{"id":"https://openalex.org/W7160517714","doi":"https://doi.org/10.48550/arxiv.2605.04791","title":"OpenWatch: A Multimodal Benchmark for Hand Gesture Recognition on Smartwatches","display_name":"OpenWatch: A Multimodal Benchmark for Hand Gesture Recognition on Smartwatches","publication_year":2026,"publication_date":"2026-05-06","ids":{"openalex":"https://openalex.org/W7160517714","doi":"https://doi.org/10.48550/arxiv.2605.04791"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.04791","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.04791","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.04791","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092506176","display_name":"Pietro Bonazzi","orcid":"https://orcid.org/0009-0006-6147-2214"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bonazzi, Pietro","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135593163","display_name":"Youssef Ahmed","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ahmed, Youssef","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135577071","display_name":"Daniel Eckert","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eckert, Daniel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044569493","display_name":"Andrea Ronco","orcid":"https://orcid.org/0000-0003-1672-8672"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ronco, Andrea","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135540373","display_name":"Junjie Zeng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeng, Junjie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135544041","display_name":"Dengxin Dai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dai, Dengxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135554396","display_name":"Michele Magno","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Magno, Michele","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.5927000045776367,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.5927000045776367,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.11720000207424164,"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/T10789","display_name":"Interactive and Immersive Displays","score":0.09200000017881393,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/smartwatch","display_name":"Smartwatch","score":0.926800012588501},{"id":"https://openalex.org/keywords/inertial-measurement-unit","display_name":"Inertial measurement unit","score":0.6601999998092651},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.6254000067710876},{"id":"https://openalex.org/keywords/wearable-computer","display_name":"Wearable computer","score":0.6177999973297119},{"id":"https://openalex.org/keywords/activity-recognition","display_name":"Activity recognition","score":0.5508999824523926},{"id":"https://openalex.org/keywords/gesture-recognition","display_name":"Gesture recognition","score":0.46209999918937683},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4156999886035919},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.41359999775886536}],"concepts":[{"id":"https://openalex.org/C29794715","wikidata":"https://www.wikidata.org/wiki/Q5362345","display_name":"Smartwatch","level":3,"score":0.926800012588501},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7820000052452087},{"id":"https://openalex.org/C79061980","wikidata":"https://www.wikidata.org/wiki/Q941680","display_name":"Inertial measurement unit","level":2,"score":0.6601999998092651},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.6254000067710876},{"id":"https://openalex.org/C150594956","wikidata":"https://www.wikidata.org/wiki/Q1334829","display_name":"Wearable computer","level":2,"score":0.6177999973297119},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6118000149726868},{"id":"https://openalex.org/C121687571","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Activity recognition","level":2,"score":0.5508999824523926},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.46209999918937683},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.44769999384880066},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4156999886035919},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.41359999775886536},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4000000059604645},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.36739999055862427},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3625999987125397},{"id":"https://openalex.org/C54290928","wikidata":"https://www.wikidata.org/wiki/Q4845080","display_name":"Wearable technology","level":3,"score":0.36059999465942383},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3197999894618988},{"id":"https://openalex.org/C89805583","wikidata":"https://www.wikidata.org/wiki/Q192940","display_name":"Accelerometer","level":2,"score":0.3095000088214874},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.29429998993873596},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.2854999899864197},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2825999855995178},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C176168674","wikidata":"https://www.wikidata.org/wiki/Q763835","display_name":"Lifelog","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.2615000009536743}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.04791","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.04791","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.04791","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.04791","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Despite":[0],"widespread":[1],"adoption":[2],"of":[3,44,59,82,157],"smartwatches":[4],"worldwide,":[5],"open-benchmarks":[6],"for":[7,25,77,89,118,136,190],"wrist-based":[8,26],"gesture":[9,27,62],"recognition":[10,28],"remain":[11],"surprisingly":[12],"limited.":[13],"In":[14,140],"this":[15],"work,":[16],"we":[17,65,84,142,170],"introduce":[18],"the":[19,177],"first":[20],"open-access":[21],"multi-modal":[22],"benchmark,":[23],"OpenWatch,":[24],"using":[29],"synchronized":[30],"inertial":[31],"and":[32,49,56,73,111,162,187],"physiological":[33],"sensing":[34],"on":[35,176],"a":[36,57,67,94,114,130],"commercial":[37],"smartwatch.":[38],"It":[39],"contains":[40],"over":[41],"10":[42],"hours":[43],"Inertial":[45],"Measurement":[46],"Unit":[47],"(IMU)":[48],"Photoplethysmography":[50],"(PPG)":[51],"data":[52,185],"across":[53],"50":[54],"participants":[55],"vocabulary":[58],"59":[60],"labelled":[61],"sequences.":[63],"Furthermore,":[64],"present":[66],"subject-independent":[68],"evaluation":[69],"protocol":[70],"including":[71],"traditional":[72],"deep":[74],"learning":[75],"methods":[76],"time-series":[78],"classification.":[79],"On":[80],"top":[81],"this,":[83],"develop":[85],"two":[86],"novel":[87],"methodologies":[88],"hand-gesture":[90],"recognition:":[91],"(i)":[92],"MixToken,":[93],"task-specific":[95,145],"mixture-of-experts":[96],"that":[97,126,144],"fuses":[98],"per-channel":[99],"IMU":[100],"filterbank":[101],"features":[102],"with":[103],"cross-channel":[104],"statistical":[105],"tokens":[106],"through":[107],"learned":[108],"logit":[109],"mixing,":[110],"(ii)":[112],"NormWear-Lora,":[113],"low-rank":[115],"adaptation":[116,189],"module":[117],"smartwatch":[119,138,152],"foundation":[120,153],"models.":[121,139],"Our":[122],"benchmarking":[123],"results":[124],"reveal":[125],"PPG":[127],"signals":[128],"carries":[129],"substantial":[131],"predictive":[132],"benefit":[133],"(+12.5%":[134],"F1-score)":[135],"foundational":[137],"addition,":[141],"show":[143],"architectures":[146],"(i.e.":[147],"MixToken)":[148],"substantially":[149],"outperforms":[150],"finetuned":[151],"models":[154],"in":[155],"terms":[156],"accuracy":[158],"(F1-score=90%":[159],"vs":[160,166],"66%)":[161],"memory":[163],"efficiency":[164],"(223k":[165],"136M":[167],"parameters).":[168],"Finally,":[169],"also":[171],"provide":[172],"clear":[173],"empirical":[174],"guidance":[175],"trade-offs":[178],"between":[179],"specialized":[180],"architecture":[181],"design,":[182],"modality":[183],"fusion,":[184],"augmentations,":[186],"foundation-model":[188],"resource-constrained":[191],"wearable":[192],"sensing.":[193]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-08T00:00:00"}