{"id":"https://openalex.org/W4389290705","doi":"https://doi.org/10.1142/s021800142354023x","title":"An End-to-End Video Coding Method via Adaptive Vision Transformer","display_name":"An End-to-End Video Coding Method via Adaptive Vision Transformer","publication_year":2023,"publication_date":"2023-12-04","ids":{"openalex":"https://openalex.org/W4389290705","doi":"https://doi.org/10.1142/s021800142354023x"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1142/s021800142354023x","pdf_url":null,"source":{"id":"https://openalex.org/S41486457","display_name":"International Journal of Pattern Recognition and Artificial Intelligence","issn_l":"0218-0014","issn":["0218-0014","1793-6381"],"is_oa":false,"is_in_doaj":false,"is_indexed_in_scopus":true,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"journal-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/A5114626289","display_name":"Haoyan Yang","orcid":"https://orcid.org/0009-0002-6291-3115"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"funder","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoyan Yang","raw_affiliation_strings":["College of Computer Science, Chongqing University, Chongqing 400044, P. R. China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science, Chongqing University, Chongqing 400044, P. R. China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107556956","display_name":"Mingliang Zhou","orcid":"https://orcid.org/0000-0002-1874-3641"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"funder","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingliang Zhou","raw_affiliation_strings":["College of Computer Science, Chongqing University, Chongqing 400044, P. R. China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science, Chongqing University, Chongqing 400044, P. R. China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052276737","display_name":"Zhaowei Shang","orcid":null},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"funder","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhaowei Shang","raw_affiliation_strings":["College of Computer Science, Chongqing University, Chongqing 400044, P. R. China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science, Chongqing University, Chongqing 400044, P. R. China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033390427","display_name":"Huayan Pu","orcid":"https://orcid.org/0000-0001-9830-3955"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"funder","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huayan Pu","raw_affiliation_strings":["School of Mechanical and Vehicle Engineering, Chongqing University, Chongqing 400044, P. R. China"],"affiliations":[{"raw_affiliation_string":"School of Mechanical and Vehicle Engineering, Chongqing University, Chongqing 400044, P. R. China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016769551","display_name":"Jun Luo","orcid":"https://orcid.org/0000-0003-1314-5631"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"funder","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Luo","raw_affiliation_strings":["School of Mechanical and Vehicle Engineering, Chongqing University, Chongqing 400044, P. R. China"],"affiliations":[{"raw_affiliation_string":"School of Mechanical and Vehicle Engineering, Chongqing University, Chongqing 400044, P. R. China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028578315","display_name":"Xiaoxu Huang","orcid":"https://orcid.org/0000-0002-4635-6112"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"funder","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoxu Huang","raw_affiliation_strings":["College of Materials Science and Engineering, Chongqing University, Chongqing 400044, P. R. China"],"affiliations":[{"raw_affiliation_string":"College of Materials Science and Engineering, Chongqing University, Chongqing 400044, P. R. China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100633957","display_name":"Shilong Wang","orcid":"https://orcid.org/0000-0002-3321-027X"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"funder","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shilong Wang","raw_affiliation_strings":["School of Mechanical and Vehicle Engineering, Chongqing University, Chongqing 400044, P. R. China"],"affiliations":[{"raw_affiliation_string":"School of Mechanical and Vehicle Engineering, Chongqing University, Chongqing 400044, P. R. China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090973579","display_name":"Huajun Cao","orcid":"https://orcid.org/0000-0001-6617-0473"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"funder","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huajun Cao","raw_affiliation_strings":["School of Mechanical and Vehicle Engineering, Chongqing University, Chongqing 400044, P. R. China"],"affiliations":[{"raw_affiliation_string":"School of Mechanical and Vehicle Engineering, Chongqing University, Chongqing 400044, P. R. China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084203901","display_name":"Xuekai Wei","orcid":"https://orcid.org/0000-0002-3761-1759"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"funder","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuekai Wei","raw_affiliation_strings":["College of Computer Science, Chongqing University, Chongqing 400044, P. R. China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science, Chongqing University, Chongqing 400044, P. R. China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060560577","display_name":"Weizhi Xian","orcid":"https://orcid.org/0000-0001-5137-3542"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"funder","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weizhi Xian","raw_affiliation_strings":["Chongqing Research Institute of Harbin Institute of Technology, Harbin Institute of Technology, Chongqing 401151, P. R. China"],"affiliations":[{"raw_affiliation_string":"Chongqing Research Institute of Harbin Institute of Technology, Harbin Institute of Technology, Chongqing 401151, P. R. China","institution_ids":["https://openalex.org/I204983213"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5052276737"],"corresponding_institution_ids":["https://openalex.org/I158842170"],"apc_list":null,"apc_paid":null,"fwci":0.372,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.489224,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":65,"max":76},"biblio":{"volume":"38","issue":"01","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10741","display_name":"Video Coding and Compression Technologies","score":0.9998,"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":0.9998,"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":0.9995,"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":0.9992,"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/end-to-end-principle","display_name":"End-to-end principle","score":0.6413804}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6898811},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.67699707},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.64223135},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6413804},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5006881},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.44808167},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15528786},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13583142},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1142/s021800142354023x","pdf_url":null,"source":{"id":"https://openalex.org/S41486457","display_name":"International Journal of Pattern Recognition and Artificial Intelligence","issn_l":"0218-0014","issn":["0218-0014","1793-6381"],"is_oa":false,"is_in_doaj":false,"is_indexed_in_scopus":true,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[],"grants":[{"funder":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China","award_id":"62176027"}],"datasets":[],"versions":[],"referenced_works_count":39,"referenced_works":["https://openalex.org/W1580389772","https://openalex.org/W1995875735","https://openalex.org/W2058839502","https://openalex.org/W2086663885","https://openalex.org/W2146395539","https://openalex.org/W2246461641","https://openalex.org/W2552953142","https://openalex.org/W2559655401","https://openalex.org/W2969260367","https://openalex.org/W2981413347","https://openalex.org/W2999288662","https://openalex.org/W3018065762","https://openalex.org/W3020741905","https://openalex.org/W3031546776","https://openalex.org/W3034469748","https://openalex.org/W3034802763","https://openalex.org/W3035195755","https://openalex.org/W3038130890","https://openalex.org/W3095479355","https://openalex.org/W3096609285","https://openalex.org/W3102015846","https://openalex.org/W3108139283","https://openalex.org/W3118176575","https://openalex.org/W3138516171","https://openalex.org/W3173272744","https://openalex.org/W3195524601","https://openalex.org/W3202918664","https://openalex.org/W4214743248","https://openalex.org/W4214761665","https://openalex.org/W4223425316","https://openalex.org/W4304087061","https://openalex.org/W4312785369","https://openalex.org/W4313058111","https://openalex.org/W4321232185","https://openalex.org/W4321791037","https://openalex.org/W4385350469","https://openalex.org/W4385350883","https://openalex.org/W4386065808","https://openalex.org/W4386076489"],"related_works":["https://openalex.org/W3116076068","https://openalex.org/W2951359407","https://openalex.org/W2772917594","https://openalex.org/W2755342338","https://openalex.org/W2229312674","https://openalex.org/W2166024367","https://openalex.org/W2079911747","https://openalex.org/W2058170566","https://openalex.org/W2036807459","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Deep":[0],"learning-based":[1],"video":[2,12,25,81,130,166,194],"coding":[3,13,26,82,131,167,195],"methods":[4],"have":[5],"demonstrated":[6],"superior":[7],"performance":[8,213,235],"compared":[9,215,237],"to":[10,65,117,168,170,186,216,238],"classical":[11],"standards":[14],"in":[15,79,102],"recent":[16],"years.":[17],"The":[18,197],"vast":[19],"majority":[20],"of":[21,49,165,246],"the":[22,47,50,70,80,85,89,103,118,136,147,153,163,239,244],"existing":[23],"deep":[24],"(DVC)":[27],"networks":[28,34],"are":[29,44],"based":[30,157,161],"on":[31,146,158,162],"convolutional":[32],"neural":[33],"(CNNs),":[35],"and":[36,59,68,139,151,228],"their":[37],"main":[38],"drawback":[39],"is":[40,84,113],"that":[41,95,200],"since":[42],"CNNs":[43],"affected":[45],"by":[46,109],"size":[48],"receptive":[51],"field,":[52],"they":[53],"cannot":[54],"effectively":[55],"handle":[56],"long-range":[57],"dependencies":[58,97],"local":[60,76],"detail":[61],"recovery.":[62],"Therefore,":[63],"how":[64],"better":[66],"capture":[67],"process":[69],"overall":[71],"structure":[72],"as":[73,75,181,221],"well":[74],"texture":[77],"information":[78],"task":[83],"core":[86],"issue.":[87],"Notably,":[88],"transformer":[90,149],"employs":[91],"a":[92,142,176,233],"self-attention":[93],"mechanism":[94],"captures":[96],"between":[98],"any":[99],"two":[100],"positions":[101],"input":[104],"sequence":[105],"without":[106],"being":[107],"constrained":[108],"distance":[110],"limitations.":[111],"This":[112],"an":[114],"effective":[115],"solution":[116],"problem":[119],"described":[120],"above.":[121],"In":[122,243],"this":[123,209],"paper,":[124],"we":[125,134,174],"propose":[126],"end-to-end":[127],"transformer-based":[128],"adaptive":[129,182],"(TAVC).":[132],"First,":[133],"compress":[135],"motion":[137,154],"vector":[138],"residuals":[140],"through":[141],"compression":[143],"network":[144,156],"built":[145],"vision":[148],"(ViT)":[150],"design":[152],"compensation":[155],"ViT.":[159],"Second,":[160],"requirement":[164],"adapt":[169],"different":[171,192],"resolution":[172,193],"inputs,":[173],"introduce":[175],"position":[177,183],"encoding":[178,184],"generator":[179],"(PEG)":[180],"(APE)":[185],"maintain":[187],"its":[188],"translation":[189],"invariance":[190],"across":[191],"tasks.":[196],"experiment":[198],"shows":[199],"for":[201],"multiscale":[202],"structural":[203],"similarity":[204],"index":[205],"measurement":[206],"(MS-SSIM)":[207],"metrics,":[208,252],"method":[210],"exhibits":[211],"significant":[212],"gaps":[214],"conventional":[217],"engineering":[218],"codecs,":[219],"such":[220],"[Formula:":[222,225],"see":[223,226],"text],":[224,227],"VTM-15.2.":[229],"We":[230],"also":[231,254],"achieved":[232],"good":[234,256],"improvement":[236],"CNN-based":[240],"DVC":[241],"methods.":[242],"case":[245],"peak":[247],"signal-to-noise":[248],"ratio":[249],"(PSNR)":[250],"evaluation":[251],"TAVC":[253],"achieves":[255],"performance.":[257]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4389290705","counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-04-20T20:51:10.013196","created_date":"2023-12-04"}