{"id":"https://openalex.org/W4406860667","doi":"https://doi.org/10.1109/vcip63160.2024.10849922","title":"Tell Codec What Worth Compressing: Semantically Disentangled Image Coding for Machine with LMMs","display_name":"Tell Codec What Worth Compressing: Semantically Disentangled Image Coding for Machine with LMMs","publication_year":2024,"publication_date":"2024-12-08","ids":{"openalex":"https://openalex.org/W4406860667","doi":"https://doi.org/10.1109/vcip63160.2024.10849922"},"language":"en","primary_location":{"id":"doi:10.1109/vcip63160.2024.10849922","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vcip63160.2024.10849922","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 Visual Communications and Image Processing (VCIP)","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/A5100676698","display_name":"Jinming Liu","orcid":"https://orcid.org/0000-0002-0643-5676"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jinming Liu","raw_affiliation_strings":["Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000185895","display_name":"Yuntao Wei","orcid":"https://orcid.org/0000-0002-3418-9329"},"institutions":[{"id":"https://openalex.org/I4210165339","display_name":"Ningbo Institute of Industrial Technology","ror":"https://ror.org/05nqg3g04","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165339"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuntao Wei","raw_affiliation_strings":["Eastern Institute of Technology,Ningbo Institute of Digital Twin,Ningbo,China"],"affiliations":[{"raw_affiliation_string":"Eastern Institute of Technology,Ningbo Institute of Digital Twin,Ningbo,China","institution_ids":["https://openalex.org/I4210165339"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049747474","display_name":"Junyan Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165339","display_name":"Ningbo Institute of Industrial Technology","ror":"https://ror.org/05nqg3g04","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165339"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junyan Lin","raw_affiliation_strings":["Eastern Institute of Technology,Ningbo Institute of Digital Twin,Ningbo,China"],"affiliations":[{"raw_affiliation_string":"Eastern Institute of Technology,Ningbo Institute of Digital Twin,Ningbo,China","institution_ids":["https://openalex.org/I4210165339"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101102569","display_name":"Shengyang Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165339","display_name":"Ningbo Institute of Industrial Technology","ror":"https://ror.org/05nqg3g04","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165339"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengyang Zhao","raw_affiliation_strings":["Eastern Institute of Technology,Ningbo Institute of Digital Twin,Ningbo,China"],"affiliations":[{"raw_affiliation_string":"Eastern Institute of Technology,Ningbo Institute of Digital Twin,Ningbo,China","institution_ids":["https://openalex.org/I4210165339"]}]},{"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/I180203408","display_name":"Yokohama National University","ror":"https://ror.org/03zyp6p76","country_code":"JP","type":"education","lineage":["https://openalex.org/I180203408"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Heming Sun","raw_affiliation_strings":["Yokohama National University"],"affiliations":[{"raw_affiliation_string":"Yokohama National University","institution_ids":["https://openalex.org/I180203408"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079572598","display_name":"Zhibo Chen","orcid":"https://orcid.org/0000-0002-8525-5066"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhibo Chen","raw_affiliation_strings":["University of Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101739843","display_name":"Wenjun Zeng","orcid":"https://orcid.org/0000-0003-0362-3388"},"institutions":[{"id":"https://openalex.org/I4210165339","display_name":"Ningbo Institute of Industrial Technology","ror":"https://ror.org/05nqg3g04","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165339"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjun Zeng","raw_affiliation_strings":["Eastern Institute of Technology,Ningbo Institute of Digital Twin,Ningbo,China"],"affiliations":[{"raw_affiliation_string":"Eastern Institute of Technology,Ningbo Institute of Digital Twin,Ningbo,China","institution_ids":["https://openalex.org/I4210165339"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023967844","display_name":"Xin Jin","orcid":"https://orcid.org/0000-0001-6655-3888"},"institutions":[{"id":"https://openalex.org/I4210165339","display_name":"Ningbo Institute of Industrial Technology","ror":"https://ror.org/05nqg3g04","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165339"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Jin","raw_affiliation_strings":["Eastern Institute of Technology,Ningbo Institute of Digital Twin,Ningbo,China"],"affiliations":[{"raw_affiliation_string":"Eastern Institute of Technology,Ningbo Institute of Digital Twin,Ningbo,China","institution_ids":["https://openalex.org/I4210165339"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5100676698"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.2624,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.58984993,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9344000220298767,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9344000220298767,"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":0.7235485315322876},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.6496888399124146},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.5543258190155029},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43145716190338135},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12191754579544067},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.12010368704795837},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.0810108482837677}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7235485315322876},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.6496888399124146},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5543258190155029},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43145716190338135},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12191754579544067},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.12010368704795837},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.0810108482837677}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/vcip63160.2024.10849922","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vcip63160.2024.10849922","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 Visual Communications and Image Processing (VCIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7900000214576721,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1905882502","https://openalex.org/W2101700394","https://openalex.org/W2138011018","https://openalex.org/W2140196014","https://openalex.org/W2146395539","https://openalex.org/W2412782625","https://openalex.org/W2552465432","https://openalex.org/W2785562966","https://openalex.org/W2904910963","https://openalex.org/W2963150697","https://openalex.org/W2963622213","https://openalex.org/W2969260367","https://openalex.org/W2984121207","https://openalex.org/W2986755220","https://openalex.org/W2986803748","https://openalex.org/W2987734933","https://openalex.org/W3000264140","https://openalex.org/W3034469748","https://openalex.org/W3082548248","https://openalex.org/W3110435696","https://openalex.org/W3112487734","https://openalex.org/W3134368609","https://openalex.org/W3160555381","https://openalex.org/W4206444875","https://openalex.org/W4312806968","https://openalex.org/W4320027612","https://openalex.org/W4360604369","https://openalex.org/W4386065641","https://openalex.org/W4386075611","https://openalex.org/W4387967955","https://openalex.org/W4390873037","https://openalex.org/W4390874575","https://openalex.org/W4391306640","https://openalex.org/W4402753874","https://openalex.org/W4404612908","https://openalex.org/W4405595839","https://openalex.org/W6620707391","https://openalex.org/W6638319203","https://openalex.org/W6772383348","https://openalex.org/W6778883912","https://openalex.org/W6791353385","https://openalex.org/W6838461927","https://openalex.org/W6849177959","https://openalex.org/W6851592950","https://openalex.org/W6851950068","https://openalex.org/W6853520483","https://openalex.org/W6857419123","https://openalex.org/W6857569170","https://openalex.org/W6857614378","https://openalex.org/W6859532197","https://openalex.org/W6861232000","https://openalex.org/W6862276026"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2964213236","https://openalex.org/W2163719598","https://openalex.org/W3161919736","https://openalex.org/W2387018512","https://openalex.org/W2107680156","https://openalex.org/W4301184752","https://openalex.org/W2008888243"],"abstract_inverted_index":{"We":[0,24,160],"present":[1],"a":[2,133,156,176,196],"new":[3],"image":[4,47,55,109,129,143],"compression":[5,48],"paradigm":[6],"to":[7,68,86,107,186],"achieve":[8],"\"intelligently":[9],"coding":[10,56],"for":[11,39,51,57,165],"machine\"":[12],"by":[13,27],"cleverly":[14],"leveraging":[15],"the":[16,28,41,54,65,91,128],"common":[17],"sense":[18],"of":[19,96,127,179],"Large":[20],"Multimodal":[21],"Models":[22],"(LMMs).":[23],"are":[25,34],"motivated":[26],"evidence":[29],"that":[30],"large":[31],"language/multimodal":[32],"models":[33],"powerful":[35,92],"general-purpose":[36],"semantics":[37],"predictors":[38],"understanding":[40,94],"real":[42],"world.":[43],"Different":[44],"from":[45],"traditional":[46],"typically":[49],"optimized":[50],"human":[52],"eyes,":[53],"machines":[58],"(ICM)":[59],"framework":[60],"we":[61,80,121],"focus":[62],"on":[63,117,175],"requires":[64],"compressed":[66],"bitstream":[67],"more":[69,187,197],"comply":[70],"with":[71,132,154,172],"different":[72,180],"downstream":[73],"intelligent":[74,199],"analysis":[75],"tasks.":[76,182],"To":[77],"this":[78,137],"end,":[79],"employ":[81],"LMM":[82],"to${\\text{tell":[83],"codec":[84,184],"what":[85],"compress}}$:":[87],"1)":[88],"first":[89],"utilize":[90],"semantic":[93,119],"capability":[95],"LMMs":[97],"w.r.t":[98],"object":[99,145],"grounding,":[100],"identification,":[101],"and":[102,114,124,169,195],"importance":[103],"ranking":[104],"via":[105],"prompts,":[106],"disentangle":[108],"content":[110],"before":[111],"compression,":[112],"2)":[113],"then":[115],"based":[116],"these":[118],"priors":[120],"accordingly":[122],"encode":[123],"transmit":[125],"objects":[126],"in":[130],"order":[131],"structured":[134,158],"bitstream.":[135,159],"In":[136],"way,":[138],"diverse":[139],"vision":[140,181],"benchmarks":[141],"including":[142],"classification,":[144],"detection,":[146],"instance":[147],"segmentation,":[148],"etc.,":[149],"can":[150],"be":[151],"well":[152],"supported":[153],"such":[155],"semantically":[157],"dub":[161],"our":[162],"method":[163],"\"SDComp\"":[164],"\"Semantically":[166],"Disentangled":[167],"Compression\",":[168],"compare":[170],"it":[171],"state-of-the-art":[173],"codecs":[174],"wide":[177],"variety":[178],"SDComp":[183],"leads":[185],"flexible":[188],"reconstruction":[189],"results,":[190],"promised":[191],"decoded":[192],"visual":[193],"quality,":[194],"generic/satisfactory":[198],"task-supporting":[200],"ability.":[201]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}