{"id":"https://openalex.org/W4385585286","doi":"https://doi.org/10.1145/3587135.3592204","title":"T-RecX","display_name":"T-RecX","publication_year":2023,"publication_date":"2023-05-09","ids":{"openalex":"https://openalex.org/W4385585286","doi":"https://doi.org/10.1145/3587135.3592204"},"language":"en","primary_location":{"id":"doi:10.1145/3587135.3592204","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3587135.3592204","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3587135.3592204","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM International Conference on Computing Frontiers","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3587135.3592204","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027945744","display_name":"Nikhil Pratap Ghanathe","orcid":"https://orcid.org/0000-0002-9342-363X"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Nikhil P. Ghanathe","raw_affiliation_strings":["University of British Columbia, Vancouver, Canada"],"raw_orcid":"https://orcid.org/0000-0002-9342-363X","affiliations":[{"raw_affiliation_string":"University of British Columbia, Vancouver, Canada","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013246362","display_name":"Steven J. E. Wilton","orcid":"https://orcid.org/0000-0002-1241-6690"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Steve Wilton","raw_affiliation_strings":["University of British Columbia, Vancouver, Canada"],"raw_orcid":"https://orcid.org/0000-0002-1241-6690","affiliations":[{"raw_affiliation_string":"University of British Columbia, Vancouver, Canada","institution_ids":["https://openalex.org/I141945490"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0105,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.78401022,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"123","last_page":"133"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9994999766349792,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9994999766349792,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9986000061035156,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8204289674758911},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5884732604026794},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.5453450679779053},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.525750458240509},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5223166346549988},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4832899868488312},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.4818197786808014},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.47453463077545166},{"id":"https://openalex.org/keywords/internet-of-things","display_name":"Internet of Things","score":0.45794788002967834},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.44360655546188354},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.42800503969192505},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42153486609458923},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.10320782661437988}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8204289674758911},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5884732604026794},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.5453450679779053},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.525750458240509},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5223166346549988},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4832899868488312},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.4818197786808014},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.47453463077545166},{"id":"https://openalex.org/C81860439","wikidata":"https://www.wikidata.org/wiki/Q251212","display_name":"Internet of Things","level":2,"score":0.45794788002967834},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.44360655546188354},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.42800503969192505},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42153486609458923},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.10320782661437988},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3587135.3592204","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3587135.3592204","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3587135.3592204","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM International Conference on Computing Frontiers","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3587135.3592204","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3587135.3592204","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3587135.3592204","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM International Conference on Computing Frontiers","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385585286.pdf","grobid_xml":"https://content.openalex.org/works/W4385585286.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W1475617732","https://openalex.org/W1937847179","https://openalex.org/W2097117768","https://openalex.org/W2108598243","https://openalex.org/W2114921551","https://openalex.org/W2124870639","https://openalex.org/W2137693329","https://openalex.org/W2194775991","https://openalex.org/W2217896605","https://openalex.org/W2265127172","https://openalex.org/W2276486856","https://openalex.org/W2557728737","https://openalex.org/W2751366252","https://openalex.org/W2808052525","https://openalex.org/W2902032143","https://openalex.org/W2912972081","https://openalex.org/W2916484109","https://openalex.org/W2924515500","https://openalex.org/W2940764740","https://openalex.org/W2951287298","https://openalex.org/W2962677625","https://openalex.org/W2964184826","https://openalex.org/W2980706162","https://openalex.org/W2981114133","https://openalex.org/W2982083293","https://openalex.org/W3019321633","https://openalex.org/W3039447636","https://openalex.org/W3102775700","https://openalex.org/W3102883737","https://openalex.org/W3104393472","https://openalex.org/W3128506819","https://openalex.org/W3150672085","https://openalex.org/W3198451434","https://openalex.org/W3205643102","https://openalex.org/W3206423279","https://openalex.org/W4233429846","https://openalex.org/W4285112901"],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W2114097550","https://openalex.org/W4286904253","https://openalex.org/W3119978414","https://openalex.org/W2516975559","https://openalex.org/W3206647229","https://openalex.org/W1969408022","https://openalex.org/W2000885660","https://openalex.org/W2545741539","https://openalex.org/W1989658893"],"abstract_inverted_index":{"Deploying":[0],"Machine":[1],"learning":[2],"(ML)":[3],"on":[4,27,102,146,206],"milliwatt-scale":[5],"edge":[6],"devices":[7],"(tinyML)":[8],"is":[9,114],"gaining":[10],"popularity":[11],"due":[12],"to":[13,40,127],"recent":[14],"breakthroughs":[15],"in":[16,74,83,86,95,183,185],"ML":[17],"and":[18,160],"Internet":[19],"of":[20,61,131,175],"Things":[21],"(IoT).":[22],"Most":[23],"tinyML":[24,110],"research":[25],"focuses":[26],"model":[28,35],"compression":[29],"techniques":[30,107],"that":[31,169,198],"trade":[32],"accuracy":[33,174,190],"(and":[34],"capacity)":[36],"for":[37,109,117,155,187],"compact":[38],"models":[39,54],"fit":[41],"into":[42],"the":[43,59,68,77,129,136,140,150,173,207],"KB-sized":[44],"tiny-edge":[45],"devices.":[46],"In":[47,121],"this":[48],"paper,":[49],"we":[50,123,196,209],"show":[51,168,197],"how":[52],"such":[53],"can":[55],"be":[56],"enhanced":[57],"by":[58,134,139],"addition":[60],"an":[62],"early":[63,80,89,141],"exit":[64,90],"intermediate":[65,69],"classifier.":[66],"If":[67],"classifier":[70],"exhibits":[71],"sufficient":[72],"confidence":[73],"its":[75],"prediction,":[76],"network":[78,132],"exits":[79],"thereby,":[81],"resulting":[82],"considerable":[84],"savings":[85],"time.":[87],"Although":[88],"classifiers":[91],"have":[92],"been":[93],"proposed":[94],"previous":[96,99],"work,":[97],"these":[98],"proposals":[100],"focus":[101],"large":[103],"networks,":[104],"making":[105],"their":[106],"suboptimal/impractical":[108],"applications.":[111],"Our":[112,166],"technique":[113],"optimized":[115],"specifically":[116],"tiny-CNN":[118],"sized":[119],"models.":[120,194],"addition,":[122],"present":[124],"a":[125],"method":[126],"alleviate":[128],"effect":[130],"overthinking":[133],"leveraging":[135],"representations":[137],"learned":[138],"exit.":[142],"We":[143],"evaluate":[144],"T-RecX":[145,170],"three":[147],"CNNs":[148],"from":[149],"MLPerf":[151],"tiny":[152],"benchmark":[153],"suite":[154],"image":[156],"classification,":[157],"keyword":[158],"spotting":[159],"visual":[161],"wake":[162],"word":[163],"detection":[164],"tasks.":[165],"results":[167],"1)":[171],"improves":[172],"baseline":[176],"network,":[177],"2)":[178],"achieves":[179],"31.58%":[180],"average":[181],"reduction":[182],"FLOPS":[184],"exchange":[186],"one":[188],"percent":[189],"across":[191],"all":[192],"evaluated":[193],"Furthermore,":[195],"our":[199],"methods":[200],"consistently":[201],"outperform":[202],"popular":[203],"prior":[204],"works":[205],"tiny-CNNs":[208],"evaluate.":[210]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2023-08-05T00:00:00"}