{"id":"https://openalex.org/W4415025593","doi":"https://doi.org/10.1109/pcs65673.2025.11417641","title":"SCALED: Surrogate-gradient for Codec-Aware Learning of Downsampling in ABR Streaming","display_name":"SCALED: Surrogate-gradient for Codec-Aware Learning of Downsampling in ABR Streaming","publication_year":2025,"publication_date":"2025-12-08","ids":{"openalex":"https://openalex.org/W4415025593","doi":"https://doi.org/10.1109/pcs65673.2025.11417641"},"language":null,"primary_location":{"id":"doi:10.1109/pcs65673.2025.11417641","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pcs65673.2025.11417641","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Picture Coding Symposium (PCS)","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/2602.00198","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119934600","display_name":"Esteban Pesnel","orcid":null},"institutions":[{"id":"https://openalex.org/I4210088288","display_name":"Compact Imaging (United States)","ror":"https://ror.org/0072bx170","country_code":"US","type":"company","lineage":["https://openalex.org/I4210088288"]},{"id":"https://openalex.org/I56067802","display_name":"Universit\u00e9 de Rennes","ror":"https://ror.org/015m7wh34","country_code":"FR","type":"education","lineage":["https://openalex.org/I56067802"]}],"countries":["FR","US"],"is_corresponding":true,"raw_author_name":"Pesnel, Esteban","raw_affiliation_strings":["COMPACT","COMPACT - Compression de donn\u00e9es visuelles massives (Centre Inria de l'Universit\u00e9 de Rennes\r\nCampus de Beaulieu\r\n263 Av. G\u00e9n\u00e9ral Leclerc\r\n35042 Rennes - France)","MediaKind [Rennes] (B\u00e2timent Stanford, 1 B Av. de Belle Fontaine, 35510 Cesson-S\u00e9vign\u00e9 - France)"],"affiliations":[{"raw_affiliation_string":"COMPACT","institution_ids":["https://openalex.org/I4210088288"]},{"raw_affiliation_string":"COMPACT - Compression de donn\u00e9es visuelles massives (Centre Inria de l'Universit\u00e9 de Rennes\r\nCampus de Beaulieu\r\n263 Av. G\u00e9n\u00e9ral Leclerc\r\n35042 Rennes - France)","institution_ids":["https://openalex.org/I56067802"]},{"raw_affiliation_string":"MediaKind [Rennes] (B\u00e2timent Stanford, 1 B Av. de Belle Fontaine, 35510 Cesson-S\u00e9vign\u00e9 - France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025786923","display_name":"Julien Le Tanou","orcid":"https://orcid.org/0000-0001-7140-4406"},"institutions":[{"id":"https://openalex.org/I4210088288","display_name":"Compact Imaging (United States)","ror":"https://ror.org/0072bx170","country_code":"US","type":"company","lineage":["https://openalex.org/I4210088288"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tanou, Julien Le","raw_affiliation_strings":["COMPACT","MediaKind [Rennes] (B\u00e2timent Stanford, 1 B Av. de Belle Fontaine, 35510 Cesson-S\u00e9vign\u00e9 - France)"],"affiliations":[{"raw_affiliation_string":"COMPACT","institution_ids":["https://openalex.org/I4210088288"]},{"raw_affiliation_string":"MediaKind [Rennes] (B\u00e2timent Stanford, 1 B Av. de Belle Fontaine, 35510 Cesson-S\u00e9vign\u00e9 - France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086856214","display_name":"Micha\u00ebl Ropert","orcid":"https://orcid.org/0000-0002-7824-2654"},"institutions":[{"id":"https://openalex.org/I4210088288","display_name":"Compact Imaging (United States)","ror":"https://ror.org/0072bx170","country_code":"US","type":"company","lineage":["https://openalex.org/I4210088288"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ropert, Michael","raw_affiliation_strings":["COMPACT","MediaKind [Rennes] (B\u00e2timent Stanford, 1 B Av. de Belle Fontaine, 35510 Cesson-S\u00e9vign\u00e9 - France)"],"affiliations":[{"raw_affiliation_string":"COMPACT","institution_ids":["https://openalex.org/I4210088288"]},{"raw_affiliation_string":"MediaKind [Rennes] (B\u00e2timent Stanford, 1 B Av. de Belle Fontaine, 35510 Cesson-S\u00e9vign\u00e9 - France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011824101","display_name":"Thomas Maugey","orcid":"https://orcid.org/0000-0002-7149-0823"},"institutions":[{"id":"https://openalex.org/I4210088288","display_name":"Compact Imaging (United States)","ror":"https://ror.org/0072bx170","country_code":"US","type":"company","lineage":["https://openalex.org/I4210088288"]},{"id":"https://openalex.org/I56067802","display_name":"Universit\u00e9 de Rennes","ror":"https://ror.org/015m7wh34","country_code":"FR","type":"education","lineage":["https://openalex.org/I56067802"]}],"countries":["FR","US"],"is_corresponding":false,"raw_author_name":"Maugey, Thomas","raw_affiliation_strings":["COMPACT","COMPACT - Compression de donn\u00e9es visuelles massives (Centre Inria de l'Universit\u00e9 de Rennes\r\nCampus de Beaulieu\r\n263 Av. G\u00e9n\u00e9ral Leclerc\r\n35042 Rennes - France)"],"affiliations":[{"raw_affiliation_string":"COMPACT","institution_ids":["https://openalex.org/I4210088288"]},{"raw_affiliation_string":"COMPACT - Compression de donn\u00e9es visuelles massives (Centre Inria de l'Universit\u00e9 de Rennes\r\nCampus de Beaulieu\r\n263 Av. G\u00e9n\u00e9ral Leclerc\r\n35042 Rennes - France)","institution_ids":["https://openalex.org/I56067802"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004726647","display_name":"Aline Roumy","orcid":"https://orcid.org/0000-0002-6352-8166"},"institutions":[{"id":"https://openalex.org/I4210088288","display_name":"Compact Imaging (United States)","ror":"https://ror.org/0072bx170","country_code":"US","type":"company","lineage":["https://openalex.org/I4210088288"]},{"id":"https://openalex.org/I56067802","display_name":"Universit\u00e9 de Rennes","ror":"https://ror.org/015m7wh34","country_code":"FR","type":"education","lineage":["https://openalex.org/I56067802"]}],"countries":["FR","US"],"is_corresponding":false,"raw_author_name":"Roumy, Aline","raw_affiliation_strings":["COMPACT","COMPACT - Compression de donn\u00e9es visuelles massives (Centre Inria de l'Universit\u00e9 de Rennes\r\nCampus de Beaulieu\r\n263 Av. G\u00e9n\u00e9ral Leclerc\r\n35042 Rennes - France)"],"affiliations":[{"raw_affiliation_string":"COMPACT","institution_ids":["https://openalex.org/I4210088288"]},{"raw_affiliation_string":"COMPACT - Compression de donn\u00e9es visuelles massives (Centre Inria de l'Universit\u00e9 de Rennes\r\nCampus de Beaulieu\r\n263 Av. G\u00e9n\u00e9ral Leclerc\r\n35042 Rennes - France)","institution_ids":["https://openalex.org/I56067802"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5119934600"],"corresponding_institution_ids":["https://openalex.org/I4210088288","https://openalex.org/I56067802"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15359277,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9866999983787537,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9623000025749207,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/upsampling","display_name":"Upsampling","score":0.7544000148773193},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.6866999864578247},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4027000069618225},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.391400009393692},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.38429999351501465},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.36469998955726624},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.3402999937534332},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.33570000529289246},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.32760000228881836}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7937999963760376},{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.7544000148773193},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.6866999864578247},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48350000381469727},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4027000069618225},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.391400009393692},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.38429999351501465},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.36469998955726624},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3538999855518341},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3508000075817108},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.3402999937534332},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.33570000529289246},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.32760000228881836},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.3197000026702881},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3158000111579895},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31029999256134033},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.30570000410079956},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.3037000000476837},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3009999990463257},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.29809999465942383},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.2937000095844269},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.29319998621940613},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C69216139","wikidata":"https://www.wikidata.org/wiki/Q931783","display_name":"JPEG 2000","level":5,"score":0.2639999985694885},{"id":"https://openalex.org/C101722063","wikidata":"https://www.wikidata.org/wiki/Q218825","display_name":"Random access","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.25679999589920044}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/pcs65673.2025.11417641","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pcs65673.2025.11417641","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Picture Coding Symposium (PCS)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2602.00198","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.00198","pdf_url":"https://arxiv.org/pdf/2602.00198","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":"pmh:doi:10.48550/arxiv.2602.00198","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"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":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2602.00198","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.00198","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:2602.00198","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.00198","pdf_url":"https://arxiv.org/pdf/2602.00198","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":{"The":[0,81],"rapid":[1],"growth":[2],"in":[3,72,89,158,234],"video":[4,16,113],"consumption":[5],"has":[6,86],"introduced":[7],"significant":[8],"challenges":[9],"to":[10,75,107,146,238],"modern":[11],"streaming":[12],"architectures.":[13],"Over-the-Top":[14],"(OTT)":[15],"delivery":[17],"now":[18],"predominantly":[19],"relies":[20],"on":[21,33,61,131],"Adaptive":[22],"Bitrate":[23],"(ABR)":[24],"streaming,":[25],"which":[26,115],"dynamically":[27],"adjusts":[28],"bitrate":[29],"and":[30,40,53,59,225],"resolution":[31],"based":[32,129],"client-side":[34],"constraints":[35],"such":[36,101,142],"as":[37,143],"display":[38],"capabilities":[39],"network":[41],"bandwidth.":[42],"This":[43],"pipeline":[44,94],"typically":[45],"involves":[46],"downsampling":[47,251],"the":[48,62,92,108,148,169,184,220,244],"original":[49],"high-resolution":[50],"content,":[51],"encoding":[52],"transmitting":[54],"it,":[55],"followed":[56],"by":[57,208],"decoding":[58],"upsampling":[60],"client":[63],"side.":[64],"Traditionally,":[65],"these":[66],"processing":[67],"stages":[68],"have":[69,121,155],"been":[70],"optimized":[71],"isolation,":[73],"leading":[74],"suboptimal":[76],"end-to-end":[77,103,202],"rate-distortion":[78,246],"(R-D)":[79],"performance.":[80,227],"advent":[82],"of":[83,111,171,186],"deep":[84,132],"learning":[85],"spurred":[87],"interest":[88],"jointly":[90],"optimizing":[91],"ABR":[93],"using":[95,125,187],"learned":[96],"resampling":[97],"methods.":[98],"However,":[99],"training":[100,203,223,240],"systems":[102],"remains":[104],"challenging":[105],"due":[106],"non-differentiable":[109,173,206],"nature":[110],"standard":[112,188],"codecs,":[114],"obstructs":[116],"gradient-based":[117],"optimization.":[118],"Recent":[119],"works":[120],"addressed":[122],"this":[123,193],"issue":[124],"differentiable":[126,140,152],"proxy":[127,153],"models,":[128],"either":[130],"neural":[133],"networks":[134],"or":[135],"hybrid":[136],"coding":[137],"schemes":[138],"with":[139,204],"components":[141],"soft":[144],"quantization,":[145],"approximate":[147],"codec":[149],"behavior.":[150],"While":[151],"codecs":[154,189,207],"enabled":[156],"progress":[157],"compression-aware":[159],"learning,":[160],"they":[161],"remain":[162],"approximations":[163],"that":[164,200],"may":[165],"not":[166],"fully":[167],"capture":[168],"behavior":[170],"standard,":[172],"codecs.":[174],"To":[175],"our":[176],"knowledge,":[177],"there":[178],"is":[179],"no":[180],"prior":[181],"evidence":[182],"demonstrating":[183],"inefficiencies":[185],"during":[190],"training.":[191],"In":[192],"work,":[194],"we":[195],"introduce":[196],"a":[197,231],"novel":[198],"framework":[199],"enables":[201],"real,":[205],"leveraging":[209],"data-driven":[210],"surrogate":[211],"gradients":[212],"derived":[213],"from":[214],"actual":[215],"compression":[216],"errors.":[217],"It":[218],"facilitates":[219],"alignment":[221],"between":[222],"objectives":[224],"deployment":[226],"Experimental":[228],"results":[229],"show":[230],"5.19\\%":[232],"improvement":[233],"BD-BR":[235],"(PSNR)":[236],"compared":[237],"codec-agnostic":[239],"approaches,":[241],"consistently":[242],"across":[243],"entire":[245],"convex":[247],"hull":[248],"spanning":[249],"multiple":[250],"ratios.":[252]},"counts_by_year":[],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}