{"id":"https://openalex.org/W4385627414","doi":"https://doi.org/10.1109/tcsvt.2023.3302858","title":"End-to-End Learnable Multi-Scale Feature Compression for VCM","display_name":"End-to-End Learnable Multi-Scale Feature Compression for VCM","publication_year":2023,"publication_date":"2023-08-07","ids":{"openalex":"https://openalex.org/W4385627414","doi":"https://doi.org/10.1109/tcsvt.2023.3302858"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2023.3302858","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2023.3302858","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-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/A5047037020","display_name":"Yeongwoong Kim","orcid":"https://orcid.org/0000-0001-7378-7367"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]},{"id":"https://openalex.org/I35928602","display_name":"Kyung Hee University","ror":"https://ror.org/01zqcg218","country_code":"KR","type":"education","lineage":["https://openalex.org/I35928602"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yeongwoong Kim","raw_affiliation_strings":["Electronics and Telecommunications Research Institute (ETRI), Daejeon, Republic of Korea","Visual Media Laboratory, School of Computing, Kyung Hee University, Yongin-si, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0001-7378-7367","affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute (ETRI), Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I142401562"]},{"raw_affiliation_string":"Visual Media Laboratory, School of Computing, Kyung Hee University, Yongin-si, Republic of Korea","institution_ids":["https://openalex.org/I35928602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101998939","display_name":"Hyewon Jeong","orcid":"https://orcid.org/0000-0003-1230-870X"},"institutions":[{"id":"https://openalex.org/I35928602","display_name":"Kyung Hee University","ror":"https://ror.org/01zqcg218","country_code":"KR","type":"education","lineage":["https://openalex.org/I35928602"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyewon Jeong","raw_affiliation_strings":["Visual Media Laboratory, School of Computing, Kyung Hee University, Yongin-si, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Visual Media Laboratory, School of Computing, Kyung Hee University, Yongin-si, Republic of Korea","institution_ids":["https://openalex.org/I35928602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101219269","display_name":"Janghyun Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I35928602","display_name":"Kyung Hee University","ror":"https://ror.org/01zqcg218","country_code":"KR","type":"education","lineage":["https://openalex.org/I35928602"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Janghyun Yu","raw_affiliation_strings":["Visual Media Laboratory, School of Computing, Kyung Hee University, Yongin-si, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Visual Media Laboratory, School of Computing, Kyung Hee University, Yongin-si, Republic of Korea","institution_ids":["https://openalex.org/I35928602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001200204","display_name":"Younhee Kim","orcid":"https://orcid.org/0000-0003-0013-4351"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]},{"id":"https://openalex.org/I35928602","display_name":"Kyung Hee University","ror":"https://ror.org/01zqcg218","country_code":"KR","type":"education","lineage":["https://openalex.org/I35928602"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Younhee Kim","raw_affiliation_strings":["Electronics and Telecommunications Research Institute (ETRI), Daejeon, Republic of Korea","Visual Media Laboratory, School of Computing, Kyung Hee University, Yongin-si, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute (ETRI), Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I142401562"]},{"raw_affiliation_string":"Visual Media Laboratory, School of Computing, Kyung Hee University, Yongin-si, Republic of Korea","institution_ids":["https://openalex.org/I35928602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100401547","display_name":"Jooyoung Lee","orcid":"https://orcid.org/0000-0003-0753-0699"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jooyoung Lee","raw_affiliation_strings":["Electronics and Telecommunications Research Institute (ETRI), Daejeon, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0003-0753-0699","affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute (ETRI), Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101718441","display_name":"Seyoon Jeong","orcid":"https://orcid.org/0000-0002-1675-4814"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Se Yoon Jeong","raw_affiliation_strings":["Electronics and Telecommunications Research Institute (ETRI), Daejeon, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-1675-4814","affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute (ETRI), Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047351360","display_name":"Hui Yong Kim","orcid":"https://orcid.org/0000-0001-7308-133X"},"institutions":[{"id":"https://openalex.org/I35928602","display_name":"Kyung Hee University","ror":"https://ror.org/01zqcg218","country_code":"KR","type":"education","lineage":["https://openalex.org/I35928602"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hui Yong Kim","raw_affiliation_strings":["Visual Media Laboratory, School of Computing, Kyung Hee University, Yongin-si, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0001-7308-133X","affiliations":[{"raw_affiliation_string":"Visual Media Laboratory, School of Computing, Kyung Hee University, Yongin-si, Republic of Korea","institution_ids":["https://openalex.org/I35928602"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.6163,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.94641776,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"34","issue":"5","first_page":"3156","last_page":"3167"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998000264167786,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998000264167786,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9995999932289124,"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":0.9995999932289124,"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":0.7503069639205933},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.633902370929718},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6214213371276855},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.5326454639434814},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4900282621383667},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4589707553386688},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.44739851355552673},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4473511278629303},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.43605419993400574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7503069639205933},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.633902370929718},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6214213371276855},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.5326454639434814},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4900282621383667},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4589707553386688},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.44739851355552673},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4473511278629303},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.43605419993400574},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2023.3302858","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2023.3302858","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1677182931","https://openalex.org/W1861492603","https://openalex.org/W1921523184","https://openalex.org/W2146395539","https://openalex.org/W2178928294","https://openalex.org/W2194775991","https://openalex.org/W2423557781","https://openalex.org/W2476548250","https://openalex.org/W2549139847","https://openalex.org/W2552465432","https://openalex.org/W2565639579","https://openalex.org/W2752782242","https://openalex.org/W2785562966","https://openalex.org/W2963150697","https://openalex.org/W2963447011","https://openalex.org/W3004198379","https://openalex.org/W3034469748","https://openalex.org/W3091266734","https://openalex.org/W3097448661","https://openalex.org/W3172982968","https://openalex.org/W3175457126","https://openalex.org/W3202918664","https://openalex.org/W3212865599","https://openalex.org/W4223425316","https://openalex.org/W4225619305","https://openalex.org/W4287605633","https://openalex.org/W4288083516","https://openalex.org/W4313058111","https://openalex.org/W4360596917","https://openalex.org/W6640185926","https://openalex.org/W6754634825","https://openalex.org/W6755487101","https://openalex.org/W6766978945","https://openalex.org/W6810067190"],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W2142795561","https://openalex.org/W2494338568","https://openalex.org/W4205302943","https://openalex.org/W2561132942","https://openalex.org/W1495042958","https://openalex.org/W3155418658","https://openalex.org/W4243199227"],"abstract_inverted_index":{"The":[0,150,241],"proliferation":[1],"of":[2,15,40,49,79,109,147,175,294],"deep":[3],"learning-based":[4],"machine":[5,22,36],"vision":[6,37],"applications":[7],"has":[8,257],"given":[9],"rise":[10],"to":[11,58,81,114,203,265],"a":[12,76,116,128,154,158,200,205,214],"new":[13],"type":[14],"compression,":[16],"so":[17,163],"called":[18],"video":[19,28,69],"coding":[20,29,70],"for":[21,35,97,101,239,277],"(VCM).":[23],"VCM":[24],"differs":[25],"from":[26,54],"traditional":[27],"in":[30,167,192],"that":[31,66,134,164,244,283],"it":[32,88,112],"is":[33,89,171,219,226,237,281],"optimized":[34],"performance":[38,290],"instead":[39],"human":[41],"visual":[42],"quality.":[43],"In":[44],"the":[45,67,105,137,141,145,165,168,178,182,187,211,223,230,234,295],"feature":[46,61,85,131,160,202,225,297],"compression":[47,62,132,183],"track":[48],"MPEG-VCM,":[50],"multi-scale":[51,130,159,169],"features":[52,99,143,170],"extracted":[53,98,142],"images":[55],"are":[56],"subject":[57],"compression.":[59],"Recent":[60],"works":[63],"have":[64],"demonstrated":[65],"versatile":[68],"(VVC)":[71],"standard-based":[72],"approach":[73],"can":[74,286],"achieve":[75],"BD-rate":[77,254],"reduction":[78,255],"up":[80],"96%":[82],"against":[83],"MPEG-VCM":[84],"anchor.":[86],"However,":[87],"still":[90],"sub-optimal":[91],"as":[92],"VVC":[93,110],"was":[94],"not":[95],"designed":[96],"but":[100],"natural":[102],"images.":[103],"Moreover,":[104],"high":[106],"encoding":[107,190,275],"complexity":[108],"makes":[111],"difficult":[113],"design":[115,146],"lightweight":[117,148],"encoder":[118],"without":[119],"sacrificing":[120],"performance.":[121],"To":[122],"address":[123],"these":[124],"challenges,":[125],"we":[126,185],"propose":[127],"novel":[129],"method":[133],"enables":[135],"both":[136],"end-to-end":[138],"optimization":[139],"on":[140],"and":[144,181,189,208,228,256],"encoders.":[149],"proposed":[151],"model":[152,197,246,285],"combines":[153],"learnable":[155],"compressor":[156],"with":[157,213,291],"fusion":[161,179,188],"network":[162,180],"redundancy":[166],"effectively":[172],"removed.":[173],"Instead":[174],"simply":[176],"cascading":[177],"network,":[184],"integrate":[186],"processes":[191],"an":[193],"interleaved":[194],"way.":[195],"Our":[196],"first":[198],"encodes":[199],"larger-scale":[201],"obtain":[204],"latent":[206,212,232],"representation":[207],"then":[209,229],"fuses":[210],"smaller-scale":[215],"feature.":[216],"This":[217],"process":[218],"successively":[220],"performed":[221],"until":[222],"smallest-scale":[224],"fused":[227],"encoded":[231],"at":[233,251],"final":[235],"stage":[236],"entropy-coded":[238],"transmission.":[240],"results":[242],"show":[243],"our":[245,284],"outperforms":[247],"previous":[248],"approaches":[249],"by":[250],"least":[252],"52%":[253],"<inline-formula":[258,266],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[259,267],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">":[260,268],"<tex-math":[261,269],"notation=\"LaTeX\">$\\times":[262,270],"5$":[263],"</tex-math></inline-formula>":[264,272],"27$":[271],"times":[273],"less":[274],"time":[276],"object":[278],"detection.":[279],"It":[280],"noteworthy":[282],"attain":[287],"near-lossless":[288],"task":[289],"only":[292],"0.002-0.003%":[293],"uncompressed":[296],"data":[298],"size.":[299]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
