","doi":"https://doi.org/10.1109/tip.2021.3138300","pmid":"https://pubmed.ncbi.nlm.nih.gov/34971532"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2021.3138300","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2021.3138300","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"M. Akin Yilmaz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"M. Akin Yilmaz","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"A. Murat Tekalp","orcid":"https://orcid.org/0000-0003-1465-8121"},"institutions":[{"id":"https://openalex.org/I1351752","display_name":"Ko\u00e7 University","ror":"https://ror.org/00jzwgz36","country_code":"TR","type":"education","lineage":["https://openalex.org/I1351752"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"A. Murat Tekalp","raw_affiliation_strings":["Department of Electrical and Electronics Engineering, Ko\u00e7 University, Istanbul, Turkey"],"raw_orcid":"https://orcid.org/0000-0003-1465-8121","affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronics Engineering, Ko\u00e7 University, Istanbul, Turkey","institution_ids":["https://openalex.org/I1351752"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.6336,"has_fulltext":false,"cited_by_count":60,"citation_normalized_percentile":{"value":0.94409256,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"31","issue":null,"first_page":"974","last_page":"983"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.5189999938011169,"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":0.5189999938011169,"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":0.4117000102996826,"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/T11165","display_name":"Image and Video Quality Assessment","score":0.02459999918937683,"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/codec","display_name":"Codec","score":0.7968000173568726},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.6011000275611877},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5641999840736389},{"id":"https://openalex.org/keywords/motion-compensation","display_name":"Motion compensation","score":0.5060999989509583},{"id":"https://openalex.org/keywords/motion-vector","display_name":"Motion vector","score":0.4869000017642975},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4271000027656555},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.40799999237060547},{"id":"https://openalex.org/keywords/video-compression-picture-types","display_name":"Video compression picture types","score":0.4075999855995178},{"id":"https://openalex.org/keywords/motion-estimation","display_name":"Motion estimation","score":0.40459999442100525},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.38940000534057617}],"concepts":[{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.7968000173568726},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7842000126838684},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.6011000275611877},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5641999840736389},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5616999864578247},{"id":"https://openalex.org/C128840427","wikidata":"https://www.wikidata.org/wiki/Q1302174","display_name":"Motion compensation","level":2,"score":0.5060999989509583},{"id":"https://openalex.org/C2779020251","wikidata":"https://www.wikidata.org/wiki/Q3555171","display_name":"Motion vector","level":3,"score":0.4869000017642975},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4271000027656555},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4117000102996826},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.40799999237060547},{"id":"https://openalex.org/C106030495","wikidata":"https://www.wikidata.org/wiki/Q1797012","display_name":"Video compression picture types","level":4,"score":0.4075999855995178},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.40459999442100525},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.38940000534057617},{"id":"https://openalex.org/C50056821","wikidata":"https://www.wikidata.org/wiki/Q774502","display_name":"Rate\u2013distortion optimization","level":5,"score":0.3668000102043152},{"id":"https://openalex.org/C23431618","wikidata":"https://www.wikidata.org/wiki/Q1404672","display_name":"Multiview Video Coding","level":4,"score":0.36169999837875366},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.35510000586509705},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.3400000035762787},{"id":"https://openalex.org/C169805256","wikidata":"https://www.wikidata.org/wiki/Q1361381","display_name":"Transform coding","level":4,"score":0.3357999920845032},{"id":"https://openalex.org/C174493125","wikidata":"https://www.wikidata.org/wiki/Q1073461","display_name":"Quarter-pixel motion","level":3,"score":0.33480000495910645},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.319599986076355},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31119999289512634},{"id":"https://openalex.org/C143184774","wikidata":"https://www.wikidata.org/wiki/Q3020846","display_name":"Deblocking filter","level":2,"score":0.3043999969959259},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.2976999878883362},{"id":"https://openalex.org/C25797200","wikidata":"https://www.wikidata.org/wiki/Q828137","display_name":"Compression ratio","level":3,"score":0.2897999882698059},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.2892000079154968},{"id":"https://openalex.org/C125864890","wikidata":"https://www.wikidata.org/wiki/Q1262687","display_name":"Intra-frame","level":3,"score":0.2858000099658966},{"id":"https://openalex.org/C1769480","wikidata":"https://www.wikidata.org/wiki/Q1345239","display_name":"Entropy encoding","level":3,"score":0.27630001306533813},{"id":"https://openalex.org/C167510206","wikidata":"https://www.wikidata.org/wiki/Q2835824","display_name":"Block-matching algorithm","level":4,"score":0.27549999952316284},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.274399995803833},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.26420000195503235},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.2524000108242035}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tip.2021.3138300","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2021.3138300","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:34971532","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34971532","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null},{"id":"pmh:oai:cdm21054.contentdm.oclc.org:IR/10269","is_oa":false,"landing_page_url":"https://doi.org/10.1109/TIP.2021.3138300 ","pdf_url":null,"source":{"id":"https://openalex.org/S4306401341","display_name":"Digital Collections portal (Ko\u00e7 University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1351752","host_organization_name":"Ko\u00e7 University","host_organization_lineage":["https://openalex.org/I1351752"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"Journal article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322628","display_name":"T\u00fcrkiye Bilimler Akademisi","ror":"https://ror.org/00aqt9352"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2146395539","https://openalex.org/W2548527721","https://openalex.org/W2552465432","https://openalex.org/W2586480386","https://openalex.org/W2769654144","https://openalex.org/W2785562966","https://openalex.org/W2798405286","https://openalex.org/W2969260367","https://openalex.org/W3031546776","https://openalex.org/W3034469748","https://openalex.org/W3034802763","https://openalex.org/W3035195755","https://openalex.org/W3038130890","https://openalex.org/W3048490762","https://openalex.org/W3091266734","https://openalex.org/W3095497211","https://openalex.org/W3097448661","https://openalex.org/W3185577028","https://openalex.org/W6631190155","https://openalex.org/W6754634825"],"related_works":[],"abstract_inverted_index":{"Conventional":[0],"video":[1,66,110,151],"compression":[2,90],"(VC)":[3],"methods":[4],"are":[5,26,135],"based":[6,68],"on":[7,57,69],"motion":[8,16,50],"compensated":[9],"transform":[10],"coding,":[11],"and":[12,19,23,51,99,121,146,166,173,202,209],"the":[13,31,35,115,130,153],"steps":[14],"of":[15,34,47,63,75,92,117,156,163],"estimation,":[17],"mode":[18],"quantization":[20],"parameter":[21],"selection,":[22],"entropy":[24,52],"coding":[25,87],"optimized":[27,45,159],"individually":[28],"due":[29,191],"to":[30,95,141,149,192,211],"combinatorial":[32],"nature":[33],"end-to-end":[36,42,61,122,158],"optimization":[37,62],"problem.":[38],"Learned":[39],"VC":[40,59,83,139],"allows":[41],"rate-distortion":[43],"(R-D)":[44],"training":[46],"nonlinear":[48],"transform,":[49],"model":[53],"simultaneously.":[54],"Most":[55],"works":[56],"learned":[58,107,138,198],"consider":[60],"a":[64,106],"sequential":[65,89],"codec":[67,111,160],"R-D":[70,132,154],"loss":[71],"averaged":[72],"over":[73],"pairs":[74],"successive":[76],"frames.":[77,102],"It":[78],"is":[79],"well-known":[80],"in":[81,143,171,182,218],"conventional":[82,150],"that":[84,113,127,134],"hierarchical,":[85],"bi-directional":[86,109],"outperforms":[88,161],"because":[91],"its":[93],"ability":[94],"use":[96],"both":[97,144,164],"past":[98],"future":[100],"reference":[101,180],"This":[103],"paper":[104],"proposes":[105],"hierarchical":[108,118],"(LHBDC)":[112],"combines":[114],"benefits":[116],"motion-compensated":[119],"prediction":[120],"optimization.":[123],"Experimental":[124],"results":[125,133,214],"show":[126],"we":[128],"achieve":[129],"best":[131],"reported":[136],"for":[137],"schemes":[140],"date":[142],"PSNR":[145,172],"MS-SSIM.":[147,183],"Compared":[148],"codecs,":[152],"performance":[155,189],"our":[157,213],"those":[162],"x265":[165],"SVT-HEVC":[167],"encoders":[168],"(\"veryslow\"":[169],"preset)":[170],"MS-SSIM":[174],"as":[175,177,197],"well":[176],"HM":[178],"16.23":[179],"software":[181],"We":[184],"present":[185],"ablation":[186],"studies":[187],"showing":[188],"gains":[190],"proposed":[193],"novel":[194],"tools":[195],"such":[196],"masking,":[199],"flow-field":[200],"subsampling,":[201],"temporal":[203],"flow":[204],"vector":[205],"prediction.":[206],"The":[207],"models":[208],"instructions":[210],"reproduce":[212],"can":[215],"be":[216],"found":[217],"https://github.com/makinyilmaz/LHBDC/.":[219]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":22},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":7}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2022-01-25T00:00:00"}