{"id":"https://openalex.org/W4402979763","doi":"https://doi.org/10.1109/icme57554.2024.10687549","title":"Unifying Generation and Compression: Ultra-low bitrate Image Coding Via Multi-stage Transformer","display_name":"Unifying Generation and Compression: Ultra-low bitrate Image Coding Via Multi-stage Transformer","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402979763","doi":"https://doi.org/10.1109/icme57554.2024.10687549"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10687549","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687549","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5102936994","display_name":"Naifu Xue","orcid":"https://orcid.org/0009-0008-2376-6152"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Naifu Xue","raw_affiliation_strings":["Communication University of China,School of Information and Communication Engineering,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Communication University of China,School of Information and Communication Engineering,Beijing,China","institution_ids":["https://openalex.org/I75689368"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039315497","display_name":"Qi Mao","orcid":"https://orcid.org/0000-0002-6040-0116"},"institutions":[{"id":"https://openalex.org/I4391768176","display_name":"State Key Laboratory of Media Convergence and Communication","ror":"https://ror.org/0595ys057","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391768176","https://openalex.org/I75689368"]},{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Mao","raw_affiliation_strings":["Communication University of China,State Key Laboratory of Media Convergence and Communication,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Communication University of China,State Key Laboratory of Media Convergence and Communication,Beijing,China","institution_ids":["https://openalex.org/I4391768176","https://openalex.org/I75689368"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100371707","display_name":"Zijian Wang","orcid":"https://orcid.org/0000-0002-7190-9620"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zijian Wang","raw_affiliation_strings":["Communication University of China,School of Information and Communication Engineering,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Communication University of China,School of Information and Communication Engineering,Beijing,China","institution_ids":["https://openalex.org/I75689368"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100368686","display_name":"Yuan Zhang","orcid":"https://orcid.org/0000-0002-1335-2780"},"institutions":[{"id":"https://openalex.org/I4391768176","display_name":"State Key Laboratory of Media Convergence and Communication","ror":"https://ror.org/0595ys057","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391768176","https://openalex.org/I75689368"]},{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Zhang","raw_affiliation_strings":["Communication University of China,State Key Laboratory of Media Convergence and Communication,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Communication University of China,State Key Laboratory of Media Convergence and Communication,Beijing,China","institution_ids":["https://openalex.org/I4391768176","https://openalex.org/I75689368"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039832462","display_name":"Siwei Ma","orcid":"https://orcid.org/0000-0002-2731-5403"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siwei Ma","raw_affiliation_strings":["Peking University,School of Electronics Engineering and Computer Science,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,School of Electronics Engineering and Computer Science,Beijing,China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8405,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.89687427,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9904000163078308,"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":0.9904000163078308,"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/T11034","display_name":"Digital Filter Design and Implementation","score":0.9473000168800354,"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"}},{"id":"https://openalex.org/T10688","display_name":"Image and Signal Denoising Methods","score":0.9235000014305115,"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":0.6144014596939087},{"id":"https://openalex.org/keywords/image-compression","display_name":"Image compression","score":0.48482075333595276},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.46558892726898193},{"id":"https://openalex.org/keywords/transform-coding","display_name":"Transform coding","score":0.41400158405303955},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.2531508803367615},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.19252613186836243},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.16665607690811157},{"id":"https://openalex.org/keywords/discrete-cosine-transform","display_name":"Discrete cosine transform","score":0.1634943187236786}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6144014596939087},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.48482075333595276},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.46558892726898193},{"id":"https://openalex.org/C169805256","wikidata":"https://www.wikidata.org/wiki/Q1361381","display_name":"Transform coding","level":4,"score":0.41400158405303955},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2531508803367615},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.19252613186836243},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.16665607690811157},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.1634943187236786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10687549","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687549","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.7099999785423279}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W845365781","https://openalex.org/W1959608418","https://openalex.org/W2101700394","https://openalex.org/W2108598243","https://openalex.org/W2559655401","https://openalex.org/W2971011627","https://openalex.org/W2981613960","https://openalex.org/W3034469748","https://openalex.org/W3036682213","https://openalex.org/W3100723657","https://openalex.org/W3160589897","https://openalex.org/W3175457126","https://openalex.org/W3180355996","https://openalex.org/W3195748956","https://openalex.org/W3202918664","https://openalex.org/W4212774754","https://openalex.org/W4224952155","https://openalex.org/W4226322431","https://openalex.org/W4313021454","https://openalex.org/W4379143777","https://openalex.org/W4386065641","https://openalex.org/W4386908184","https://openalex.org/W4398164016","https://openalex.org/W6640963894","https://openalex.org/W6675207249","https://openalex.org/W6754634825","https://openalex.org/W6779823529","https://openalex.org/W6780365925","https://openalex.org/W6810638181"],"related_works":["https://openalex.org/W2129829718","https://openalex.org/W2521595930","https://openalex.org/W4243608781","https://openalex.org/W3165542721","https://openalex.org/W4313046148","https://openalex.org/W1939109514","https://openalex.org/W4378191574","https://openalex.org/W2751842002","https://openalex.org/W2161981399","https://openalex.org/W2595043295"],"abstract_inverted_index":{"Recent":[0],"progress":[1],"in":[2,44,126,145,152,162],"generative":[3,29,163],"compression":[4,46],"technology":[5],"has":[6],"significantly":[7],"improved":[8],"the":[9,26,33,53,73,83,87,108,113,118,127,135,138],"perceptual":[10,146],"quality":[11,147],"of":[12,28,36,55,75,82,89,129,137],"compressed":[13],"data.":[14],"However,":[15],"these":[16],"advancements":[17],"primarily":[18],"focus":[19],"on":[20],"producing":[21],"high-frequency":[22],"details,":[23],"often":[24],"overlooking":[25],"ability":[27],"models":[30,58,93],"to":[31,101],"capture":[32],"prior":[34,109,120],"distribution":[35],"image":[37,92],"content,":[38],"thus":[39],"impeding":[40],"further":[41],"bitrate":[42,154],"reduction":[43],"extreme":[45],"scenarios":[47,155],"(<":[48],"0.05":[49],"bpp).":[50],"Motivated":[51],"by":[52],"capabilities":[54],"predictive":[56],"language":[57],"for":[59,94,106,121],"lossless":[60],"compression,":[61],"this":[62],"paper":[63],"introduces":[64],"a":[65,97,159],"novel":[66],"Unified":[67],"Image":[68],"Generation-Compression":[69],"(UIGC)":[70],"paradigm,":[71],"merging":[72],"processes":[74],"generation":[76],"and":[77,124,148],"compression.":[78,164],"A":[79],"key":[80],"feature":[81],"UIGC":[84,140],"framework":[85,115,141],"is":[86],"adoption":[88],"vector-quantized":[90],"(VQ)":[91],"tokenization,":[95],"alongside":[96],"multi-stage":[98],"transformer":[99],"designed":[100],"exploit":[102],"spatial":[103],"contextual":[104],"information":[105],"modeling":[107],"distribution.":[110],"As":[111],"such,":[112],"dual-purpose":[114],"effectively":[116],"utilizes":[117],"learned":[119],"entropy":[122],"estimation":[123],"assists":[125],"regeneration":[128],"lost":[130],"tokens.":[131],"Extensive":[132],"experiments":[133],"demonstrate":[134],"superiority":[136],"proposed":[139],"over":[142],"existing":[143],"codecs":[144],"human":[149],"perception,":[150],"particularly":[151],"ultra-low":[153],"(\u22640.03":[156],"bpp),":[157],"pioneering":[158],"new":[160],"direction":[161]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
