{"id":"https://openalex.org/W4415540419","doi":"https://doi.org/10.1145/3746027.3755254","title":"VidIQ: Inference-Aware Neural Codecs for Quality-Enhanced, Real-Time Video Analytics","display_name":"VidIQ: Inference-Aware Neural Codecs for Quality-Enhanced, Real-Time Video Analytics","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415540419","doi":"https://doi.org/10.1145/3746027.3755254"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755254","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755254","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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/A5075138256","display_name":"Andong Zhu","orcid":"https://orcid.org/0009-0002-8233-329X"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Andong Zhu","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100394022","display_name":"Sheng Zhang","orcid":"https://orcid.org/0000-0002-6581-6399"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sheng Zhang","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073263875","display_name":"Xiaohang Shi","orcid":"https://orcid.org/0009-0002-9796-238X"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaohang Shi","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103189262","display_name":"Hesheng Sun","orcid":"https://orcid.org/0009-0005-5246-6018"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hesheng Sun","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056373751","display_name":"Yu Liang","orcid":"https://orcid.org/0000-0002-9251-4337"},"institutions":[{"id":"https://openalex.org/I152031979","display_name":"Nanjing Normal University","ror":"https://ror.org/036trcv74","country_code":"CN","type":"education","lineage":["https://openalex.org/I152031979"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Liang","raw_affiliation_strings":["Nanjing Normal University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing Normal University, Nanjing, China","institution_ids":["https://openalex.org/I152031979"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015547394","display_name":"Zhuzhong Qian","orcid":"https://orcid.org/0000-0003-1625-7575"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuzhong Qian","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103724712","display_name":"Haoye Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Zheng","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102337891","display_name":"Xiaokun Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaokun Wang","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101560987","display_name":"Ning Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ning Jiang","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5075138256"],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30748036,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12025","last_page":"12034"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11105","display_name":"Advanced Image Processing Techniques","score":1.0,"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":1.0,"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/T10688","display_name":"Image and Signal Denoising Methods","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/T10531","display_name":"Advanced Vision and Imaging","score":0.9995999932289124,"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/analytics","display_name":"Analytics","score":0.6700999736785889},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.6306999921798706},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5449000000953674},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.5145999789237976},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.5047000050544739},{"id":"https://openalex.org/keywords/deblocking-filter","display_name":"Deblocking filter","score":0.5031999945640564},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4805999994277954},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4765999913215637},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.4620000123977661}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8619999885559082},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.6700999736785889},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.6306999921798706},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5449000000953674},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.5145999789237976},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.5047000050544739},{"id":"https://openalex.org/C143184774","wikidata":"https://www.wikidata.org/wiki/Q3020846","display_name":"Deblocking filter","level":2,"score":0.5031999945640564},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4805999994277954},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4765999913215637},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.4620000123977661},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.4332999885082245},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4075999855995178},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3970000147819519},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.3774000108242035},{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.367000013589859},{"id":"https://openalex.org/C103910844","wikidata":"https://www.wikidata.org/wiki/Q2631256","display_name":"Video quality","level":3,"score":0.3528999984264374},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.34130001068115234},{"id":"https://openalex.org/C23431618","wikidata":"https://www.wikidata.org/wiki/Q1404672","display_name":"Multiview Video Coding","level":4,"score":0.32850000262260437},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.32429999113082886},{"id":"https://openalex.org/C133529210","wikidata":"https://www.wikidata.org/wiki/Q1076113","display_name":"Scalable Video Coding","level":3,"score":0.31209999322891235},{"id":"https://openalex.org/C5119721","wikidata":"https://www.wikidata.org/wiki/Q220501","display_name":"Quality of service","level":2,"score":0.3057999908924103},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.2987000048160553},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.2928999960422516},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2913999855518341},{"id":"https://openalex.org/C106030495","wikidata":"https://www.wikidata.org/wiki/Q1797012","display_name":"Video compression picture types","level":4,"score":0.2897999882698059},{"id":"https://openalex.org/C128840427","wikidata":"https://www.wikidata.org/wiki/Q1302174","display_name":"Motion compensation","level":2,"score":0.28529998660087585},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.27390000224113464},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C116537","wikidata":"https://www.wikidata.org/wiki/Q2169973","display_name":"Service provider","level":3,"score":0.25859999656677246}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755254","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755254","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1885185971","https://openalex.org/W2003771645","https://openalex.org/W2735173535","https://openalex.org/W3013529009","https://openalex.org/W3202918664","https://openalex.org/W4298127364","https://openalex.org/W4306174033","https://openalex.org/W4393404832"],"related_works":[],"abstract_inverted_index":{"Video":[0],"analytics":[1,123,143,185],"pipelines":[2],"migrating":[3],"to":[4,18,74,85,136,153,168,190],"edge":[5,59],"deployments":[6],"are":[7],"facing":[8],"performance":[9,171],"bottlenecks":[10],"under":[11],"limited":[12],"bandwidth.":[13,43],"Non-uniform":[14],"intra-frame":[15],"encoding":[16,71,105],"emerges":[17],"further":[19],"compress":[20],"pixels":[21],"without":[22],"affecting":[23],"the":[24,27,127,148,162,165,191],"output":[25],"of":[26,48,78,130,164],"server":[28],"deep":[29],"neural":[30,49,101,131],"network":[31,128],"(DNN),":[32],"while":[33],"it":[34],"is":[35,72],"inefficient":[36],"in":[37],"high-resolution":[38],"video":[39,110,122,193],"streaming":[40,111,197],"at":[41],"low":[42],"The":[44],"detail":[45],"enhancement":[46],"capability":[47],"super-resolution":[50],"(SR)":[51],"permits":[52],"resolution":[53],"downsampling":[54],"and":[55,93,106,145,151,158,183,196],"aggressive":[56],"compression":[57],"on":[58],"devices":[60],"for":[61,91,97,103],"low-latency":[62],"transmission.":[63],"To":[64],"exploit":[65],"its":[66],"accuracy":[67,186],"potential,":[68],"DNN-oriented":[69,142],"non-uniform":[70],"expected":[73],"be":[75],"additionally":[76],"aware":[77],"SR":[79,92,138],"models.":[80],"However,":[81],"traditional":[82],"codecs":[83,102,132],"struggle":[84],"cope":[86],"with":[87,112,161],"both":[88],"quality":[89],"optimization":[90],"global":[94],"semantic":[95],"features":[96],"DNN.":[98],"We":[99],"advocate":[100],"coordinated":[104],"enhancement,":[107,195],"enabling":[108],"analytic-oriented":[109],"optimal":[113],"accuracy-delay":[114],"tradeoffs.":[115],"Our":[116],"system,":[117],"VidIQ,":[118],"achieves":[119],"quality-enhanced":[120],"real-time":[121],"by":[124,181,187],"1)":[125],"improving":[126],"architecture":[129],"(at":[133],"two":[134],"granularity)":[135],"integrate":[137],"models":[139],"into":[140],"a":[141,170],"pipeline,":[144],"2)":[146],"adapting":[147],"multi-scale":[149],"encoder":[150],"SR-decoder":[152],"scene":[154],"dynamics":[155],"(i.e.,":[156],"content":[157],"bandwidth":[159],"variations)":[160],"help":[163],"monolithic":[166],"controller":[167],"hold":[169],"advantage.":[172],"Extensive":[173],"evaluations":[174],"showcase":[175],"that":[176],"VidIQ":[177],"reduces":[178],"end-to-end":[179],"delay":[180],"35.8%":[182],"improves":[184],"21.2%":[188],"compared":[189],"recent":[192],"compression,":[194],"baselines.":[198]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-25T00:00:00"}
