{"id":"https://openalex.org/W4414565371","doi":"https://doi.org/10.1145/3810218","title":"COMODO: Cross-Modal Video-to-IMU Distillation for Efficient Egocentric Human Activity Recognition","display_name":"COMODO: Cross-Modal Video-to-IMU Distillation for Efficient Egocentric Human Activity Recognition","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W4414565371","doi":"https://doi.org/10.1145/3810218"},"language":"en","primary_location":{"id":"doi:10.1145/3810218","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3810218","pdf_url":null,"source":{"id":"https://openalex.org/S4210219751","display_name":"Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies","issn_l":"2474-9567","issn":["2474-9567"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3810218","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Baiyu Chen","orcid":"https://orcid.org/0009-0000-8617-9635"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Baiyu Chen","raw_affiliation_strings":["School of Computer Science and Engineering, The University of New South Wales, Sydney, Australia"],"raw_orcid":"https://orcid.org/0009-0000-8617-9635","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, The University of New South Wales, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025726978","display_name":"Wilson Wongso","orcid":"https://orcid.org/0000-0003-0896-1941"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Wilson Wongso","raw_affiliation_strings":["School of Computer Science and Engineering, The University of New South Wales, Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0003-0896-1941","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, The University of New South Wales, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085444034","display_name":"Zechen Li","orcid":"https://orcid.org/0000-0002-1810-1446"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zechen Li","raw_affiliation_strings":["School of Computer Science and Engineering, The University of New South Wales, Sydney, Australia"],"raw_orcid":"https://orcid.org/0009-0001-6900-833X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, The University of New South Wales, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060960319","display_name":"Yonchanok Khaokaew","orcid":"https://orcid.org/0000-0003-4297-6274"},"institutions":[{"id":"https://openalex.org/I82828225","display_name":"King Mongkut's University of Technology North Bangkok","ror":"https://ror.org/04fy6jb97","country_code":"TH","type":"education","lineage":["https://openalex.org/I82828225"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Yonchanok Khaokaew","raw_affiliation_strings":["King Mongkut's University of Technology North Bangkok, Bangkok, Thailand and School of Computer Science and Engineering, The University of New South Wales, Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0003-4297-6274","affiliations":[{"raw_affiliation_string":"King Mongkut's University of Technology North Bangkok, Bangkok, Thailand and School of Computer Science and Engineering, The University of New South Wales, Sydney, Australia","institution_ids":["https://openalex.org/I82828225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114245307","display_name":"Hao Xue","orcid":"https://orcid.org/0009-0000-3369-8511"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]},{"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","HK"],"is_corresponding":false,"raw_author_name":"Hao Xue","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China and School of Computer Science and Engineering, The University of New South Wales, Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0003-1700-9215","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China and School of Computer Science and Engineering, The University of New South Wales, Sydney, Australia","institution_ids":["https://openalex.org/I889458895","https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090893421","display_name":"Flora D. Salim","orcid":"https://orcid.org/0000-0002-1237-1664"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Flora D. Salim","raw_affiliation_strings":["School of Computer Science and Engineering, The University of New South Wales, Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0002-1237-1664","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, The University of New South Wales, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.4815,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.91512062,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"10","issue":"2","first_page":"1","last_page":"29"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.8371999859809875,"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/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.8371999859809875,"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/T12222","display_name":"IoT-based Smart Home Systems","score":0.7235000133514404,"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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.694599986076355,"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/leverage","display_name":"Leverage (statistics)","score":0.6883999705314636},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6859999895095825},{"id":"https://openalex.org/keywords/activity-recognition","display_name":"Activity recognition","score":0.5769000053405762},{"id":"https://openalex.org/keywords/inertial-measurement-unit","display_name":"Inertial measurement unit","score":0.5555999875068665},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.49790000915527344},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.48010000586509705},{"id":"https://openalex.org/keywords/downstream","display_name":"Downstream (manufacturing)","score":0.4171999990940094},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.41260001063346863},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4011000096797943},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3912000060081482}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7605000138282776},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6883999705314636},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6859999895095825},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6123999953269958},{"id":"https://openalex.org/C121687571","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Activity recognition","level":2,"score":0.5769000053405762},{"id":"https://openalex.org/C79061980","wikidata":"https://www.wikidata.org/wiki/Q941680","display_name":"Inertial measurement unit","level":2,"score":0.5555999875068665},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.49790000915527344},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.48010000586509705},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.4171999990940094},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.41260001063346863},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4050000011920929},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4011000096797943},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3912000060081482},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3750999867916107},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.357699990272522},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.3529999852180481},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.34860000014305115},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3425000011920929},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33739998936653137},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.32350000739097595},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3133000135421753},{"id":"https://openalex.org/C2778598663","wikidata":"https://www.wikidata.org/wiki/Q1407599","display_name":"Video content analysis","level":4,"score":0.28949999809265137},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.287200003862381},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C173386949","wikidata":"https://www.wikidata.org/wiki/Q192735","display_name":"Inertial frame of reference","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.2587999999523163},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.2558000087738037},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.25290000438690186},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.25270000100135803}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3810218","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3810218","pdf_url":null,"source":{"id":"https://openalex.org/S4210219751","display_name":"Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies","issn_l":"2474-9567","issn":["2474-9567"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2503.07259","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.07259","pdf_url":"https://arxiv.org/pdf/2503.07259","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:arXiv.org:2503.07259","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2503.07259","pdf_url":"https://arxiv.org/pdf/2503.07259","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2503.07259","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.07259","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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:10.1145/3810218","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3810218","pdf_url":null,"source":{"id":"https://openalex.org/S4210219751","display_name":"Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies","issn_l":"2474-9567","issn":["2474-9567"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies","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":{"The":[0,195],"goal":[1],"of":[2,114],"creating":[3],"intelligent,":[4],"human-centered":[5],"wearable":[6],"systems":[7],"for":[8,47,135],"continuous":[9,48],"activity":[10,30],"understanding":[11],"faces":[12],"a":[13,79,97,105],"fundamental":[14],"trade-off:":[15],"Egocentric":[16],"video-based":[17],"models":[18,189],"capture":[19],"rich":[20,126],"semantic":[21,86,127],"information":[22],"and":[23,40,99,116,157,166,175,186],"have":[24],"demonstrated":[25],"strong":[26,159],"performance":[27],"in":[28,190],"human":[29],"recognition":[31],"(HAR),":[32],"but":[33],"their":[34,45],"high":[35],"power":[36],"consumption,":[37],"privacy":[38],"concerns,":[39],"dependence":[41],"on":[42,139],"lighting":[43],"limit":[44],"feasibility":[46],"on-device":[49],"recognition.":[50],"In":[51],"contrast,":[52],"inertial":[53],"measurement":[54],"unit":[55],"(IMU)":[56],"sensors":[57],"offer":[58],"an":[59],"energy-efficient,":[60],"privacy-preserving":[61],"alternative,":[62],"yet":[63],"lack":[64],"large-scale":[65],"annotated":[66],"datasets,":[67],"leading":[68],"to":[69,90,103,109,124,181],"weaker":[70],"generalization.":[71,161],"To":[72],"bridge":[73],"this":[74,200],"gap,":[75],"we":[76],"propose":[77],"COMODO,":[78],"cross-modal":[80],"self-supervised":[81],"distillation":[82],"framework":[83],"that":[84,145],"transfers":[85],"knowledge":[87],"from":[88,129,163],"video":[89,101,115,130,174],"IMU":[91,117,122],"without":[92],"requiring":[93],"labels.":[94],"COMODO":[95,146,168],"leverages":[96],"pretrained":[98,173],"frozen":[100],"encoder":[102,123],"construct":[104],"dynamic":[106],"instance":[107],"queue":[108],"align":[110],"the":[111,121,179],"feature":[112],"distributions":[113],"embeddings.":[118],"This":[119],"enables":[120],"inherit":[125],"structure":[128],"while":[131],"maintaining":[132],"its":[133,164],"efficiency":[134],"real-world":[136],"applications.":[137],"Experiments":[138],"multiple":[140],"egocentric":[141],"HAR":[142],"datasets":[143],"show":[144],"consistently":[147],"improves":[148],"downstream":[149],"performance,":[150],"matching":[151],"or":[152],"surpassing":[153],"fully":[154],"supervised":[155],"models,":[156,177],"demonstrating":[158],"cross-dataset":[160],"Benefiting":[162],"simplicity":[165],"flexibility,":[167],"is":[169,197],"compatible":[170],"with":[171],"diverse":[172],"time-series":[176],"offering":[178],"potential":[180],"leverage":[182],"more":[183],"powerful":[184],"teacher":[185],"student":[187],"foundation":[188],"future":[191],"ubiquitous":[192],"computing":[193],"research.":[194],"code":[196],"available":[198],"at":[199],"repository:":[201],"https://github.com/cruiseresearchgroup/COMODO.":[202]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-09-27T00:00:00"}