{"id":"https://openalex.org/W4412623398","doi":"https://doi.org/10.1109/tmc.2025.3592647","title":"Squeezer: Efficient Multi-DNN Inference for Edge Video Analytics via Cross-Model Scheduling","display_name":"Squeezer: Efficient Multi-DNN Inference for Edge Video Analytics via Cross-Model Scheduling","publication_year":2025,"publication_date":"2025-07-24","ids":{"openalex":"https://openalex.org/W4412623398","doi":"https://doi.org/10.1109/tmc.2025.3592647"},"language":"en","primary_location":{"id":"doi:10.1109/tmc.2025.3592647","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmc.2025.3592647","pdf_url":null,"source":{"id":"https://openalex.org/S69141925","display_name":"IEEE Transactions on Mobile Computing","issn_l":"1536-1233","issn":["1536-1233","1558-0660","2161-9875"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Mobile Computing","raw_type":"journal-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":null,"display_name":"Xiang Wang","orcid":"https://orcid.org/0009-0003-3223-5744"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiang Wang","raw_affiliation_strings":["Department of Computer Science and Technology, BNRist, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102874660","display_name":"Lingxiao Ma","orcid":"https://orcid.org/0009-0009-9524-5476"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingxiao Ma","raw_affiliation_strings":["Microsoft Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045410502","display_name":"Ziyan Fu","orcid":"https://orcid.org/0000-0002-1039-0386"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyan Fu","raw_affiliation_strings":["Department of Computer Science and Technology, BNRist, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiangyu Li","orcid":"https://orcid.org/0009-0001-5341-2303"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyu Li","raw_affiliation_strings":["Institute for AI Industry Research (AIR), Tsinghua University, Beijing, China","Institute for AI Industry Research (AIR) and the Department of Electronic Engineering, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute for AI Industry Research (AIR), Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Institute for AI Industry Research (AIR) and the Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100628298","display_name":"Yuanchun Li","orcid":"https://orcid.org/0000-0002-1591-2526"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanchun Li","raw_affiliation_strings":["Institute for AI Industry Research (AIR), Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute for AI Industry Research (AIR), Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015419107","display_name":"Ju Ren","orcid":"https://orcid.org/0000-0003-2782-183X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ju Ren","raw_affiliation_strings":["Department of Computer Science and Technology, BNRist, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069049205","display_name":"Yaoxue Zhang","orcid":"https://orcid.org/0000-0001-6717-461X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaoxue Zhang","raw_affiliation_strings":["Department of Computer Science and Technology, BNRist, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102880548","display_name":"Yunxin Liu","orcid":"https://orcid.org/0000-0001-7352-8955"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunxin Liu","raw_affiliation_strings":["Institute for AI Industry Research (AIR), Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute for AI Industry Research (AIR), Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22580645,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"24","issue":"12","first_page":"13309","last_page":"13321"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9746999740600586,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9746999740600586,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9491000175476074,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9286999702453613,"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":0.8283753991127014},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.6436299085617065},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6406189203262329},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5830056071281433},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3482978343963623},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.2705380320549011},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.10335215926170349}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8283753991127014},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.6436299085617065},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6406189203262329},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5830056071281433},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3482978343963623},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2705380320549011},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.10335215926170349},{"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/tmc.2025.3592647","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmc.2025.3592647","pdf_url":null,"source":{"id":"https://openalex.org/S69141925","display_name":"IEEE Transactions on Mobile Computing","issn_l":"1536-1233","issn":["1536-1233","1558-0660","2161-9875"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Mobile Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1218059104","display_name":null,"funder_award_id":"62402268","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3184683627","display_name":null,"funder_award_id":"62432004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F3230804744","display_name":"Guoqiang Institute, Tsinghua University","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2604514113","https://openalex.org/W2905810301","https://openalex.org/W2951890823","https://openalex.org/W2982157693","https://openalex.org/W3005253217","https://openalex.org/W3046256272","https://openalex.org/W3086544482","https://openalex.org/W3174529902","https://openalex.org/W3208777667","https://openalex.org/W4360831842","https://openalex.org/W4372261197","https://openalex.org/W4387321503","https://openalex.org/W4387967984","https://openalex.org/W4394923418","https://openalex.org/W4394944658","https://openalex.org/W4404237407"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2502104792"],"abstract_inverted_index":{"Video":[0],"analytics":[1],"at":[2],"the":[3,28,81,105,121],"edge":[4,73],"is":[5],"becoming":[6],"increasingly":[7],"prevalent":[8],"in":[9,126,132,149],"many":[10],"scenarios,":[11],"such":[12],"as":[13],"smart":[14],"campuses":[15],"and":[16,108],"intelligent":[17],"factories.":[18],"These":[19],"applications":[20],"often":[21],"consist":[22],"of":[23,97],"multiple":[24,68,98],"subtasks,":[25],"which":[26,88,94,112],"necessitates":[27],"optimization":[29],"for":[30],"multi-DNN":[31,133],"(Deep":[32],"Neural":[33],"Network)":[34],"inference.":[35,134],"Due":[36],"to":[37,52,146],"limited":[38],"consideration":[39],"over":[40],"cross-model":[41,82,130],"scheduling,":[42],"current":[43],"practices":[44],"cannot":[45],"fully":[46],"leverage":[47],"available":[48],"computing":[49],"resources,":[50],"leading":[51],"suboptimal":[53],"performance.":[54],"To":[55],"address":[56],"this,":[57],"we":[58],"propose":[59],"Squeezer,":[60],"a":[61,76,85],"multiDNN":[62],"serving":[63],"framework":[64],"that":[65,139],"holistically":[66],"schedules":[67],"DNN":[69,99],"models":[70,100],"on":[71],"an":[72],"server":[74],"with":[75],"single":[77],"GPU.":[78],"Squeezer":[79,140],"decouples":[80],"scheduling":[83,106],"into":[84,101],"two-layered":[86],"approach,":[87],"involves":[89],"(1)":[90],"balanced":[91],"operator":[92],"grouping":[93],"partitions":[95],"operators":[96],"groups,":[102],"significantly":[103],"reducing":[104],"complexity":[107],"(2)":[109],"kernel":[110],"scheduler":[111],"orchestrates":[113],"parallel":[114],"execution":[115],"within":[116],"each":[117],"group":[118],"by":[119],"considering":[120],"interplay":[122],"among":[123],"kernels":[124],"running":[125],"parallel,":[127],"thereby":[128],"enabling":[129],"optimizations":[131],"Performance":[135],"evaluation":[136],"results":[137],"demonstrate":[138],"outperforms":[141],"state-of-the-art":[142],"baselines,":[143],"achieving":[144],"up":[145],"1.91\u00d7":[147],"improvement":[148],"system":[150],"throughput.":[151]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}