{"id":"https://openalex.org/W4389474451","doi":"https://doi.org/10.1109/mmsp59012.2023.10337731","title":"Region of Interest Enabled Learned Image Coding for Machines","display_name":"Region of Interest Enabled Learned Image Coding for Machines","publication_year":2023,"publication_date":"2023-09-27","ids":{"openalex":"https://openalex.org/W4389474451","doi":"https://doi.org/10.1109/mmsp59012.2023.10337731"},"language":"en","primary_location":{"id":"doi:10.1109/mmsp59012.2023.10337731","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp59012.2023.10337731","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 25th International Workshop on Multimedia Signal Processing (MMSP)","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/A5028336376","display_name":"Jukka Ahonen","orcid":"https://orcid.org/0000-0003-1683-4475"},"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":true,"raw_author_name":"Jukka I. Ahonen","raw_affiliation_strings":["Tampere University,Tampere,Finland","Tampere University, Tampere, Finland"],"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/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"],"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,Tampere,Finland","Nokia Technologies, Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Nokia Technologies,Tampere,Finland","institution_ids":["https://openalex.org/I2738502077"]},{"raw_affiliation_string":"Nokia Technologies, Tampere, Finland","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,Tampere,Finland","Nokia Technologies, Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Nokia Technologies,Tampere,Finland","institution_ids":["https://openalex.org/I2738502077"]},{"raw_affiliation_string":"Nokia Technologies, Tampere, Finland","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/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":"Esa Rahtu","raw_affiliation_strings":["Nokia Technologies,Tampere,Finland","Nokia Technologies, Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Nokia Technologies,Tampere,Finland","institution_ids":["https://openalex.org/I2738502077"]},{"raw_affiliation_string":"Nokia Technologies, Tampere, Finland","institution_ids":["https://openalex.org/I2738502077"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5028336376"],"corresponding_institution_ids":["https://openalex.org/I166825849"],"apc_list":null,"apc_paid":null,"fwci":0.7222,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.73449106,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","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/T10531","display_name":"Advanced Vision and Imaging","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/T10627","display_name":"Advanced Image and Video Retrieval 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/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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8098659515380859},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.7248594164848328},{"id":"https://openalex.org/keywords/region-of-interest","display_name":"Region of interest","score":0.6428641080856323},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6338056325912476},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5044816732406616},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.5027787685394287},{"id":"https://openalex.org/keywords/image-compression","display_name":"Image compression","score":0.46232086420059204},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.45762667059898376},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4176826775074005},{"id":"https://openalex.org/keywords/image-quality","display_name":"Image quality","score":0.4103360176086426},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4031849503517151},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3725520372390747},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.2863759994506836},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08480927348136902},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.07671472430229187}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8098659515380859},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.7248594164848328},{"id":"https://openalex.org/C19609008","wikidata":"https://www.wikidata.org/wiki/Q2138203","display_name":"Region of interest","level":2,"score":0.6428641080856323},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6338056325912476},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5044816732406616},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5027787685394287},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.46232086420059204},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.45762667059898376},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4176826775074005},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.4103360176086426},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4031849503517151},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3725520372390747},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2863759994506836},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08480927348136902},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.07671472430229187},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/mmsp59012.2023.10337731","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp59012.2023.10337731","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 25th International Workshop on Multimedia Signal Processing (MMSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:trepo.tuni.fi:10024/225711","is_oa":false,"landing_page_url":"https://trepo.tuni.fi/handle/10024/225711","pdf_url":null,"source":{"id":"https://openalex.org/S7407055260","display_name":"Trepo - Institutional Repository of Tampere University","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W2099001231","https://openalex.org/W2101700394","https://openalex.org/W2146395539","https://openalex.org/W2949361041","https://openalex.org/W2982483316","https://openalex.org/W2997454254","https://openalex.org/W3034469748","https://openalex.org/W3117485197","https://openalex.org/W3119744415","https://openalex.org/W3160673571","https://openalex.org/W3169876831","https://openalex.org/W3202918664","https://openalex.org/W4205495609","https://openalex.org/W4304701258","https://openalex.org/W4308233870","https://openalex.org/W4308233894","https://openalex.org/W4312289667","https://openalex.org/W4312590925","https://openalex.org/W4313019099","https://openalex.org/W4386598521","https://openalex.org/W6620707391","https://openalex.org/W6754634825","https://openalex.org/W6769827072","https://openalex.org/W6846144196"],"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/W2751422192","https://openalex.org/W1509797384","https://openalex.org/W1201576901","https://openalex.org/W2479386627","https://openalex.org/W2326552140"],"abstract_inverted_index":{"Image":[0,92,192],"and":[1,11,18,32,156,168],"video":[2],"coding":[3,42],"for":[4,50,55,86,95,106,146,190,194],"machines":[5,56],"has":[6,33],"been":[7],"recently":[8],"gaining":[9],"more":[10,12,132],"interest":[13],"from":[14],"both":[15],"the":[16,19,38,47,61,67,71,99,103,107,111,115,118,122,126,139,142,162,174,181],"industry":[17],"research":[20,183],"community.":[21],"One":[22],"successful":[23],"approach":[24],"is":[25,57,180],"based":[26],"on":[27,165],"end-to-end":[28],"(E2E)":[29],"learned":[30],"compression":[31],"shown":[34],"significant":[35,153],"gains":[36],"over":[37,63,161],"state-of-the-art":[39],"conventional":[40],"image":[41,53,112],"methods.":[43],"However,":[44],"one":[45],"of":[46,66,110,117,141,176],"remaining":[48],"challenges":[49],"such":[51],"E2E-learned":[52],"codecs":[54],"to":[58,121],"adaptively":[59],"allocate":[60],"bits":[62,104],"different":[64],"regions":[65,109,124],"image,":[68],"while":[69,137],"retaining":[70],"machine":[72,147],"vision":[73],"performance.":[74],"In":[75,97],"this":[76,179],"paper,":[77],"we":[78],"propose":[79],"a":[80,90],"method":[81,101,151],"that":[82],"leverages":[83],"Regions-Of-Interest":[84],"(ROIs)":[85],"bitrate":[87],"allocation":[88],"within":[89],"Learned":[91,191],"Codec":[93],"(LIC)":[94],"machines.":[96,195],"particular,":[98],"proposed":[100,150],"reduces":[102],"allocated":[105],"background":[108,123,135],"by":[113],"reducing":[114],"variance":[116],"elements":[119],"corresponding":[120],"in":[125,131],"latent":[127],"representation.":[128],"This":[129],"results":[130],"heavily":[133],"quantized":[134],"areas,":[136],"keeping":[138],"quality":[140],"ROI":[143],"areas":[144],"suitable":[145],"tasks.":[148],"The":[149],"achieves":[152],"gains,":[154],"-15.80%":[155],"-22.43%":[157],"Pareto":[158],"BD-rate":[159],"reduction,":[160],"baseline":[163],"LIC":[164],"object":[166],"detection":[167],"instance":[169],"segmentation":[170],"tasks,":[171],"respectively.":[172],"To":[173],"best":[175],"our":[177],"knowledge,":[178],"first":[182],"paper":[184],"proposing":[185],"an":[186],"ROI-based":[187],"inference-time":[188],"technology":[189],"Coding":[193]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-29T08:15:47.926485","created_date":"2025-10-10T00:00:00"}