{"id":"https://openalex.org/W4391220956","doi":"https://doi.org/10.3390/data9020021","title":"MHAiR: A Dataset of Audio-Image Representations for Multimodal Human Actions","display_name":"MHAiR: A Dataset of Audio-Image Representations for Multimodal Human Actions","publication_year":2024,"publication_date":"2024-01-25","ids":{"openalex":"https://openalex.org/W4391220956","doi":"https://doi.org/10.3390/data9020021"},"language":"en","primary_location":{"id":"doi:10.3390/data9020021","is_oa":true,"landing_page_url":"https://doi.org/10.3390/data9020021","pdf_url":"https://www.mdpi.com/2306-5729/9/2/21/pdf?version=1706178039","source":{"id":"https://openalex.org/S4210226510","display_name":"Data","issn_l":"2306-5729","issn":["2306-5729"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2306-5729/9/2/21/pdf?version=1706178039","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036110830","display_name":"Muhammad Bilal Shaikh","orcid":"https://orcid.org/0000-0001-9042-5018"},"institutions":[{"id":"https://openalex.org/I12079687","display_name":"Edith Cowan University","ror":"https://ror.org/05jhnwe22","country_code":"AU","type":"education","lineage":["https://openalex.org/I12079687"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Muhammad Bilal Shaikh","raw_affiliation_strings":["School of Engineering, Edith Cowan University, 270 Joondalup Drive, Joondalup, Perth, WA 6027, Australia"],"raw_orcid":"https://orcid.org/0000-0001-9042-5018","affiliations":[{"raw_affiliation_string":"School of Engineering, Edith Cowan University, 270 Joondalup Drive, Joondalup, Perth, WA 6027, Australia","institution_ids":["https://openalex.org/I12079687"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056138775","display_name":"Douglas Chai","orcid":"https://orcid.org/0000-0002-9004-7608"},"institutions":[{"id":"https://openalex.org/I12079687","display_name":"Edith Cowan University","ror":"https://ror.org/05jhnwe22","country_code":"AU","type":"education","lineage":["https://openalex.org/I12079687"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Douglas Chai","raw_affiliation_strings":["School of Engineering, Edith Cowan University, 270 Joondalup Drive, Joondalup, Perth, WA 6027, Australia"],"raw_orcid":"https://orcid.org/0000-0002-9004-7608","affiliations":[{"raw_affiliation_string":"School of Engineering, Edith Cowan University, 270 Joondalup Drive, Joondalup, Perth, WA 6027, Australia","institution_ids":["https://openalex.org/I12079687"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034900636","display_name":"Syed Mohammed Shamsul Islam","orcid":"https://orcid.org/0000-0002-3200-2903"},"institutions":[{"id":"https://openalex.org/I12079687","display_name":"Edith Cowan University","ror":"https://ror.org/05jhnwe22","country_code":"AU","type":"education","lineage":["https://openalex.org/I12079687"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Syed Mohammed Shamsul Islam","raw_affiliation_strings":["School of Science, Edith Cowan University, 270 Joondalup Drive, Joondalup, Perth, WA 6027, Australia"],"raw_orcid":"https://orcid.org/0000-0002-3200-2903","affiliations":[{"raw_affiliation_string":"School of Science, Edith Cowan University, 270 Joondalup Drive, Joondalup, Perth, WA 6027, Australia","institution_ids":["https://openalex.org/I12079687"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069697936","display_name":"Naveed Akhtar","orcid":"https://orcid.org/0000-0003-3406-673X"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Naveed Akhtar","raw_affiliation_strings":["School of Computing and Information Systems, The University of Melbourne, Melbourne Connect, 700 Swanston Street, Carlton, WA 3053, Australia"],"raw_orcid":"https://orcid.org/0000-0003-3406-673X","affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems, The University of Melbourne, Melbourne Connect, 700 Swanston Street, Carlton, WA 3053, Australia","institution_ids":["https://openalex.org/I165779595"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5036110830"],"corresponding_institution_ids":["https://openalex.org/I12079687"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1732},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1732},"fwci":0.4488,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.57920086,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"9","issue":"2","first_page":"21","last_page":"21"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9997000098228455,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9997000098228455,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.989799976348877,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9765999913215637,"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/computer-science","display_name":"Computer science","score":0.6519391536712646},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.6277546882629395},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4803520441055298},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.46555668115615845},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.404110312461853},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.36709412932395935},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.2982713580131531}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6519391536712646},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6277546882629395},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4803520441055298},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.46555668115615845},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.404110312461853},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36709412932395935},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2982713580131531}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3390/data9020021","is_oa":true,"landing_page_url":"https://doi.org/10.3390/data9020021","pdf_url":"https://www.mdpi.com/2306-5729/9/2/21/pdf?version=1706178039","source":{"id":"https://openalex.org/S4210226510","display_name":"Data","issn_l":"2306-5729","issn":["2306-5729"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data","raw_type":"journal-article"},{"id":"pmh:oai:ro.ecu.edu.au:ecuworks2022-2026-4398","is_oa":true,"landing_page_url":"https://ro.ecu.edu.au/ecuworks2022-2026/3397","pdf_url":null,"source":{"id":"https://openalex.org/S2765015692","display_name":"Australasian Journal of Paramedicine","issn_l":"2202-7270","issn":["2202-7270"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Research outputs 2022 to 2026","raw_type":"text"},{"id":"pmh:oai:RePEc:gam:jdataj:v:9:y:2024:i:2:p:21-:d:1326377","is_oa":false,"landing_page_url":"https://www.mdpi.com/2306-5729/9/2/21/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"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":"article"},{"id":"pmh:oai:doaj.org/article:709cacbc249242b2840d9c43727cdff7","is_oa":true,"landing_page_url":"https://doaj.org/article/709cacbc249242b2840d9c43727cdff7","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":"Data, Vol 9, Iss 2, p 21 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/data9020021","is_oa":true,"landing_page_url":"https://doi.org/10.3390/data9020021","pdf_url":"https://www.mdpi.com/2306-5729/9/2/21/pdf?version=1706178039","source":{"id":"https://openalex.org/S4210226510","display_name":"Data","issn_l":"2306-5729","issn":["2306-5729"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3406409465","display_name":null,"funder_award_id":"NIPG-2021-001","funder_id":"https://openalex.org/F4320315885","funder_display_name":"Australian Government"},{"id":"https://openalex.org/G7966873392","display_name":null,"funder_award_id":"NIPG-2021-001","funder_id":"https://openalex.org/F4320337300","funder_display_name":"Office of National Intelligence"}],"funders":[{"id":"https://openalex.org/F4320315885","display_name":"Australian Government","ror":"https://ror.org/0314h5y94"},{"id":"https://openalex.org/F4320337300","display_name":"Office of National Intelligence","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4391220956.pdf"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W2400288553","https://openalex.org/W2465313502","https://openalex.org/W2507009361","https://openalex.org/W2570915410","https://openalex.org/W2608988379","https://openalex.org/W2770804203","https://openalex.org/W2889985731","https://openalex.org/W2900595477","https://openalex.org/W2913133959","https://openalex.org/W2953327099","https://openalex.org/W2954996726","https://openalex.org/W2964109005","https://openalex.org/W2964350391","https://openalex.org/W2969121634","https://openalex.org/W3005865003","https://openalex.org/W3025948831","https://openalex.org/W3034658206","https://openalex.org/W3034768625","https://openalex.org/W3035757124","https://openalex.org/W3091959638","https://openalex.org/W3099319035","https://openalex.org/W3124591034","https://openalex.org/W3168640669","https://openalex.org/W3174760001","https://openalex.org/W3214007456","https://openalex.org/W4214777631","https://openalex.org/W4220894980","https://openalex.org/W4226025707","https://openalex.org/W4249723087","https://openalex.org/W4316660066","https://openalex.org/W4367663575","https://openalex.org/W4383532469","https://openalex.org/W4388893704","https://openalex.org/W4390736386","https://openalex.org/W6784043113","https://openalex.org/W6792861227","https://openalex.org/W6906515096","https://openalex.org/W6906603944","https://openalex.org/W6906665652","https://openalex.org/W6906746191","https://openalex.org/W6906752160"],"related_works":["https://openalex.org/W2755342338","https://openalex.org/W2058170566","https://openalex.org/W2036807459","https://openalex.org/W2775347418","https://openalex.org/W1969923398","https://openalex.org/W2166024367","https://openalex.org/W2772917594","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2079911747"],"abstract_inverted_index":{"Audio-image":[0],"representations":[1,13,123],"for":[2,89,106,114,127,146,175,190],"a":[3,27,55,103,128,156,187],"multimodal":[4],"human":[5,90,115,180],"action":[6,91,116],"(MHAiR)":[7],"dataset":[8,34,65,105,141,165],"contains":[9],"six":[10],"different":[11,195],"image":[12],"of":[14,23,57,110,131,170,179,194],"the":[15,20,24,38,63,108,168,177,192],"audio":[16,39,161],"signals":[17],"that":[18],"capture":[19],"temporal":[21],"dynamics":[22],"actions":[25],"in":[26],"very":[28],"compact":[29],"and":[30,62,72,93,118,138,173,183,199],"informative":[31],"way.":[32],"The":[33,76,140],"was":[35,66],"extracted":[36],"from":[37,44],"recordings":[40],"which":[41,85],"were":[42,80],"captured":[43,54],"an":[45],"existing":[46],"video":[47],"dataset,":[48],"i.e.,":[49],"UCF101.":[50],"Each":[51],"data":[52],"sample":[53],"duration":[56],"approximately":[58],"10":[59],"s":[60],"long,":[61],"overall":[64],"split":[67],"into":[68,83],"4893":[69],"training":[70],"samples":[71],"1944":[73],"testing":[74,191],"samples.":[75],"resulting":[77],"feature":[78],"sequences":[79],"then":[81],"converted":[82],"images,":[84],"can":[86,99,142,152,166],"be":[87,100,125,144,153],"used":[88,101,145],"recognition":[92,117],"other":[94],"related":[95,119],"tasks.":[96,120],"These":[97,121],"images":[98],"as":[102,134,186],"benchmark":[104,189],"evaluating":[107],"performance":[109,193],"machine":[111,196],"learning":[112,197],"models":[113,151,198],"audio-image":[122],"could":[124],"suitable":[126],"wide":[129],"range":[130],"applications,":[132],"such":[133],"surveillance,":[135],"healthcare":[136],"monitoring,":[137],"robotics.":[139],"also":[143,184],"transfer":[147],"learning,":[148],"where":[149],"pre-trained":[150],"fine-tuned":[154],"on":[155],"specific":[157,160],"task":[158],"using":[159],"images.":[162],"Thus,":[163],"this":[164],"facilitate":[167],"development":[169],"new":[171],"techniques":[172],"approaches":[174],"improving":[176],"accuracy":[178],"action-related":[181],"tasks":[182],"serve":[185],"standard":[188],"algorithms.":[200]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
