{"id":"https://openalex.org/W7123656777","doi":"https://doi.org/10.1109/mmsp64401.2025.11324339","title":"Explicit Residual-Based Scalable Image Coding for Humans and Machines","display_name":"Explicit Residual-Based Scalable Image Coding for Humans and Machines","publication_year":2025,"publication_date":"2025-09-21","ids":{"openalex":"https://openalex.org/W7123656777","doi":"https://doi.org/10.1109/mmsp64401.2025.11324339"},"language":null,"primary_location":{"id":"doi:10.1109/mmsp64401.2025.11324339","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp64401.2025.11324339","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 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/A5102674043","display_name":"Yui Tatsumi","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":"Yui Tatsumi","raw_affiliation_strings":["Waseda University,Graduate School of FSE,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University,Graduate School of FSE,Tokyo,Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102257326","display_name":"Ziyue Zeng","orcid":"https://orcid.org/0009-0006-8906-3770"},"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":"Ziyue Zeng","raw_affiliation_strings":["Waseda University,Graduate School of FSE,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University,Graduate School of FSE,Tokyo,Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080047284","display_name":"H. Watanabe","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":false,"raw_author_name":"Hiroshi Watanabe","raw_affiliation_strings":["Waseda University,Graduate School of FSE,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University,Graduate School of FSE,Tokyo,Japan","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102674043"],"corresponding_institution_ids":["https://openalex.org/I150744194"],"apc_list":null,"apc_paid":null,"fwci":1.2784,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.86920094,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"90","last_page":"95"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.9876000285148621,"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":0.9876000285148621,"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":0.002899999963119626,"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":0.002300000051036477,"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/interpretability","display_name":"Interpretability","score":0.7470999956130981},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6646000146865845},{"id":"https://openalex.org/keywords/image-compression","display_name":"Image compression","score":0.5613999962806702},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5291000008583069},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.5284000039100647},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.462799996137619},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.3971000015735626},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.3765999972820282},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.3725000023841858}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.760699987411499},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.7470999956130981},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6646000146865845},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.614799976348877},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.5613999962806702},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5291000008583069},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5284000039100647},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.47360000014305115},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.462799996137619},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.40459999442100525},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.3971000015735626},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.3765999972820282},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3725000023841858},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32710000872612},{"id":"https://openalex.org/C205372480","wikidata":"https://www.wikidata.org/wiki/Q210521","display_name":"Image resolution","level":2,"score":0.3003999888896942},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2980000078678131},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.29179999232292175},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29170000553131104},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.29010000824928284},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C169805256","wikidata":"https://www.wikidata.org/wiki/Q1361381","display_name":"Transform coding","level":4,"score":0.28119999170303345},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.28040000796318054},{"id":"https://openalex.org/C46900642","wikidata":"https://www.wikidata.org/wiki/Q2647","display_name":"Huffman coding","level":3,"score":0.2759999930858612},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C153338461","wikidata":"https://www.wikidata.org/wiki/Q2651","display_name":"Arithmetic coding","level":4,"score":0.26249998807907104},{"id":"https://openalex.org/C175732694","wikidata":"https://www.wikidata.org/wiki/Q1128713","display_name":"Context-adaptive binary arithmetic coding","level":3,"score":0.2533999979496002}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mmsp64401.2025.11324339","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp64401.2025.11324339","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Workshop on Multimedia Signal Processing (MMSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2963661664","https://openalex.org/W2969260367","https://openalex.org/W3034469748","https://openalex.org/W3091266734","https://openalex.org/W3112487734","https://openalex.org/W3113521585","https://openalex.org/W3160673571","https://openalex.org/W3169876831","https://openalex.org/W3171673455","https://openalex.org/W3183629544","https://openalex.org/W3186910762","https://openalex.org/W3209814877","https://openalex.org/W3216897684","https://openalex.org/W4248310230","https://openalex.org/W4284691924","https://openalex.org/W4308233870","https://openalex.org/W4313019099","https://openalex.org/W4386075611","https://openalex.org/W4386210947","https://openalex.org/W4386211507","https://openalex.org/W4387967955","https://openalex.org/W4389474451","https://openalex.org/W4390872012","https://openalex.org/W4390872385","https://openalex.org/W4390873037","https://openalex.org/W4390874575","https://openalex.org/W4392628334","https://openalex.org/W4392931027","https://openalex.org/W4402915458","https://openalex.org/W4402916594","https://openalex.org/W4403841811","https://openalex.org/W4404295444","https://openalex.org/W4404349826","https://openalex.org/W4404848950","https://openalex.org/W4408352733","https://openalex.org/W4408861750","https://openalex.org/W4410383337"],"related_works":[],"abstract_inverted_index":{"Scalable":[0,140,146],"image":[1,13,32,43,64],"compression":[2,44,118,169],"is":[3,96,121],"a":[4],"technique":[5],"that":[6,46],"progressively":[7],"reconstructs":[8],"multiple":[9],"versions":[10],"of":[11,110,183],"an":[12,115],"for":[14],"different":[15],"requirements.":[16,177],"In":[17,80,100],"recent":[18],"years,":[19],"images":[20],"have":[21,67],"increasingly":[22],"been":[23],"consumed":[24],"not":[25,97],"only":[26],"by":[27,31,74,113],"humans":[28],"but":[29],"also":[30],"recognition":[33],"models.":[34],"This":[35],"shift":[36],"has":[37],"drawn":[38],"growing":[39],"attention":[40],"to":[41,154,163,174,191],"scalable":[42,126],"methods":[45,128,151],"serve":[47],"both":[48],"machine":[49,156],"and":[50,66,92,108,143,168],"human":[51],"vision":[52,157],"(ICMH).":[53],"Many":[54],"existing":[55],"models":[56,84],"employ":[57],"neural":[58],"network-based":[59],"codecs,":[60],"known":[61],"as":[62,130],"learned":[63],"compression,":[65],"made":[68],"significant":[69],"strides":[70],"in":[71,124],"this":[72,101],"field":[73],"carefully":[75],"designing":[76],"the":[77,105,181,196],"loss":[78],"functions.":[79],"some":[81],"cases,":[82],"however,":[83],"are":[85,152],"overly":[86],"reliant":[87],"on":[88],"their":[89,93],"learning":[90],"capacity,":[91],"architectural":[94],"design":[95],"sufficiently":[98],"considered.":[99],"paper,":[102],"we":[103,133],"enhance":[104],"coding":[106,127],"efficiency":[107],"interpretability":[109],"ICMH":[111],"framework":[112],"integrating":[114],"explicit":[116],"residual":[117],"mechanism,":[119],"which":[120],"commonly":[122],"employed":[123],"resolution":[125],"such":[129],"JPEG2000.":[131],"Specifically,":[132],"propose":[134],"two":[135],"complementary":[136],"methods:":[137],"Feature":[138],"Residual-based":[139,145],"Coding":[141,147],"(FR-ICMH)":[142],"Pixel":[144],"(PR-ICMH).":[148],"These":[149],"proposed":[150,185],"applicable":[153],"various":[155],"tasks.":[158],"Moreover,":[159],"they":[160],"provide":[161],"flexibility":[162],"choose":[164],"between":[165],"encoder":[166],"complexity":[167],"performance,":[170],"making":[171],"it":[172],"adaptable":[173],"diverse":[175],"application":[176],"Experimental":[178],"results":[179],"demonstrate":[180],"effectiveness":[182],"our":[184],"methods,":[186],"with":[187],"PR-ICMH":[188],"achieving":[189],"up":[190],"29.57%":[192],"BD-rate":[193],"savings":[194],"over":[195],"previous":[197],"work.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-29T08:15:47.926485","created_date":"2026-01-14T00:00:00"}