{"id":"https://openalex.org/W4391974577","doi":"https://doi.org/10.1109/tpami.2024.3367293","title":"Video Coding for Machines: Compact Visual Representation Compression for Intelligent Collaborative Analytics","display_name":"Video Coding for Machines: Compact Visual Representation Compression for Intelligent Collaborative Analytics","publication_year":2024,"publication_date":"2024-02-20","ids":{"openalex":"https://openalex.org/W4391974577","doi":"https://doi.org/10.1109/tpami.2024.3367293","pmid":"https://pubmed.ncbi.nlm.nih.gov/38376966"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2024.3367293","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3367293","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5070884682","display_name":"Wenhan Yang","orcid":"https://orcid.org/0000-0002-1692-0069"},"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"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhan Yang","raw_affiliation_strings":["Peking University, Beijing, China","Peng Cheng Laboratory, Shenzhen, Guangdong Province, China"],"raw_orcid":"https://orcid.org/0000-0002-1692-0069","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, Guangdong Province, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028420385","display_name":"Haofeng Huang","orcid":"https://orcid.org/0000-0002-1480-7388"},"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":"Haofeng Huang","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1480-7388","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087570320","display_name":"Yueyu Hu","orcid":"https://orcid.org/0000-0003-4919-4515"},"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":"Yueyu Hu","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4919-4515","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024879728","display_name":"Ling\u2010Yu Duan","orcid":"https://orcid.org/0000-0002-4491-2023"},"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"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ling-Yu Duan","raw_affiliation_strings":["National Engineering Research Center of Visual Technology, School of Computer Science, Peking University, Beijing, China","Peng Cheng Laboratory, Shenzhen, Guangdong Province, China"],"raw_orcid":"https://orcid.org/0000-0002-4491-2023","affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Visual Technology, School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, Guangdong Province, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100761525","display_name":"Jiaying Liu","orcid":"https://orcid.org/0000-0002-0468-9576"},"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":"Jiaying Liu","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0468-9576","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":10.1865,"has_fulltext":false,"cited_by_count":48,"citation_normalized_percentile":{"value":0.99068577,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"46","issue":"7","first_page":"5174","last_page":"5191"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10741","display_name":"Video Coding and Compression Technologies","score":0.9987000226974487,"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":0.9987000226974487,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9986000061035156,"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":0.9980999827384949,"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":0.7610223293304443},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.5853469967842102},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.5462340116500854},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.5395772457122803},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5323361158370972},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4882984161376953},{"id":"https://openalex.org/keywords/visual-analytics","display_name":"Visual analytics","score":0.4867298901081085},{"id":"https://openalex.org/keywords/predictive-coding","display_name":"Predictive coding","score":0.48037442564964294},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4496753513813019},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3830716013908386},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.34009790420532227},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.33731287717819214},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.22765490412712097}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7610223293304443},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5853469967842102},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.5462340116500854},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.5395772457122803},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5323361158370972},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4882984161376953},{"id":"https://openalex.org/C59732488","wikidata":"https://www.wikidata.org/wiki/Q2528440","display_name":"Visual analytics","level":3,"score":0.4867298901081085},{"id":"https://openalex.org/C2778061373","wikidata":"https://www.wikidata.org/wiki/Q1315146","display_name":"Predictive coding","level":3,"score":0.48037442564964294},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4496753513813019},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3830716013908386},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34009790420532227},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.33731287717819214},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.22765490412712097},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2024.3367293","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3367293","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:38376966","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38376966","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3833898155","display_name":null,"funder_award_id":"62088102","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3940598769","display_name":null,"funder_award_id":"62332010","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320330032","display_name":"Ng Teng Fong Charitable Foundation","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":73,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W1861492603","https://openalex.org/W2056061164","https://openalex.org/W2086335247","https://openalex.org/W2140199336","https://openalex.org/W2146395539","https://openalex.org/W2194775991","https://openalex.org/W2478708596","https://openalex.org/W2785562966","https://openalex.org/W2939317989","https://openalex.org/W2962793481","https://openalex.org/W2962847516","https://openalex.org/W2963037989","https://openalex.org/W2964185501","https://openalex.org/W2970003075","https://openalex.org/W2970004826","https://openalex.org/W2970339328","https://openalex.org/W2971011627","https://openalex.org/W2975749976","https://openalex.org/W2981749440","https://openalex.org/W3000419664","https://openalex.org/W3012708638","https://openalex.org/W3015246788","https://openalex.org/W3015540635","https://openalex.org/W3015673133","https://openalex.org/W3015735582","https://openalex.org/W3034333985","https://openalex.org/W3034383034","https://openalex.org/W3034469748","https://openalex.org/W3035205678","https://openalex.org/W3035384921","https://openalex.org/W3035564946","https://openalex.org/W3035574324","https://openalex.org/W3035685239","https://openalex.org/W3082007109","https://openalex.org/W3082548248","https://openalex.org/W3085046840","https://openalex.org/W3086333990","https://openalex.org/W3088343230","https://openalex.org/W3089768884","https://openalex.org/W3090094956","https://openalex.org/W3090392341","https://openalex.org/W3090672847","https://openalex.org/W3090720321","https://openalex.org/W3102451820","https://openalex.org/W3102550237","https://openalex.org/W3109340983","https://openalex.org/W3117951133","https://openalex.org/W3130131412","https://openalex.org/W3140060010","https://openalex.org/W3160073521","https://openalex.org/W3160555381","https://openalex.org/W3160673571","https://openalex.org/W3160882100","https://openalex.org/W3162893611","https://openalex.org/W3163045957","https://openalex.org/W3166030101","https://openalex.org/W3169876831","https://openalex.org/W3171673455","https://openalex.org/W3172615411","https://openalex.org/W3172982968","https://openalex.org/W3175359120","https://openalex.org/W3176103974","https://openalex.org/W3180770160","https://openalex.org/W3183629544","https://openalex.org/W3186910762","https://openalex.org/W3194896438","https://openalex.org/W3195748956","https://openalex.org/W4288092016","https://openalex.org/W6637373629","https://openalex.org/W6684191040","https://openalex.org/W6756663807","https://openalex.org/W6767856145"],"related_works":["https://openalex.org/W2955990109","https://openalex.org/W4311138500","https://openalex.org/W2017266518","https://openalex.org/W2148525144","https://openalex.org/W2744288354","https://openalex.org/W2584189775","https://openalex.org/W2186032312","https://openalex.org/W1758089587","https://openalex.org/W2062873527","https://openalex.org/W3022978462"],"abstract_inverted_index":{"As":[0,287],"an":[1,27],"emerging":[2],"research":[3,30],"practice":[4],"leveraging":[5],"recent":[6],"advanced":[7],"AI":[8],"techniques,":[9],"e.g.":[10],"deep":[11,65],"models":[12],"based":[13,83],"prediction":[14],"and":[15,35,38,43,55,68,81,87,99,117,155,172,235,264],"generation,":[16],"Video":[17],"Coding":[18],"for":[19,191,208],"Machines":[20],"(VCM)":[21],"is":[22,107,135,219,279,296],"committed":[23],"to":[24,26,40,142,175,196,240,251,281,298],"bridging":[25],"extent":[28],"separate":[29],"tracks":[31],"of":[32,50,64,92,102,125,146,167,179,200,214,267,314,317],"video/image":[33],"compression":[34,71,190,218,301],"feature":[36,66,115,300],"compression,":[37],"attempts":[39],"optimize":[41],"compactness":[42],"efficiency":[44,302],"jointly":[45,244],"from":[46,122,205,262],"a":[47,95,161,177,186,265,276],"unified":[48],"perspective":[49,213],"high":[51],"accuracy":[52],"machine":[53,118,154,229,268],"vision":[54,119,126,157,230,269],"full":[56],"fidelity":[57],"human":[58,156],"vision.":[59],"With":[60],"the":[61,100,144,165,192,198,225,253,283,305,315],"rapid":[62],"advances":[63],"representation":[67,148],"visual":[69,180,188,202,209],"data":[70],"in":[72,74,149,164,223,289],"mind,":[73],"this":[75,292],"paper,":[76],"we":[77,184,238],"summarize":[78],"VCM":[79,93],"methodology":[80],"philosophy":[82],"on":[84],"existing":[85,139],"academia":[86],"industrial":[88],"efforts.":[89],"The":[90],"development":[91],"follows":[94],"general":[96],"rate-distortion":[97],"optimization,":[98],"categorization":[101],"key":[103],"modules":[104],"or":[105],"techniques":[106],"established":[108],"including":[109],"feature-assisted":[110],"coding,":[111,113],"scalable":[112,147],"intermediate":[114],"compression/optimization,":[116],"targeted":[120],"codec,":[121],"broader":[123],"perspectives":[124],"tasks,":[127,158],"analytics":[128,193],"resources,":[129],"etc.":[130],"From":[131],"previous":[132],"works,":[133],"it":[134],"demonstrated":[136,288],"that,":[137],"although":[138],"works":[140],"attempt":[141],"reveal":[143],"nature":[145],"bits":[150],"when":[151],"dealing":[152],"with":[153],"there":[159],"remains":[160],"rare":[162],"study":[163],"generality":[166],"low":[168,246],"bit":[169,247],"rate":[170],"representation,":[171],"accordingly":[173],"how":[174],"support":[176,241],"variety":[178,266],"analytic":[181],"tasks.":[182,323],"Therefore,":[183],"investigate":[185],"novel":[187],"information":[189],"taxonomy":[194],"problem":[195],"strengthen":[197],"capability":[199],"compact":[201,319],"representations":[203],"extracted":[204,261],"multiple":[206,242],"tasks":[207,231,243],"analytics.":[210],"A":[211],"new":[212,293],"task":[215],"relationships":[216],"versus":[217],"revisited.":[220],"By":[221],"keeping":[222],"mind":[224],"transferability":[226],"among":[227,321],"different":[228,322],"(e.g.":[232,271],"high-level":[233],"semantic":[234],"mid-level":[236],"geometry-related),":[237],"aim":[239],"at":[245],"rates.":[248],"In":[249],"particular,":[250],"narrow":[252],"dimensionality":[254],"gap":[255],"between":[256],"neural":[257,284],"network":[258],"generated":[259],"features":[260,320],"pixels":[263],"features/labels":[270],"scene":[272],"class,":[273],"segmentation":[274],"labels),":[275],"codebook":[277],"hyperprior":[278,294],"designed":[280],"compress":[282],"network-generated":[285],"features.":[286],"our":[290],"experiments,":[291],"model":[295],"expected":[297],"improve":[299],"by":[303],"estimating":[304],"signal":[306],"entropy":[307],"more":[308],"accurately,":[309],"which":[310],"enables":[311],"further":[312],"investigation":[313],"granularity":[316],"abstracting":[318]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":23},{"year":2024,"cited_by_count":16}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}