{"id":"https://openalex.org/W7161563313","doi":"https://doi.org/10.1109/access.2026.3694334","title":"MR2-ByteTrack: CNN and Transformer-Based Video Object Detection for AI-Augmented Embedded Vision Sensor Nodes","display_name":"MR2-ByteTrack: CNN and Transformer-Based Video Object Detection for AI-Augmented Embedded Vision Sensor Nodes","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7161563313","doi":"https://doi.org/10.1109/access.2026.3694334"},"language":"en","primary_location":{"id":"doi:10.1109/access.2026.3694334","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3694334","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3694334","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053723723","display_name":"Luca Bompani","orcid":"https://orcid.org/0009-0002-1277-8584"},"institutions":[{"id":"https://openalex.org/I4210098188","display_name":"Laboratori Guglielmo Marconi (Italy)","ror":"https://ror.org/01r3vad87","country_code":"IT","type":"company","lineage":["https://openalex.org/I4210098188"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Luca Bompani","raw_affiliation_strings":["1Department of Electrical, Electronic, and Information Engineering “Guglielmo Marconi” (DEI), University of Bologna, Bologna, Italy"],"raw_orcid":"https://orcid.org/0009-0002-1277-8584","affiliations":[{"raw_affiliation_string":"1Department of Electrical, Electronic, and Information Engineering “Guglielmo Marconi” (DEI), University of Bologna, Bologna, Italy","institution_ids":["https://openalex.org/I4210098188"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030025275","display_name":"Manuele Rusci","orcid":"https://orcid.org/0000-0001-7458-4019"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Manuele Rusci","raw_affiliation_strings":["2Department of Electrical Engineering (ESAT), KU Leuven, Leuven, Belgium"],"raw_orcid":"https://orcid.org/0000-0001-7458-4019","affiliations":[{"raw_affiliation_string":"2Department of Electrical Engineering (ESAT), KU Leuven, Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043408422","display_name":"Luca Benini","orcid":"https://orcid.org/0000-0001-8068-3806"},"institutions":[{"id":"https://openalex.org/I4210098188","display_name":"Laboratori Guglielmo Marconi (Italy)","ror":"https://ror.org/01r3vad87","country_code":"IT","type":"company","lineage":["https://openalex.org/I4210098188"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Luca Benini","raw_affiliation_strings":["1Department of Electrical, Electronic, and Information Engineering “Guglielmo Marconi” (DEI), University of Bologna, Bologna, Italy"],"raw_orcid":"https://orcid.org/0000-0001-8068-3806","affiliations":[{"raw_affiliation_string":"1Department of Electrical, Electronic, and Information Engineering “Guglielmo Marconi” (DEI), University of Bologna, Bologna, Italy","institution_ids":["https://openalex.org/I4210098188"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061890705","display_name":"Daniele Palossi","orcid":"https://orcid.org/0000-0003-4487-0836"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Daniele Palossi","raw_affiliation_strings":["3Integrated Systems Laboratory (IIS), ETH Zürich, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0003-4487-0836","affiliations":[{"raw_affiliation_string":"3Integrated Systems Laboratory (IIS), ETH Zürich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089543048","display_name":"Francesco Conti","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098188","display_name":"Laboratori Guglielmo Marconi (Italy)","ror":"https://ror.org/01r3vad87","country_code":"IT","type":"company","lineage":["https://openalex.org/I4210098188"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Francesco Conti","raw_affiliation_strings":["1Department of Electrical, Electronic, and Information Engineering “Guglielmo Marconi” (DEI), University of Bologna, Bologna, Italy"],"raw_orcid":"https://orcid.org/0000-0002-7924-933X","affiliations":[{"raw_affiliation_string":"1Department of Electrical, Electronic, and Information Engineering “Guglielmo Marconi” (DEI), University of Bologna, Bologna, Italy","institution_ids":["https://openalex.org/I4210098188"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.78563311,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"75865","last_page":"75880"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.5616000294685364,"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":0.5616000294685364,"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":0.01590000092983246,"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"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.014000000432133675,"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/object-detection","display_name":"Object detection","score":0.7160999774932861},{"id":"https://openalex.org/keywords/object-class-detection","display_name":"Object-class detection","score":0.4081000089645386},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.40149998664855957},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.3813999891281128},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.35350000858306885},{"id":"https://openalex.org/keywords/machine-vision","display_name":"Machine vision","score":0.3467999994754791},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3449999988079071},{"id":"https://openalex.org/keywords/wireless-sensor-network","display_name":"Wireless sensor network","score":0.33959999680519104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.809499979019165},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.7160999774932861},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7103999853134155},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6503999829292297},{"id":"https://openalex.org/C71681937","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object-class detection","level":5,"score":0.4081000089645386},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.40149998664855957},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.3813999891281128},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.35350000858306885},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.3467999994754791},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3449999988079071},{"id":"https://openalex.org/C24590314","wikidata":"https://www.wikidata.org/wiki/Q336038","display_name":"Wireless sensor network","level":2,"score":0.33959999680519104},{"id":"https://openalex.org/C76935873","wikidata":"https://www.wikidata.org/wiki/Q209121","display_name":"Image sensor","level":2,"score":0.33640000224113464},{"id":"https://openalex.org/C2780624872","wikidata":"https://www.wikidata.org/wiki/Q852453","display_name":"Motion detection","level":3,"score":0.31949999928474426},{"id":"https://openalex.org/C4641261","wikidata":"https://www.wikidata.org/wiki/Q11681085","display_name":"Face detection","level":4,"score":0.30399999022483826},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.28999999165534973},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C193536780","wikidata":"https://www.wikidata.org/wiki/Q1513153","display_name":"Edge detection","level":4,"score":0.2709999978542328},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.2621000111103058},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.25119999051094055},{"id":"https://openalex.org/C182521987","wikidata":"https://www.wikidata.org/wiki/Q2493877","display_name":"Viola\u2013Jones object detection framework","level":5,"score":0.25029999017715454}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2026.3694334","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3694334","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:c122904c5d2942c8b7ed7ec7f6e0cf02","is_oa":true,"landing_page_url":"https://doaj.org/article/c122904c5d2942c8b7ed7ec7f6e0cf02","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 14, Pp 75865-75880 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3694334","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3694334","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Modern":[0],"smart":[1],"vision":[2,72,207],"sensors":[3],"need":[4],"on-device":[5],"intelligence":[6],"to":[7,18,104,114,146,187,192],"process":[8],"video":[9,41],"streams,":[10],"as":[11,162,164],"cloud":[12],"computing":[13],"is":[14],"often":[15],"impractical":[16],"due":[17],"bandwidth,":[19],"latency,":[20],"and":[21,37,82,92,119,152,169],"privacy":[22],"constraints.":[23],"However,":[24],"these":[25],"sensory":[26],"systems":[27],"typically":[28],"rely":[29],"on":[30,134,176,203],"ultra-low-power":[31,179],"microcontrollers":[32],"(MCUs)":[33],"with":[34,128],"limited":[35],"memory":[36],"compute,":[38],"making":[39],"conventional":[40],"object":[42],"detection":[43,106],"methods,":[44],"which":[45,99],"require":[46],"feature":[47],"storage":[48],"or":[49],"multi-frame":[50],"buffering,":[51],"unfeasible.":[52],"To":[53],"address":[54],"this":[55],"challenge,":[56],"we":[57],"introduce":[58],"Multi-Resolution":[59],"Rescored":[60],"ByteTrack":[61,91],"(MR2-ByteTrack),":[62],"aVideo":[63],"Object":[64],"Detection":[65],"(VOD)":[66],"method":[67,184],"tailored":[68],"for":[69,148,154,166,171],"MCU-based":[70],"embedded":[71,206],"nodes.":[73],"MR2-ByteTrack":[74,138],"reduces":[75],"computational":[76],"cost":[77],"by":[78,161],"alternating":[79],"between":[80],"full-":[81],"low-resolution":[83],"inference,":[84],"while":[85,157],"linking":[86],"detections":[87],"across":[88,109,126],"frames":[89],"via":[90],"correcting":[93],"misclassifications":[94],"through":[95],"the":[96,149,155,167,172,198],"Rescore":[97],"algorithm,":[98],"applies":[100],"probability":[101],"union":[102],"rules":[103],"aggregate":[105],"confidence":[107],"scores":[108,143],"frames.We":[110],"apply":[111],"our":[112,183],"approach":[113],"both":[115],"a":[116,120],"CNN-based":[117,150],"detector":[118],"Transformer-based":[121,201],"model,":[122],"demonstrating":[123],"its":[124],"generality":[125],"architectures":[127],"fundamentally":[129],"different":[130],"spatial":[131],"processing.":[132],"Experiments":[133],"ImageNetVID":[135],"demonstrate":[136],"that":[137],"maintains":[139],"accuracy,":[140],"achieving":[141],"mAP":[142],"of":[144],"up":[145,186],"49.0":[147],"models":[151],"48.7":[153],"Transformer,":[156],"reducing":[158],"multiply\u2013accumulate":[159],"operations":[160],"much":[163],"53%":[165],"CNNs":[168],"32%":[170],"Transformer.":[173],"When":[174],"deployed":[175],"GAP9,":[177],"an":[178,204],"RISC-V":[180],"multicore":[181],"MCU,":[182],"yields":[185],"55%":[188],"energy":[189],"savings":[190],"compared":[191],"processing":[193],"only":[194],"full-resolution":[195],"images,":[196],"enabling":[197],"first":[199],"real-time":[200],"VOD":[202],"MCU-class":[205],"node.code":[208],"available":[209],"at":[210],"https://github.com/Bomps4/Multi_Resolution_Rescored_ByteTrack/tree/IEEE_Access.":[211]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-19T00:00:00"}