{"id":"https://openalex.org/W7084074500","doi":"https://doi.org/10.1109/bmsb65076.2025.11165647","title":"MobiMind: A Lightweight and Fast Inference Framework of Deep Neural Networks for Mobile Devices","display_name":"MobiMind: A Lightweight and Fast Inference Framework of Deep Neural Networks for Mobile Devices","publication_year":2025,"publication_date":"2025-06-11","ids":{"openalex":"https://openalex.org/W7084074500","doi":"https://doi.org/10.1109/bmsb65076.2025.11165647"},"language":"en","primary_location":{"id":"doi:10.1109/bmsb65076.2025.11165647","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bmsb65076.2025.11165647","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB)","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":null,"display_name":"Kaian Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kaian Wang","raw_affiliation_strings":["Southern University of Science and Technology,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology,Shenzhen,China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Longhao Zou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longhao Zou","raw_affiliation_strings":["Pengcheng Laboratory,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Pengcheng Laboratory,Shenzhen,China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Haoyu Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210146427","display_name":"CCCC Wuhan Harbour Engineering Design and Research (China)","ror":"https://ror.org/04y08pq82","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210146427"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoyu Zhang","raw_affiliation_strings":["CCCC First Harbor Engineering Company Ltd"],"affiliations":[{"raw_affiliation_string":"CCCC First Harbor Engineering Company Ltd","institution_ids":["https://openalex.org/I4210146427"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tonghao Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I2801045807","display_name":"Shenzhen Stock Exchange","ror":"https://ror.org/058h0n244","country_code":"CN","type":"other","lineage":["https://openalex.org/I2801045807"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tonghao Wu","raw_affiliation_strings":["Shenzhen Power Supply Company Ltd,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Power Supply Company Ltd,Shenzhen,China","institution_ids":["https://openalex.org/I2801045807"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zihao Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zihao Chen","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":null,"display_name":"Kai Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Hu","raw_affiliation_strings":["South China University of Technology"],"affiliations":[{"raw_affiliation_string":"South China University of Technology","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I3045169105"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.57860011,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10005","display_name":"Ecology and Vegetation Dynamics Studies","score":0.4277999997138977,"subfield":{"id":"https://openalex.org/subfields/2309","display_name":"Nature and Landscape Conservation"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10005","display_name":"Ecology and Vegetation Dynamics Studies","score":0.4277999997138977,"subfield":{"id":"https://openalex.org/subfields/2309","display_name":"Nature and Landscape Conservation"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12467","display_name":"Rangeland Management and Livestock Ecology","score":0.22089999914169312,"subfield":{"id":"https://openalex.org/subfields/2308","display_name":"Management, Monitoring, Policy and Law"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12630","display_name":"African Botany and Ecology Studies","score":0.06700000166893005,"subfield":{"id":"https://openalex.org/subfields/1107","display_name":"Forestry"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.7319999933242798},{"id":"https://openalex.org/keywords/mobile-device","display_name":"Mobile device","score":0.722000002861023},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6636999845504761},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5350000262260437},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.4657000005245209},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.4465000033378601},{"id":"https://openalex.org/keywords/mobile-cloud-computing","display_name":"Mobile cloud computing","score":0.4318000078201294},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.36469998955726624}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8194000124931335},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.7319999933242798},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.722000002861023},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6636999845504761},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5350000262260437},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5023999810218811},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.4657000005245209},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.4465000033378601},{"id":"https://openalex.org/C2779191767","wikidata":"https://www.wikidata.org/wiki/Q6887075","display_name":"Mobile cloud computing","level":3,"score":0.4318000078201294},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.36469998955726624},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3601999878883362},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.3402999937534332},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.3337000012397766},{"id":"https://openalex.org/C144543869","wikidata":"https://www.wikidata.org/wiki/Q2738570","display_name":"Mobile computing","level":2,"score":0.32839998602867126},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.326200008392334},{"id":"https://openalex.org/C95491727","wikidata":"https://www.wikidata.org/wiki/Q992968","display_name":"Mobile telephony","level":3,"score":0.3131999969482422},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3073999881744385},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.30720001459121704},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.296099990606308},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2955000102519989},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.2922999858856201},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C157170001","wikidata":"https://www.wikidata.org/wiki/Q4781507","display_name":"Applications of artificial intelligence","level":2,"score":0.2565999925136566}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bmsb65076.2025.11165647","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bmsb65076.2025.11165647","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB)","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":23,"referenced_works":["https://openalex.org/W2626129225","https://openalex.org/W2739789140","https://openalex.org/W2860338957","https://openalex.org/W2940862705","https://openalex.org/W2963319203","https://openalex.org/W2963363373","https://openalex.org/W3015998244","https://openalex.org/W3023820783","https://openalex.org/W3131920484","https://openalex.org/W3132942233","https://openalex.org/W3135807226","https://openalex.org/W3154627629","https://openalex.org/W3159185005","https://openalex.org/W3192336523","https://openalex.org/W4200566604","https://openalex.org/W4231164953","https://openalex.org/W4236868170","https://openalex.org/W4288083528","https://openalex.org/W4292363360","https://openalex.org/W4313349401","https://openalex.org/W4385882167","https://openalex.org/W4401508508","https://openalex.org/W4405002449"],"related_works":[],"abstract_inverted_index":{"As":[0],"intelligent":[1],"application":[2],"services":[3],"transition":[4],"from":[5],"the":[6,41,143],"cloud":[7],"to":[8,103,123,139,155,184],"mobile":[9,35,81,108],"devices":[10],"such":[11],"as":[12],"AIPC":[13],"laptops":[14],"and":[15,21,30,52,87,120,146,176,186],"smart-phones,":[16],"they":[17],"face":[18],"increasing":[19],"computational":[20],"storage":[22],"challenges.":[23],"Running":[24],"deep":[25],"neural":[26],"network":[27],"(DNN)":[28],"inference":[29,86,106],"real-time":[31,166],"high-precision":[32],"tasks":[33],"on":[34,49,80,107,111],"platforms":[36],"demands":[37],"significant":[38],"resources,":[39],"pushing":[40],"limits":[42],"of":[43,168,182],"their":[44],"capabilities.":[45],"While":[46],"extensive":[47],"research":[48],"model":[50],"compression":[51,122],"pruning":[53,59,68,101],"techniques":[54,117],"has":[55],"shown":[56],"promise,":[57],"non-structured":[58],"maintains":[60],"accuracy":[61,190],"but":[62,71],"lacks":[63],"hardware":[64,125],"efficiency,":[65],"whereas":[66],"structured":[67],"is":[69],"hardware-friendly":[70],"often":[72],"sacrifices":[73],"accuracy.":[74,129],"Additionally,":[75],"efficient":[76],"memory":[77],"buffer":[78],"utilization":[79],"devices,":[82,109],"particularly":[83],"for":[84],"AI":[85],"accelerator":[88],"optimization,":[89],"remains":[90],"a":[91,131],"persistent":[92],"bottleneck.":[93],"In":[94],"this":[95],"paper,":[96],"We":[97],"propose":[98],"an":[99,156],"optimized":[100],"method":[102],"enhance":[104],"DNN":[105,170],"focusing":[110],"compiler-level":[112],"optimization.":[113],"This":[114],"approach":[115],"integrates":[116],"like":[118],"Quantization":[119],"weight":[121],"improve":[124],"efficiency":[126],"while":[127],"maintaining":[128],"Using":[130],"recursive":[132],"depth-first":[133],"search":[134,144],"strategy,":[135],"it":[136],"restricts":[137],"exploration":[138],"canonical":[140],"solutions,":[141],"reducing":[142],"space":[145],"enabling":[147],"more":[148],"effective":[149],"pruning.":[150],"Empirical":[151],"results":[152],"show":[153],"up":[154,183],"order-of-magnitude":[157],"performance":[158],"improvement":[159],"The":[160],"framework":[161],"minimizes":[162],"resource":[163],"use,":[164],"achieving":[165],"execution":[167],"demanding":[169],"models.":[171],"It":[172],"outperforms":[173],"TensorFlow":[174],"Lite":[175],"Tensor":[177],"Virtual":[178],"Machine(TVM)":[179],"with":[180],"speedups":[181],"53.2\u00d7":[185],"16.3\u00d7,":[187],"respectively,":[188],"without":[189],"loss.":[191]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}