{"id":"https://openalex.org/W3091226623","doi":"https://doi.org/10.1109/icip40778.2020.9190704","title":"Scalable Learned Image Compression With A Recurrent Neural Networks-Based Hyperprior","display_name":"Scalable Learned Image Compression With A Recurrent Neural Networks-Based Hyperprior","publication_year":2020,"publication_date":"2020-09-30","ids":{"openalex":"https://openalex.org/W3091226623","doi":"https://doi.org/10.1109/icip40778.2020.9190704","mag":"3091226623"},"language":"en","primary_location":{"id":"doi:10.1109/icip40778.2020.9190704","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip40778.2020.9190704","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"},"type":"article","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/A5082336210","display_name":"Rige Su","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Rige Su","raw_affiliation_strings":["Graduate School of Fundamental Science and Engineering, Waseda University, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Fundamental Science and Engineering, Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071945287","display_name":"Zhengxue Cheng","orcid":"https://orcid.org/0000-0001-8258-6364"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Zhengxue Cheng","raw_affiliation_strings":["Graduate School of Fundamental Science and Engineering, Waseda University, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Fundamental Science and Engineering, Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089205282","display_name":"Heming Sun","orcid":"https://orcid.org/0000-0001-5583-4895"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Heming Sun","raw_affiliation_strings":["Waseda Research Institute for Science and Engineering, Waseda University, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda Research Institute for Science and Engineering, Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002294739","display_name":"Jiro Katto","orcid":"https://orcid.org/0000-0002-1671-2614"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jiro Katto","raw_affiliation_strings":["Graduate School of Fundamental Science and Engineering, Waseda University, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Fundamental Science and Engineering, Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5082336210"],"corresponding_institution_ids":["https://openalex.org/I150744194"],"apc_list":null,"apc_paid":null,"fwci":0.8828,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.76831368,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3369","last_page":"3373"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9997000098228455,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9994000196456909,"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/computer-science","display_name":"Computer science","score":0.7451416254043579},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6778531670570374},{"id":"https://openalex.org/keywords/entropy-encoding","display_name":"Entropy encoding","score":0.6684496402740479},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6094560623168945},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.517795205116272},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5144641399383545},{"id":"https://openalex.org/keywords/image-compression","display_name":"Image compression","score":0.48016586899757385},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4704771637916565},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.46129003167152405},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4507770240306854},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.44625598192214966},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.42464497685432434},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.36949634552001953},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.17574229836463928},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.17251479625701904},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14953291416168213}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7451416254043579},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6778531670570374},{"id":"https://openalex.org/C1769480","wikidata":"https://www.wikidata.org/wiki/Q1345239","display_name":"Entropy encoding","level":3,"score":0.6684496402740479},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6094560623168945},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.517795205116272},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5144641399383545},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.48016586899757385},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4704771637916565},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.46129003167152405},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4507770240306854},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.44625598192214966},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.42464497685432434},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.36949634552001953},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.17574229836463928},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.17251479625701904},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14953291416168213},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip40778.2020.9190704","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip40778.2020.9190704","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1485009520","https://openalex.org/W2030265202","https://openalex.org/W2040903332","https://openalex.org/W2140196014","https://openalex.org/W2146395539","https://openalex.org/W2552465432","https://openalex.org/W2593493485","https://openalex.org/W2597747080","https://openalex.org/W2785562966","https://openalex.org/W2891212213","https://openalex.org/W2962676454","https://openalex.org/W2963149687","https://openalex.org/W2964098744","https://openalex.org/W2982853315","https://openalex.org/W4294567867","https://openalex.org/W4297659253","https://openalex.org/W6694251005","https://openalex.org/W6734035190","https://openalex.org/W6754669699"],"related_works":["https://openalex.org/W2129829718","https://openalex.org/W2521595930","https://openalex.org/W3165542721","https://openalex.org/W4243608781","https://openalex.org/W4378191574","https://openalex.org/W3156493487","https://openalex.org/W2161981399","https://openalex.org/W1520703599","https://openalex.org/W2595043295","https://openalex.org/W2751842002"],"abstract_inverted_index":{"Recently":[0],"learned":[1,63],"image":[2,64],"compression":[3],"has":[4],"achieved":[5],"many":[6],"great":[7],"progresses,":[8],"such":[9],"as":[10],"representative":[11],"hyperprior":[12,106,130],"and":[13,30,49,74,141],"its":[14],"variants":[15],"based":[16],"on":[17,132],"convolutional":[18],"neural":[19,55],"networks":[20,56],"(CNNs).":[21],"However,":[22],"CNNs":[23],"are":[24],"not":[25],"fit":[26],"for":[27,114],"scalable":[28,62,80,140],"coding":[29,143],"multiple":[31,87,147],"models":[32,52,113],"need":[33],"to":[34,38,59,86,107,145],"be":[35,125],"trained":[36],"separately":[37],"achieve":[39,60,146],"variable":[40],"rates.":[41],"In":[42],"this":[43],"paper,":[44],"we":[45,67,82,102],"incorporate":[46],"differentiable":[47],"quantization":[48,73],"accurate":[50],"entropy":[51,75,112],"into":[53],"recurrent":[54],"(RNNs)":[57],"architectures":[58],"a":[61,139],"compression.":[65],"First,":[66],"present":[68],"an":[69,104],"RNN":[70],"architecture":[71],"with":[72,127],"coding.":[76],"To":[77],"realize":[78],"the":[79,84,91,109],"coding,":[81],"allocate":[83],"bits":[85],"layers,":[88],"by":[89],"adjusting":[90],"layer-wise":[92],"lambda":[93],"values":[94],"in":[95],"Lagrangian":[96],"multiplier-based":[97],"rate-distortion":[98],"optimization":[99],"function.":[100],"Second,":[101],"add":[103],"RNN-based":[105],"improve":[108],"accuracy":[110],"of":[111],"multiple-layer":[115],"residual":[116],"representations.":[117],"Experimental":[118],"results":[119],"demonstrate":[120],"that":[121],"our":[122,136],"performance":[123],"can":[124],"comparable":[126],"recent":[128],"CNN-based":[129],"methods":[131],"Kodak":[133],"dataset.":[134],"Besides,":[135],"method":[137],"is":[138,154],"flexible":[142],"approach,":[144],"rates":[148],"using":[149],"one":[150],"single":[151],"model,":[152],"which":[153],"very":[155],"appealing.":[156]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":3}],"updated_date":"2026-06-03T09:05:47.796612","created_date":"2025-10-10T00:00:00"}