{"id":"https://openalex.org/W4308235948","doi":"https://doi.org/10.1109/icip46576.2022.9897830","title":"Learning-Based End-to-End Video Compression with Spatial-Temporal Adaptation","display_name":"Learning-Based End-to-End Video Compression with Spatial-Temporal Adaptation","publication_year":2022,"publication_date":"2022-10-16","ids":{"openalex":"https://openalex.org/W4308235948","doi":"https://doi.org/10.1109/icip46576.2022.9897830"},"language":"en","primary_location":{"id":"doi:10.1109/icip46576.2022.9897830","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip46576.2022.9897830","pdf_url":null,"source":{"id":"https://openalex.org/S4363607719","display_name":"2022 IEEE International Conference on Image Processing (ICIP)","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 Image Processing (ICIP)","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/A5102714187","display_name":"Zhaobin Zhang","orcid":"https://orcid.org/0000-0001-5961-5163"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhaobin 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/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":[]}]},{"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":"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":"last","author":{"id":"https://openalex.org/A5100297578","display_name":"Yuwen He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuwen He","raw_affiliation_strings":["Bytedance Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bytedance Inc","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1846,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.36941274,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"2821","last_page":"2825"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10741","display_name":"Video Coding and Compression Technologies","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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":0.9983999729156494,"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":0.8122114539146423},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.5686504244804382},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5515095591545105},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5294677019119263},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5156006217002869},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5133861303329468},{"id":"https://openalex.org/keywords/key-frame","display_name":"Key frame","score":0.5106843113899231},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.4847075939178467},{"id":"https://openalex.org/keywords/video-compression-picture-types","display_name":"Video compression picture types","score":0.46668916940689087},{"id":"https://openalex.org/keywords/reference-frame","display_name":"Reference frame","score":0.43691059947013855},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4291674494743347},{"id":"https://openalex.org/keywords/data-compression-ratio","display_name":"Data compression ratio","score":0.41039302945137024},{"id":"https://openalex.org/keywords/image-compression","display_name":"Image compression","score":0.35164886713027954},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.3446982502937317},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.3364332318305969},{"id":"https://openalex.org/keywords/video-processing","display_name":"Video processing","score":0.25092947483062744},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.21514487266540527},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.12984123826026917},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.09670701622962952},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07866683602333069},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.07546833157539368}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8122114539146423},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.5686504244804382},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5515095591545105},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5294677019119263},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5156006217002869},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5133861303329468},{"id":"https://openalex.org/C2780139006","wikidata":"https://www.wikidata.org/wiki/Q1493902","display_name":"Key frame","level":3,"score":0.5106843113899231},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.4847075939178467},{"id":"https://openalex.org/C106030495","wikidata":"https://www.wikidata.org/wiki/Q1797012","display_name":"Video compression picture types","level":4,"score":0.46668916940689087},{"id":"https://openalex.org/C172849965","wikidata":"https://www.wikidata.org/wiki/Q3148875","display_name":"Reference frame","level":3,"score":0.43691059947013855},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4291674494743347},{"id":"https://openalex.org/C94835093","wikidata":"https://www.wikidata.org/wiki/Q3113333","display_name":"Data compression ratio","level":5,"score":0.41039302945137024},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.35164886713027954},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.3446982502937317},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3364332318305969},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.25092947483062744},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.21514487266540527},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.12984123826026917},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.09670701622962952},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07866683602333069},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.07546833157539368},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip46576.2022.9897830","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip46576.2022.9897830","pdf_url":null,"source":{"id":"https://openalex.org/S4363607719","display_name":"2022 IEEE International Conference on Image Processing (ICIP)","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 Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W2140199336","https://openalex.org/W2146395539","https://openalex.org/W2552465432","https://openalex.org/W2785562966","https://openalex.org/W2948654165","https://openalex.org/W2963189365","https://openalex.org/W2963782415","https://openalex.org/W2964098744","https://openalex.org/W2964251418","https://openalex.org/W2969260367","https://openalex.org/W2987947587","https://openalex.org/W2992051623","https://openalex.org/W3018065762","https://openalex.org/W3020741905","https://openalex.org/W3034469748","https://openalex.org/W3034802763","https://openalex.org/W3035195755","https://openalex.org/W3097448661","https://openalex.org/W3098284407","https://openalex.org/W3108139283","https://openalex.org/W3110286842","https://openalex.org/W3117007398","https://openalex.org/W4242177911","https://openalex.org/W4287605633"],"related_works":["https://openalex.org/W1995589563","https://openalex.org/W3123991145","https://openalex.org/W2782365651","https://openalex.org/W2100570504","https://openalex.org/W4205899500","https://openalex.org/W2170532137","https://openalex.org/W2379860320","https://openalex.org/W4386870095","https://openalex.org/W2491286475","https://openalex.org/W4382053412"],"abstract_inverted_index":{"The":[0,136,146,156],"learning-based":[1,68,161],"end-to-end":[2,69,141],"video":[3,56,162,177],"compression":[4,40,73,92,163],"exhibits":[5],"a":[6,15,52,67,95,166],"fast":[7],"development":[8],"with":[9,142],"continuous":[10],"improvements.":[11],"In":[12],"previous":[13],"works,":[14],"key":[16,63,81,90,96,110],"frame":[17,91,111],"in":[18,55,179],"random-access":[19],"scenarios":[20],"is":[21,48,112,131,139],"typically":[22],"compressed":[23],"by":[24,34,165],"an":[25,88,102,106],"image":[26,39,103],"compressor,":[27],"and":[28,105,127,169,183],"the":[29,44,80,117,123,128,134,144,150,153],"remaining":[30],"frames":[31],"are":[32],"reconstructed":[33],"interpolations.":[35],"But":[36],"solely":[37],"using":[38],"fails":[41],"to":[42,50,75,115,122,133,174],"leverage":[43],"temporal":[45,60],"correlations,":[46],"which":[47],"critical":[49],"achieve":[51],"substantial":[53],"gain":[54],"compression.":[57],"To":[58],"exploit":[59],"correlations":[61],"among":[62],"frames,":[64],"we":[65,86],"introduce":[66],"spatial-temporal":[70],"adaptive":[71],"(e2e-STA)":[72],"solution":[74,119],"offer":[76],"flexible":[77],"options":[78],"for":[79],"frames.":[82],"First":[83],"of":[84,152,181],"all,":[85],"design":[87],"extrapolation-based":[89],"scheme.":[93],"Given":[94],"frame,":[97],"e2e-STA":[98],"can":[99],"switch":[100],"between":[101],"compressor":[104],"extrapolative":[107],"compressor.":[108],"A":[109],"thereby":[113],"able":[114],"select":[116],"optimal":[118,129],"adaptively":[120],"according":[121],"rate-distortion":[124],"optimization":[125],"criteria":[126],"selection":[130],"sent":[132],"decoder.":[135],"proposed":[137,154,157],"approach":[138],"optimized":[140],"all":[143],"networks.":[145],"experimental":[147],"results":[148],"validate":[149],"effectiveness":[151],"mechanism.":[155],"method":[158],"outperforms":[159],"existing":[160],"methods":[164],"noticeable":[167],"margin":[168],"provides":[170],"promising":[171],"performance":[172],"compared":[173],"traditional":[175],"benchmark":[176],"codecs":[178],"terms":[180],"PSNR":[182],"MS-SSIM.":[184]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}