{"id":"https://openalex.org/W3160673571","doi":"https://doi.org/10.1109/icassp39728.2021.9414465","title":"Image Coding For Machines: an End-To-End Learned Approach","display_name":"Image Coding For Machines: an End-To-End Learned Approach","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3160673571","doi":"https://doi.org/10.1109/icassp39728.2021.9414465","mag":"3160673571"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414465","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414465","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2108.09993","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100768610","display_name":"Nam Le","orcid":"https://orcid.org/0000-0002-9722-3790"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Nam Le","raw_affiliation_strings":["Tampere University,Tampere,Finland","Tampere University, Tampere, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tampere University,Tampere,Finland","institution_ids":["https://openalex.org/I166825849"]},{"raw_affiliation_string":"Tampere University, Tampere, Finland","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100671939","display_name":"Honglei Zhang","orcid":"https://orcid.org/0000-0002-8229-852X"},"institutions":[{"id":"https://openalex.org/I2738502077","display_name":"Nokia (Finland)","ror":"https://ror.org/04pkc8m17","country_code":"FI","type":"company","lineage":["https://openalex.org/I2738502077"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Honglei Zhang","raw_affiliation_strings":["Nokia Technologies"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nokia Technologies","institution_ids":["https://openalex.org/I2738502077"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049106121","display_name":"Francesco Cricri","orcid":"https://orcid.org/0000-0002-1521-420X"},"institutions":[{"id":"https://openalex.org/I2738502077","display_name":"Nokia (Finland)","ror":"https://ror.org/04pkc8m17","country_code":"FI","type":"company","lineage":["https://openalex.org/I2738502077"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Francesco Cricri","raw_affiliation_strings":["Nokia Technologies"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nokia Technologies","institution_ids":["https://openalex.org/I2738502077"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038279606","display_name":"Ramin G. Youvalari","orcid":"https://orcid.org/0000-0001-7260-0599"},"institutions":[{"id":"https://openalex.org/I2738502077","display_name":"Nokia (Finland)","ror":"https://ror.org/04pkc8m17","country_code":"FI","type":"company","lineage":["https://openalex.org/I2738502077"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Ramin Ghaznavi-Youvalari","raw_affiliation_strings":["Nokia Technologies"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nokia Technologies","institution_ids":["https://openalex.org/I2738502077"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088180438","display_name":"Esa Rahtu","orcid":"https://orcid.org/0000-0001-8767-0864"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Esa Rahtu","raw_affiliation_strings":["Tampere University,Tampere,Finland","Tampere University, Tampere, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tampere University,Tampere,Finland","institution_ids":["https://openalex.org/I166825849"]},{"raw_affiliation_string":"Tampere University, Tampere, Finland","institution_ids":["https://openalex.org/I166825849"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.307,"has_fulltext":false,"cited_by_count":111,"citation_normalized_percentile":{"value":0.98138035,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1590","last_page":"1594"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11105","display_name":"Advanced Image Processing Techniques","score":0.9995999932289124,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9995999932289124,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9994999766349792,"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/T10627","display_name":"Advanced Image and Video Retrieval 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/codec","display_name":"Codec","score":0.8683428764343262},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8259053230285645},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6481073498725891},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5922447443008423},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.450784832239151},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4263649880886078},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4256145656108856},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.3783159852027893},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.14446291327476501}],"concepts":[{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.8683428764343262},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8259053230285645},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6481073498725891},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5922447443008423},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.450784832239151},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4263649880886078},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4256145656108856},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.3783159852027893},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.14446291327476501},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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":3,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414465","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414465","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2108.09993","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2108.09993","pdf_url":"https://arxiv.org/pdf/2108.09993","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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:trepo.tuni.fi:10024/220807","is_oa":false,"landing_page_url":"https://trepo.tuni.fi/handle/10024/220807","pdf_url":null,"source":{"id":"https://openalex.org/S4306401860","display_name":"Tampere University Institutional Repository (Tampere University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I150589677","host_organization_name":"Tampere University of Applied Sciences","host_organization_lineage":["https://openalex.org/I150589677"],"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":"conference"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2108.09993","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2108.09993","pdf_url":"https://arxiv.org/pdf/2108.09993","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":"acceptedVersion","is_accepted":true,"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":31,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1577505202","https://openalex.org/W1861492603","https://openalex.org/W2267126114","https://openalex.org/W2340897893","https://openalex.org/W2342840547","https://openalex.org/W2490784316","https://openalex.org/W2613718673","https://openalex.org/W2618011341","https://openalex.org/W2785562966","https://openalex.org/W2892278106","https://openalex.org/W2936032968","https://openalex.org/W2949361041","https://openalex.org/W2952122856","https://openalex.org/W2953318193","https://openalex.org/W2963150697","https://openalex.org/W2963677766","https://openalex.org/W2964098744","https://openalex.org/W2965631471","https://openalex.org/W2975043431","https://openalex.org/W2979673094","https://openalex.org/W3025488607","https://openalex.org/W3035345719","https://openalex.org/W3113550930","https://openalex.org/W6620707391","https://openalex.org/W6634535725","https://openalex.org/W6639102338","https://openalex.org/W6704559304","https://openalex.org/W6754634825","https://openalex.org/W6779708741","https://openalex.org/W6787196661"],"related_works":["https://openalex.org/W2107680156","https://openalex.org/W2163719598","https://openalex.org/W3161919736","https://openalex.org/W2387018512","https://openalex.org/W4301184752","https://openalex.org/W3179968364","https://openalex.org/W1509797384","https://openalex.org/W1201576901","https://openalex.org/W2751422192","https://openalex.org/W1522196789"],"abstract_inverted_index":{"Over":[0],"recent":[1],"years,":[2],"deep":[3],"learning-based":[4],"computer":[5,97],"vision":[6,98],"systems":[7],"have":[8],"been":[9],"applied":[10],"to":[11,143],"images":[12,35],"at":[13],"an":[14,46,62],"ever-increasing":[15],"pace,":[16],"oftentimes":[17],"representing":[18],"the":[19,28,32,87,116,124,148,155],"only":[20],"type":[21],"of":[22,34,82,90,135,150],"consumption":[23],"for":[24,65],"those":[25],"images.":[26],"Given":[27],"dramatic":[29],"explosion":[30],"in":[31],"number":[33],"generated":[36],"per":[37],"day,":[38],"a":[39,80],"question":[40],"arises:":[41],"how":[42],"much":[43],"better":[44],"would":[45],"image":[47,63,101,160],"codec":[48,64,114],"targeting":[49,55],"machine-consumption":[50],"perform":[51],"against":[52],"state-of-the-art":[53,117],"codecs":[54],"human-consumption?":[56],"In":[57,76],"this":[58,153],"paper,":[59],"we":[60,78],"propose":[61,79],"machines":[66],"which":[67],"is":[68,154],"neural":[69],"network":[70],"(NN)":[71],"based":[72],"and":[73,104,127,133],"end-to-end":[74,157],"learned.":[75],"particular,":[77],"set":[81],"training":[83],"strategies":[84],"that":[85,111],"address":[86],"delicate":[88],"problem":[89],"balancing":[91],"competing":[92],"loss":[93],"functions,":[94],"such":[95],"as":[96],"task":[99],"losses,":[100,103],"distortion":[102],"rate":[105],"loss.":[106],"Our":[107],"experimental":[108],"results":[109],"show":[110],"our":[112,151],"NN-based":[113],"outperforms":[115],"Versa-tile":[118],"Video":[119],"Coding":[120],"(VVC)":[121],"standard":[122],"on":[123],"object":[125],"detection":[126],"instance":[128],"segmentation":[129],"tasks,":[130],"achieving":[131],"-37.87%":[132],"-32.90%":[134],"BD-rate":[136],"gain,":[137],"respectively,":[138],"while":[139],"being":[140],"fast":[141],"thanks":[142],"its":[144],"compact":[145],"size.":[146],"To":[147],"best":[149],"knowledge,":[152],"first":[156],"learned":[158],"machine-targeted":[159],"codec.":[161]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":19},{"year":2024,"cited_by_count":48},{"year":2023,"cited_by_count":21},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}