{"id":"https://openalex.org/W4316660599","doi":"https://doi.org/10.1109/vcip56404.2022.10008806","title":"Hierarchical Reinforcement Learning Based Video Semantic Coding for Segmentation","display_name":"Hierarchical Reinforcement Learning Based Video Semantic Coding for Segmentation","publication_year":2022,"publication_date":"2022-12-13","ids":{"openalex":"https://openalex.org/W4316660599","doi":"https://doi.org/10.1109/vcip56404.2022.10008806"},"language":"en","primary_location":{"id":"doi:10.1109/vcip56404.2022.10008806","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/vcip56404.2022.10008806","pdf_url":null,"source":{"id":"https://openalex.org/S4363608486","display_name":"2022 IEEE International Conference on Visual Communications and Image Processing (VCIP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Visual Communications and Image Processing (VCIP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5064860356","display_name":"Guangqi Xie","orcid":"https://orcid.org/0000-0002-0292-1626"},"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":"Guangqi Xie","raw_affiliation_strings":["Unviersity of Science and Technology of China,Hefei,China","Unviersity of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Unviersity of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"Unviersity of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100353783","display_name":"Xin Li","orcid":"https://orcid.org/0000-0002-0144-9489"},"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":"Xin Li","raw_affiliation_strings":["Unviersity of Science and Technology of China,Hefei,China","Unviersity of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Unviersity of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"Unviersity of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022498073","display_name":"Shiqi Lin","orcid":"https://orcid.org/0000-0001-7388-8651"},"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":"Shiqi Lin","raw_affiliation_strings":["Unviersity of Science and Technology of China,Hefei,China","Unviersity of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Unviersity of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"Unviersity of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"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":["Unviersity of Science and Technology of China,Hefei,China","Unviersity of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Unviersity of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"Unviersity of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100425726","display_name":"Li Zhang","orcid":"https://orcid.org/0000-0003-2118-4876"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li Zhang","raw_affiliation_strings":["ByteDance Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100323986","display_name":"Kai Zhang","orcid":"https://orcid.org/0000-0002-6627-0009"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kai Zhang","raw_affiliation_strings":["ByteDance Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Inc","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100387803","display_name":"Yue Li","orcid":"https://orcid.org/0000-0002-5624-7235"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yue Li","raw_affiliation_strings":["ByteDance Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Inc","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T10741","display_name":"Video Coding and Compression Technologies","score":0.9991999864578247,"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":0.9991999864578247,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9991000294685364,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9988999962806702,"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":0.841905415058136},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6400718092918396},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.5183461904525757},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.5069335103034973},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5068731904029846},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.49848341941833496},{"id":"https://openalex.org/keywords/video-compression-picture-types","display_name":"Video compression picture types","score":0.49195191264152527},{"id":"https://openalex.org/keywords/semantic-compression","display_name":"Semantic compression","score":0.4869750440120697},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.467746764421463},{"id":"https://openalex.org/keywords/motion-compensation","display_name":"Motion compensation","score":0.41242894530296326},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.41011661291122437},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3749055862426758},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32765740156173706},{"id":"https://openalex.org/keywords/semantic-technology","display_name":"Semantic technology","score":0.3208838701248169},{"id":"https://openalex.org/keywords/semantic-computing","display_name":"Semantic computing","score":0.29667437076568604},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.22873422503471375},{"id":"https://openalex.org/keywords/video-processing","display_name":"Video processing","score":0.19924181699752808},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.10955330729484558},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.07434210181236267}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.841905415058136},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6400718092918396},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.5183461904525757},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5069335103034973},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5068731904029846},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.49848341941833496},{"id":"https://openalex.org/C106030495","wikidata":"https://www.wikidata.org/wiki/Q1797012","display_name":"Video compression picture types","level":4,"score":0.49195191264152527},{"id":"https://openalex.org/C202708506","wikidata":"https://www.wikidata.org/wiki/Q7449050","display_name":"Semantic compression","level":5,"score":0.4869750440120697},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.467746764421463},{"id":"https://openalex.org/C128840427","wikidata":"https://www.wikidata.org/wiki/Q1302174","display_name":"Motion compensation","level":2,"score":0.41242894530296326},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.41011661291122437},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3749055862426758},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32765740156173706},{"id":"https://openalex.org/C6881194","wikidata":"https://www.wikidata.org/wiki/Q7449091","display_name":"Semantic technology","level":4,"score":0.3208838701248169},{"id":"https://openalex.org/C511149849","wikidata":"https://www.wikidata.org/wiki/Q7449051","display_name":"Semantic computing","level":3,"score":0.29667437076568604},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.22873422503471375},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.19924181699752808},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.10955330729484558},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.07434210181236267},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/vcip56404.2022.10008806","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/vcip56404.2022.10008806","pdf_url":null,"source":{"id":"https://openalex.org/S4363608486","display_name":"2022 IEEE International Conference on Visual Communications and Image Processing (VCIP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Visual Communications and Image Processing (VCIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.6800000071525574,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G1080581378","display_name":null,"funder_award_id":"U1908209,62021001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1586809628","display_name":null,"funder_award_id":"2018AAA0101400","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program 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/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1928419358","https://openalex.org/W2040903332","https://openalex.org/W2140199336","https://openalex.org/W2146395539","https://openalex.org/W2204750386","https://openalex.org/W2249544981","https://openalex.org/W2335901184","https://openalex.org/W2470139095","https://openalex.org/W2511584835","https://openalex.org/W2540658878","https://openalex.org/W2564998703","https://openalex.org/W2623587439","https://openalex.org/W2755841480","https://openalex.org/W2793361125","https://openalex.org/W2801519264","https://openalex.org/W2809714054","https://openalex.org/W2885976210","https://openalex.org/W2898044248","https://openalex.org/W2916743882","https://openalex.org/W2962785568","https://openalex.org/W2963253279","https://openalex.org/W2963566548","https://openalex.org/W2963653352","https://openalex.org/W2964043796","https://openalex.org/W2997987796","https://openalex.org/W3000026832","https://openalex.org/W3021895009","https://openalex.org/W3035548386","https://openalex.org/W3091252764","https://openalex.org/W3091566619","https://openalex.org/W3100935401","https://openalex.org/W3127131334","https://openalex.org/W3174001468","https://openalex.org/W3175317007","https://openalex.org/W3183673520","https://openalex.org/W3202918664","https://openalex.org/W3207351130","https://openalex.org/W4292787477","https://openalex.org/W4320901380","https://openalex.org/W6692846177"],"related_works":["https://openalex.org/W2187171999","https://openalex.org/W3134365128","https://openalex.org/W2624542985","https://openalex.org/W2359259132","https://openalex.org/W858433989","https://openalex.org/W4220697622","https://openalex.org/W2354561560","https://openalex.org/W4387489691","https://openalex.org/W2133831373","https://openalex.org/W2156467700"],"abstract_inverted_index":{"The":[0],"rapid":[1],"development":[2],"of":[3,122,153,162,172,177,185],"intelligent":[4],"tasks,":[5],"e.g.,":[6],"segmentation,":[7],"detection,":[8],"and":[9,86,101,133,140,155,193],"classification,":[10],"etc,":[11],"has":[12,77],"brought":[13],"an":[14,53],"urgent":[15],"need":[16],"for":[17,147,189,202,231],"semantic":[18,31,41,70,75,99,124,164,191,233],"compression,":[19],"which":[20],"aims":[21],"to":[22,37,67,97,116],"reduce":[23],"the":[24,29,40,44,73,103,118,128,143,151,160,170,183,236],"compression":[25,76,87,100],"cost":[26],"while":[27],"maintaining":[28],"original":[30],"information.":[32],"However,":[33],"it":[34],"is":[35],"impractical":[36],"directly":[38],"integrate":[39],"metric":[42],"into":[43,131],"traditional":[45],"codecs":[46],"since":[47,81,159],"they":[48],"cannot":[49],"be":[50],"optimized":[51],"in":[52,136,174],"end-to-end":[54],"manner.":[55],"To":[56],"solve":[57],"this":[58,90],"problem,":[59],"some":[60],"pioneering":[61],"works":[62],"have":[63,205],"applied":[64],"reinforcement":[65],"learning":[66],"implement":[68],"image-wise":[69],"compression.":[71],"Nevertheless,":[72],"video":[74,98,123,163,190,210,232],"not":[78],"been":[79],"explored":[80],"its":[82],"complex":[83,119],"reference":[84,215],"architectures":[85],"modes.":[88],"In":[89],"paper,":[91],"we":[92,126,180],"take":[93],"a":[94,137,175,195],"step":[95],"forward":[96],"propose":[102],"Hierarchical":[104],"Reinforcement":[105],"Learning":[106],"based":[107],"task-driven":[108],"Video":[109],"Semantic":[110],"Coding,":[111],"named":[112],"as":[113],"HRLVSC.":[114],"Specifically,":[115],"simplify":[117],"mode":[120,145,187,199],"decision":[121],"coding,":[125,192],"divided":[127],"action":[129],"space":[130],"frame-level":[132,154],"CTU-level":[134,156],"spaces":[135],"hierarchical":[138],"manner,":[139],"then":[141],"explore":[142],"best":[144],"selection":[146],"them":[148],"progressively":[149],"with":[150,169,213],"cooperation":[152],"agents.":[157],"Moreover,":[158],"modes":[161],"coding":[165,234],"will":[166],"exponentially":[167],"increase":[168],"number":[171],"frames":[173],"Group":[176],"Pictures":[178],"(GOP),":[179],"carefully":[181],"investigate":[182],"effects":[184],"different":[186],"selections":[188],"design":[194],"simple":[196],"but":[197],"effective":[198],"simplification":[200],"strategy":[201],"it.":[203],"We":[204],"validated":[206],"our":[207,223],"HRLVSC":[208,224],"on":[209],"segmentation":[211],"task":[212],"HEVC":[214],"software":[216],"HM16.19.":[217],"Extensive":[218],"experimental":[219],"results":[220],"demonstrated":[221],"that":[222],"can":[225],"achieve":[226],"over":[227],"39%":[228],"BD-rate":[229],"saving":[230],"under":[235],"Low":[237],"Delay":[238],"P":[239],"configuration.":[240]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}