{"id":"https://openalex.org/W4317555285","doi":"https://doi.org/10.1109/pcs56426.2022.10018030","title":"Generative Video Compression with a Transformer-Based Discriminator","display_name":"Generative Video Compression with a Transformer-Based Discriminator","publication_year":2022,"publication_date":"2022-12-07","ids":{"openalex":"https://openalex.org/W4317555285","doi":"https://doi.org/10.1109/pcs56426.2022.10018030"},"language":"en","primary_location":{"id":"doi:10.1109/pcs56426.2022.10018030","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pcs56426.2022.10018030","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 Picture Coding Symposium (PCS)","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/A5103093056","display_name":"Pengli Du","orcid":"https://orcid.org/0009-0008-9331-1479"},"institutions":[{"id":"https://openalex.org/I16269868","display_name":"Santa Clara University","ror":"https://ror.org/03ypqe447","country_code":"US","type":"education","lineage":["https://openalex.org/I16269868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pengli Du","raw_affiliation_strings":["Santa Clara University,Department of Computer Science and Engineering,Santa Clara,CA,USA,95053"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Santa Clara University,Department of Computer Science and Engineering,Santa Clara,CA,USA,95053","institution_ids":["https://openalex.org/I16269868"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100414451","display_name":"Ying Liu","orcid":"https://orcid.org/0000-0003-3380-4243"},"institutions":[{"id":"https://openalex.org/I16269868","display_name":"Santa Clara University","ror":"https://ror.org/03ypqe447","country_code":"US","type":"education","lineage":["https://openalex.org/I16269868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ying Liu","raw_affiliation_strings":["Santa Clara University,Department of Computer Science and Engineering,Santa Clara,CA,USA,95053"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Santa Clara University,Department of Computer Science and Engineering,Santa Clara,CA,USA,95053","institution_ids":["https://openalex.org/I16269868"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018686979","display_name":"Nam Ling","orcid":"https://orcid.org/0000-0002-5741-7937"},"institutions":[{"id":"https://openalex.org/I16269868","display_name":"Santa Clara University","ror":"https://ror.org/03ypqe447","country_code":"US","type":"education","lineage":["https://openalex.org/I16269868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nam Ling","raw_affiliation_strings":["Santa Clara University,Department of Computer Science and Engineering,Santa Clara,CA,USA,95053"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Santa Clara University,Department of Computer Science and Engineering,Santa Clara,CA,USA,95053","institution_ids":["https://openalex.org/I16269868"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071767061","display_name":"Yongxiong Ren","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yongxiong Ren","raw_affiliation_strings":["Kwai Inc.,Palo Alto,CA,USA,94306"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kwai Inc.,Palo Alto,CA,USA,94306","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101421899","display_name":"Lingzhi Liu","orcid":"https://orcid.org/0000-0002-8596-5199"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lingzhi Liu","raw_affiliation_strings":["Kwai Inc.,Palo Alto,CA,USA,94306"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kwai Inc.,Palo Alto,CA,USA,94306","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3046,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.56483861,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"349","last_page":"353"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11105","display_name":"Advanced Image Processing Techniques","score":0.9997000098228455,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9997000098228455,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9993000030517578,"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/T10741","display_name":"Video Coding and Compression Technologies","score":0.9980999827384949,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.8853244781494141},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.811530351638794},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6509385108947754},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5958607196807861},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.5932652950286865},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5590408444404602},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.4937768876552582},{"id":"https://openalex.org/keywords/video-compression-picture-types","display_name":"Video compression picture types","score":0.4854024350643158},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.4115387797355652},{"id":"https://openalex.org/keywords/generative-adversarial-network","display_name":"Generative adversarial network","score":0.4101719856262207},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3963853120803833},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.33511069416999817},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32751139998435974},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.2760912775993347},{"id":"https://openalex.org/keywords/video-processing","display_name":"Video processing","score":0.1876973807811737},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09205123782157898},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07698136568069458},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06159263849258423}],"concepts":[{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.8853244781494141},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.811530351638794},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6509385108947754},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5958607196807861},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.5932652950286865},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5590408444404602},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.4937768876552582},{"id":"https://openalex.org/C106030495","wikidata":"https://www.wikidata.org/wiki/Q1797012","display_name":"Video compression picture types","level":4,"score":0.4854024350643158},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.4115387797355652},{"id":"https://openalex.org/C2988773926","wikidata":"https://www.wikidata.org/wiki/Q25104379","display_name":"Generative adversarial network","level":3,"score":0.4101719856262207},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3963853120803833},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.33511069416999817},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32751139998435974},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.2760912775993347},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.1876973807811737},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09205123782157898},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07698136568069458},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06159263849258423},{"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},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/pcs56426.2022.10018030","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pcs56426.2022.10018030","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 Picture Coding Symposium (PCS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2146395539","https://openalex.org/W2548527721","https://openalex.org/W2769654144","https://openalex.org/W2785562966","https://openalex.org/W2950689937","https://openalex.org/W2963189365","https://openalex.org/W2969260367","https://openalex.org/W2979990382","https://openalex.org/W2987947587","https://openalex.org/W3034802763","https://openalex.org/W3038130890","https://openalex.org/W3098284407","https://openalex.org/W3102015846","https://openalex.org/W3153143402","https://openalex.org/W3160589897","https://openalex.org/W3202918664","https://openalex.org/W4281772919","https://openalex.org/W4285201443","https://openalex.org/W4285604424","https://openalex.org/W4385245566","https://openalex.org/W6765779288","https://openalex.org/W6769015554","https://openalex.org/W6780365925"],"related_works":["https://openalex.org/W3005996785","https://openalex.org/W3156291593","https://openalex.org/W3024390022","https://openalex.org/W4313479464","https://openalex.org/W3020253784","https://openalex.org/W3119931323","https://openalex.org/W4280544492","https://openalex.org/W3197610371","https://openalex.org/W4301431435","https://openalex.org/W2975432854"],"abstract_inverted_index":{"Deep":[0],"learning":[1],"has":[2],"been":[3],"successfully":[4],"applied":[5],"to":[6,54,66,103],"image":[7],"and":[8,26,79,106],"video":[9,38,52,108],"compression.":[10],"Specifically,":[11],"generative":[12,37],"adversarial":[13,56],"network":[14],"(GAN)":[15],"can":[16],"compress":[17],"images":[18],"at":[19,97],"low":[20,99],"bit":[21,100],"rates":[22],"with":[23,42],"sharp":[24],"details":[25],"high":[27],"perceptual":[28,81],"quality.":[29],"In":[30],"this":[31],"work,":[32],"we":[33],"propose":[34],"a":[35,43,63,72,75,80],"novel":[36],"compression":[39],"(GVC)":[40],"model":[41,61,93],"transformer-based":[44],"discriminator":[45],"(TD),":[46],"which":[47,70],"learns":[48],"non-local":[49],"correlations":[50],"within":[51],"frames":[53],"improve":[55],"training.":[57],"Besides,":[58],"our":[59],"GVC":[60,92],"incorporates":[62],"new":[64],"loss":[65],"train":[67],"the":[68,90],"generator,":[69],"combines":[71],"base":[73],"loss,":[74,78],"discriminator-dependent":[76],"feature":[77],"loss.":[82],"Experiments":[83],"on":[84],"HEVC":[85],"test":[86],"sequences":[87],"demonstrate":[88],"that":[89],"proposed":[91],"provides":[94],"superior":[95],"performance":[96],"extremely":[98],"rates,":[101],"compared":[102],"existing":[104],"learned":[105],"traditional":[107],"coding":[109],"schemes.":[110]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}