{"id":"https://openalex.org/W4307474240","doi":"https://doi.org/10.48550/arxiv.2210.14395","title":"IMU2CLIP: Multimodal Contrastive Learning for IMU Motion Sensors from Egocentric Videos and Text","display_name":"IMU2CLIP: Multimodal Contrastive Learning for IMU Motion Sensors from Egocentric Videos and Text","publication_year":2022,"publication_date":"2022-10-26","ids":{"openalex":"https://openalex.org/W4307474240","doi":"https://doi.org/10.48550/arxiv.2210.14395"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2210.14395","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.14395","pdf_url":"https://arxiv.org/pdf/2210.14395","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,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2210.14395","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091107431","display_name":"Seungwhan Moon","orcid":"https://orcid.org/0009-0003-2507-1884","observed_orcids":["https://orcid.org/0009-0003-2507-1884"]},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Moon, Seungwhan","raw_affiliation_strings":["Meta Reality Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Reality Labs","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061096363","display_name":"Andrea Madotto","orcid":"https://orcid.org/0000-0002-8672-715X","observed_orcids":["https://orcid.org/0000-0002-8672-715X"]},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Madotto, Andrea","raw_affiliation_strings":["Meta Reality Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Reality Labs","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021691940","display_name":"Zhaojiang Lin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lin, Zhaojiang","raw_affiliation_strings":["Meta Reality Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Reality Labs","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035904832","display_name":"Alireza Dirafzoon","orcid":"https://orcid.org/0000-0001-6143-3457","observed_orcids":["https://orcid.org/0000-0001-6143-3457"]},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dirafzoon, Alireza","raw_affiliation_strings":["Meta Reality Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Reality Labs","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056496877","display_name":"Aparajita Saraf","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saraf, Aparajita","raw_affiliation_strings":["Meta Reality Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Reality Labs","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025085069","display_name":"Amy Bearman","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bearman, Amy","raw_affiliation_strings":["Meta Reality Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Reality Labs","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020194007","display_name":"Babak Damavandi","orcid":"https://orcid.org/0009-0006-2598-1329","observed_orcids":["https://orcid.org/0009-0006-2598-1329"]},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Damavandi, Babak","raw_affiliation_strings":["Meta Reality Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Reality Labs","institution_ids":["https://openalex.org/I4210114444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210114444"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":51,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5605000257492065,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5605000257492065,"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/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.1996999979019165,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.07670000195503235,"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/inertial-measurement-unit","display_name":"inertial measurement unit","score":0.9049999713897705},{"id":"https://openalex.org/keywords/motion-sensors","display_name":"motion sensors","score":0.4790000021457672},{"id":"https://openalex.org/keywords/multimodal-contrastive-learning","display_name":"multimodal contrastive learning","score":0.878000020980835},{"id":"https://openalex.org/keywords/clip","display_name":"CLIP","score":0.7839999794960022},{"id":"https://openalex.org/keywords/egocentric-video","display_name":"egocentric video","score":0.8360000252723694},{"id":"https://openalex.org/keywords/activity-recognition","display_name":"activity recognition","score":0.7829999923706055},{"id":"https://openalex.org/keywords/pretraining","display_name":"pre-training","score":0.5529999732971191}],"concepts":[{"id":"https://openalex.org/C79061980","wikidata":"https://www.wikidata.org/wiki/Q941680","display_name":"Inertial measurement unit","level":2,"score":0.869476318359375},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7577559947967529},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.6641217470169067},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6312174201011658},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.549968957901001},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5285441279411316},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.49936580657958984},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4851249158382416},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.48345670104026794},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.429080069065094},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2210.14395","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.14395","pdf_url":"https://arxiv.org/pdf/2210.14395","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,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2210.14395","doi":"https://doi.org/10.48550/arxiv.2210.14395","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2210.14395","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,"listed_in":[],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2210.14395","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.14395","pdf_url":"https://arxiv.org/pdf/2210.14395","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,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4307474240.pdf","grobid_xml":"https://content.openalex.org/works/W4307474240.grobid-xml"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W2896457183","https://openalex.org/W3005700362","https://openalex.org/W4226352076","https://openalex.org/W4285606530","https://openalex.org/W7133208266"],"related_works":["https://openalex.org/W4389520547","https://openalex.org/W4408346015","https://openalex.org/W4409098643","https://openalex.org/W4294789972","https://openalex.org/W7131376991","https://openalex.org/W7164312201","https://openalex.org/W4406858963","https://openalex.org/W7124887492","https://openalex.org/W4402952279","https://openalex.org/W7203442430"],"abstract_inverted_index":{"We":[0,62],"present":[1],"IMU2CLIP,":[2],"a":[3,111],"novel":[4],"pre-training":[5],"approach":[6,35],"to":[7,38],"align":[8],"Inertial":[9],"Measurement":[10],"Unit":[11],"(IMU)":[12],"motion":[13,82],"sensor":[14],"recordings":[15],"with":[16,81],"video":[17],"and":[18,52,76],"text,":[19],"by":[20,44],"projecting":[21],"them":[22],"into":[23,47],"the":[24,57,93,105],"joint":[25],"representation":[26],"space":[27],"of":[28,108],"Contrastive":[29],"Language-Image":[30],"Pre-training":[31],"(CLIP).":[32],"The":[33],"proposed":[34],"allows":[36],"IMU2CLIP":[37,69,89,109],"translate":[39],"human":[40],"motions":[41],"(as":[42],"measured":[43],"IMU":[45],"sensors)":[46],"their":[48],"corresponding":[49],"textual":[50],"descriptions":[51],"videos":[53],"--":[54],"while":[55],"preserving":[56],"transitivity":[58],"across":[59],"these":[60],"modalities.":[61],"explore":[63],"several":[64],"new":[65,112],"IMU-based":[66],"applications":[67],"that":[68,88],"enables,":[70],"such":[71],"as":[72,110],"motion-based":[73],"media":[74],"retrieval":[75],"natural":[77],"language":[78],"reasoning":[79],"tasks":[80],"data.":[83],"In":[84],"addition,":[85],"we":[86],"show":[87],"can":[90],"significantly":[91],"improve":[92],"downstream":[94],"performance":[95],"when":[96],"fine-tuned":[97],"for":[98],"each":[99],"application":[100],"(e.g.":[101],"activity":[102],"recognition),":[103],"demonstrating":[104],"universal":[106],"usage":[107],"pre-trained":[113],"resource.":[114],"Our":[115],"code":[116],"will":[117],"be":[118],"made":[119],"publicly":[120],"available.":[121]},"counts_by_year":[{"year":2026,"cited_by_count":14},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":9}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2022-11-02T00:00:00"}