{"id":"https://openalex.org/W4415709504","doi":"https://doi.org/10.1109/icme59968.2025.11209144","title":"Representation Disentanglement for Semantic Coding","display_name":"Representation Disentanglement for Semantic Coding","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415709504","doi":"https://doi.org/10.1109/icme59968.2025.11209144"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209144","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209144","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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":false,"raw_author_name":"Jinming Liu","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101935504","display_name":"Junhao Geng","orcid":"https://orcid.org/0000-0002-3891-839X"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]},{"id":"https://openalex.org/I24407930","display_name":"Hunan University of Science and Engineering","ror":"https://ror.org/04ymz0q33","country_code":"CN","type":"education","lineage":["https://openalex.org/I24407930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junhao Geng","raw_affiliation_strings":["Hunan University,The College of Computer Science and Electronic Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University,The College of Computer Science and Electronic Engineering","institution_ids":["https://openalex.org/I16609230","https://openalex.org/I24407930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108909482","display_name":"Lin Lv","orcid":"https://orcid.org/0009-0007-2624-343X"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]},{"id":"https://openalex.org/I24407930","display_name":"Hunan University of Science and Engineering","ror":"https://ror.org/04ymz0q33","country_code":"CN","type":"education","lineage":["https://openalex.org/I24407930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lexiang Lv","raw_affiliation_strings":["Hunan University,The College of Computer Science and Electronic Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University,The College of Computer Science and Electronic Engineering","institution_ids":["https://openalex.org/I16609230","https://openalex.org/I24407930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101739843","display_name":"Wenjun Zeng","orcid":"https://orcid.org/0000-0003-2531-3137"},"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"],"raw_orcid":null,"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"],"raw_orcid":null,"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":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27367236,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.2930999994277954,"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":0.2930999994277954,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.1738000065088272,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.13519999384880066,"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/leverage","display_name":"Leverage (statistics)","score":0.47929999232292175},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4255000054836273},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4092000126838684},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.4083999991416931},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.40070000290870667},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.3671000003814697},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.3434999883174896},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3343999981880188},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.33340001106262207}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7670999765396118},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6069999933242798},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5059000253677368},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.47929999232292175},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4255000054836273},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4092000126838684},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.4083999991416931},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.40070000290870667},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.3671000003814697},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3434999883174896},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3343999981880188},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.33340001106262207},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3246000111103058},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3228999972343445},{"id":"https://openalex.org/C136695289","wikidata":"https://www.wikidata.org/wiki/Q415568","display_name":"Bitstream","level":3,"score":0.3212999999523163},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3154999911785126},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.29330000281333923},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.28940001130104065},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2858000099658966},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C169805256","wikidata":"https://www.wikidata.org/wiki/Q1361381","display_name":"Transform coding","level":4,"score":0.2685000002384186},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C2777946921","wikidata":"https://www.wikidata.org/wiki/Q7449044","display_name":"Semantic analysis (machine learning)","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2574000060558319}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209144","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209144","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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":18,"referenced_works":["https://openalex.org/W2140196014","https://openalex.org/W2146395539","https://openalex.org/W2163922914","https://openalex.org/W2962770929","https://openalex.org/W3034469748","https://openalex.org/W3034600949","https://openalex.org/W3082548248","https://openalex.org/W3112487734","https://openalex.org/W3202918664","https://openalex.org/W3217030260","https://openalex.org/W4312933868","https://openalex.org/W4386065641","https://openalex.org/W4386075611","https://openalex.org/W4390873037","https://openalex.org/W4403878008","https://openalex.org/W4404654662","https://openalex.org/W4405844682","https://openalex.org/W4406860667"],"related_works":[],"abstract_inverted_index":{"The":[0],"learned":[1,114],"image":[2,102],"compression":[3,49],"methods":[4,17],"have":[5],"achieved":[6],"advances":[7],"in":[8,31,96],"both":[9],"human":[10],"perception":[11],"and":[12,45,62,132,150],"machine":[13],"vision.":[14],"However,":[15],"previous":[16],"focus":[18],"on":[19,52],"transmitting":[20],"visual":[21],"symbols":[22],"losslessly":[23],"instead":[24],"of":[25,100],"precisely":[26],"conveying":[27],"semantic":[28,64,93,131,143],"meaning,":[29],"resulting":[30],"bandwidth":[32],"waste,":[33],"especially":[34],"for":[35,74,85,136],"AI":[36],"applications.":[37],"In":[38],"this":[39],"work,":[40],"we":[41,77,111],"study":[42],"\"Semantic":[43],"Coding\"":[44],"propose":[46],"a":[47,70,80,86,113,123,129],"novel":[48],"method":[50,145],"based":[51],"representation":[53,88],"disentanglement,":[54],"which":[55,90],"understands":[56],"images":[57,149],"at":[58],"the":[59,97,101,105,118,155],"attribute":[60,94],"level":[61],"separates":[63],"factors":[65,95],"into":[66],"different":[67],"parts,":[68],"achieving":[69],"semantically":[71],"structured":[72],"bitstream":[73],"transmission.":[75],"Specifically,":[76],"first":[78],"leverage":[79],"conditional":[81],"generative":[82],"diffusion":[83],"procedure":[84],"disentangled":[87,120],"learning,":[89],"learns":[91],"meaningful":[92],"latent":[98],"space":[99],"assisted":[103],"by":[104,153],"extra":[106],"language":[107],"inductive":[108],"bias.":[109],"Furthermore,":[110],"employ":[112],"codec":[115],"to":[116],"compress":[117],"inner":[119,156],"representations":[121],"as":[122],"bitstream,":[124],"where":[125],"each":[126],"part":[127],"represents":[128],"specific":[130],"can":[133],"be":[134],"used":[135],"purposely":[137],"decoding.":[138],"Experiments":[139],"show":[140],"that":[141],"our":[142],"coding":[144],"could":[146],"reconstruct":[147],"high-quality":[148],"enable":[151],"encryption":[152],"shifting":[154],"semantics.":[157]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-30T00:00:00"}