{"id":"https://openalex.org/W4415708114","doi":"https://doi.org/10.1109/icme59968.2025.11210034","title":"Embedding Compression Distortion in Video Coding for Machines","display_name":"Embedding Compression Distortion in Video Coding for Machines","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708114","doi":"https://doi.org/10.1109/icme59968.2025.11210034"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11210034","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11210034","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/A5090418853","display_name":"Yuxiao Sun","orcid":"https://orcid.org/0009-0005-6505-1479"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuxiao Sun","raw_affiliation_strings":["Beijing Jiaotong University,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University,Beijing,China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009318707","display_name":"Yao Zhao","orcid":"https://orcid.org/0000-0001-9370-7934"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao Zhao","raw_affiliation_strings":["Beijing Jiaotong University,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University,Beijing,China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115592099","display_name":"Meiqin Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meiqin Liu","raw_affiliation_strings":["Beijing Jiaotong University,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University,Beijing,China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100362745","display_name":"Yao Zhao","orcid":"https://orcid.org/0000-0002-8581-9554"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Yao","raw_affiliation_strings":["University of Scienece and Technology Beijing,Beijing,China"],"affiliations":[{"raw_affiliation_string":"University of Scienece and Technology Beijing,Beijing,China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100403129","display_name":"Weisi Lin","orcid":"https://orcid.org/0000-0001-9866-1947"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Weisi Lin","raw_affiliation_strings":["Nanyang Technological University,Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5090418853"],"corresponding_institution_ids":["https://openalex.org/I21193070"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.39212162,"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/T10741","display_name":"Video Coding and Compression Technologies","score":0.32170000672340393,"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"}},"topics":[{"id":"https://openalex.org/T10741","display_name":"Video Coding and Compression Technologies","score":0.32170000672340393,"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/T11165","display_name":"Image and Video Quality Assessment","score":0.24609999358654022,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.11580000072717667,"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/codec","display_name":"Codec","score":0.7973999977111816},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.5536999702453613},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5271999835968018},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.477400004863739},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.40790000557899475},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.39320001006126404},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3522999882698059},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.3483999967575073}],"concepts":[{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.7973999977111816},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7958999872207642},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.5536999702453613},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5271999835968018},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.477400004863739},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.46230000257492065},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4447999894618988},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.40790000557899475},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.39320001006126404},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3522999882698059},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.3483999967575073},{"id":"https://openalex.org/C165021410","wikidata":"https://www.wikidata.org/wiki/Q55564","display_name":"Lossy compression","level":2,"score":0.33649998903274536},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3280999958515167},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3133000135421753},{"id":"https://openalex.org/C64185310","wikidata":"https://www.wikidata.org/wiki/Q843483","display_name":"Rate\u2013distortion theory","level":3,"score":0.3125999867916107},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.29809999465942383},{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.29319998621940613},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.288100004196167},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.28610000014305115},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.28349998593330383},{"id":"https://openalex.org/C94835093","wikidata":"https://www.wikidata.org/wiki/Q3113333","display_name":"Data compression ratio","level":5,"score":0.27410000562667847},{"id":"https://openalex.org/C106030495","wikidata":"https://www.wikidata.org/wiki/Q1797012","display_name":"Video compression picture types","level":4,"score":0.26010000705718994},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.25690001249313354}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11210034","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11210034","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":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W2140199336","https://openalex.org/W2142683286","https://openalex.org/W2146395539","https://openalex.org/W2152281536","https://openalex.org/W2536460611","https://openalex.org/W2626739722","https://openalex.org/W2969260367","https://openalex.org/W3034469748","https://openalex.org/W4312651322","https://openalex.org/W4312815172","https://openalex.org/W4386065808","https://openalex.org/W4389169596","https://openalex.org/W4390871708","https://openalex.org/W4391365622","https://openalex.org/W4402915930","https://openalex.org/W4402979167","https://openalex.org/W4415481232"],"related_works":[],"abstract_inverted_index":{"Currently,":[0],"video":[1],"transmission":[2],"serves":[3],"not":[4],"only":[5],"the":[6,32,63,76,89,103,111,117,146],"Human":[7],"Visual":[8],"System":[9],"(HVS)":[10],"for":[11,17,25],"viewing":[12],"but":[13],"also":[14],"machine":[15,35],"perception":[16],"analysis.":[18],"However,":[19],"existing":[20,150],"codecs":[21,135,151],"are":[22,170],"primarily":[23],"optimized":[24],"pixel-domain":[26],"and":[27,56,68,129,136,161,167],"HVS-perception":[28],"metrics":[29],"rather":[30],"than":[31],"needs":[33],"of":[34,149,157,163],"vision":[36],"tasks.":[37],"To":[38],"address":[39],"this":[40],"issue,":[41],"we":[42,79],"propose":[43],"a":[44,81,95,107],"Compression":[45],"Distortion":[46],"Representation":[47],"Embedding":[48],"(CDRE)":[49],"framework,":[50],"which":[51],"extracts":[52],"machine-perception-related":[53,77],"distortion":[54,97,104],"representation":[55,112],"embeds":[57],"it":[58,121],"into":[59,106,116],"downstream":[60,118,137],"models,":[61],"addressing":[62],"information":[64,105],"lost":[65],"during":[66],"compression":[67,86,127],"improving":[69],"task":[70],"performance.":[71,131],"Specifically,":[72],"to":[73,101,122],"better":[74,124],"analyze":[75],"distortion,":[78],"design":[80],"compression-sensitive":[82],"extractor":[83],"that":[84,140],"identifies":[85],"degradation":[87,128],"in":[88,155,172],"feature":[90],"domain.":[91],"For":[92],"efficient":[93],"transmission,":[94],"lightweight":[96],"codec":[98],"is":[99,113],"introduced":[100],"compress":[102],"compact":[108],"representation.":[109],"Subsequently,":[110],"progressively":[114],"embedded":[115],"model,":[119],"enabling":[120],"be":[123],"informed":[125],"about":[126],"enhancing":[130],"Experiments":[132],"across":[133],"various":[134],"tasks":[138],"demonstrate":[139],"our":[141],"framework":[142],"can":[143],"effectively":[144],"boost":[145],"rate-task":[147],"performance":[148],"with":[152],"minimal":[153],"overhead":[154],"terms":[156],"bitrate,":[158],"execution":[159],"time,":[160],"number":[162],"parameters.":[164],"Our":[165],"codes":[166],"supplementary":[168],"materials":[169],"released":[171],"https://github.com/Ws-Syx/CDRE/.":[173]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-30T00:00:00"}
