{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:21:20Z","timestamp":1775578880208,"version":"3.50.1"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Academia Sinica Thematic Research Program","award":["AS-TP-111-M02"],"award-info":[{"award-number":["AS-TP-111-M02"]}]},{"DOI":"10.13039\/100020595","name":"National Science and Technology Council","doi-asserted-by":"publisher","award":["112-2423-H-001-008-MY3"],"award-info":[{"award-number":["112-2423-H-001-008-MY3"]}],"id":[{"id":"10.13039\/100020595","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/taslp.2024.3407529","type":"journal-article","created":{"date-parts":[[2024,5,30]],"date-time":"2024-05-30T17:56:23Z","timestamp":1717091783000},"page":"4157-4170","source":"Crossref","is-referenced-by-count":6,"title":["MOSA: Music Motion With Semantic Annotation Dataset for Cross-Modal Music Processing"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0716-9330","authenticated-orcid":false,"given":"Yu-Fen","family":"Huang","sequence":"first","affiliation":[{"name":"Institute of Information Science, Academia Sinica, Taipei, Taiwan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4607-9258","authenticated-orcid":false,"given":"Nikki","family":"Moran","sequence":"additional","affiliation":[{"name":"Reid School of Music, University of Edinburgh, Edinburgh, U.K."}]},{"given":"Simon","family":"Coleman","sequence":"additional","affiliation":[{"name":"Institute for Sport, Physical Education, Health Sciences (ISPEHS), University of Edinburgh, Edinburgh, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3737-5978","authenticated-orcid":false,"given":"Jon","family":"Kelly","sequence":"additional","affiliation":[{"name":"Institute for Sport, Physical Education, Health Sciences (ISPEHS), University of Edinburgh, Edinburgh, U.K."}]},{"given":"Shun-Hwa","family":"Wei","sequence":"additional","affiliation":[{"name":"Department of Physical Therapy, Assistive Technology, National Yang Ming Chiao Tung University, Hsinchu, Taiwan"}]},{"given":"Po-Yin","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Physical Therapy, Assistive Technology, National Yang Ming Chiao Tung University, Hsinchu, Taiwan"}]},{"given":"Yun-Hsin","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Physical Therapy, Assistive Technology, National Yang Ming Chiao Tung University, Hsinchu, Taiwan"}]},{"given":"Tsung-Ping","family":"Chen","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Academia Sinica, Taipei, Taiwan"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6542-0192","authenticated-orcid":false,"given":"Yu-Chia","family":"Kuo","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Academia Sinica, Taipei, Taiwan"}]},{"given":"Yu-Chi","family":"Wei","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Academia Sinica, Taipei, Taiwan"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6482-3270","authenticated-orcid":false,"given":"Chih-Hsuan","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Academia Sinica, Taipei, Taiwan"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3267-3799","authenticated-orcid":false,"given":"Da-Yu","family":"Huang","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Academia Sinica, Taipei, Taiwan"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3293-2517","authenticated-orcid":false,"given":"Hsuan-Kai","family":"Kao","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Academia Sinica, Taipei, Taiwan"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6571-4760","authenticated-orcid":false,"given":"Ting-Wei","family":"Lin","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Academia Sinica, Taipei, Taiwan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4275-8832","authenticated-orcid":false,"given":"Li","family":"Su","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Academia Sinica, Taipei, Taiwan"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1037\/pmu0000186"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP48831.2020.9287124"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2856090"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1080\/09298215.2014.922999"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3077981.3078032"},{"key":"ref6","first-page":"157","article-title":"A multi-modal dance corpus for research into interaction between humans in virtual environments","volume":"7","author":"Essid","year":"2013","journal-title":"J. Multimodal User Interfaces"},{"key":"ref7","article-title":"Vision-based detection of acoustic timed events: A case study on clarinet note onsets","author":"Bazzica","year":"2017"},{"key":"ref8","first-page":"156","article-title":"ENST-drums: An extensive audio-visual database for drum signals processing","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Gillet","year":"2006"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46282-0_5"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_35"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00037"},{"key":"ref12","first-page":"501","article-title":"AIST dance video database: Multi-genre, multi-dancer, and multi-camera database for dance information processing","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Tsuchida","year":"2019"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01315"},{"key":"ref14","first-page":"347","article-title":"Performance error detection and post-processing for fast and accurate symbolic music alignment","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Nakamura","year":"2017"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_44"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806359"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123399"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01031"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9533662"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3126686.3126723"},{"key":"ref21","first-page":"218","article-title":"Skeleton plays piano: Online generation of pianist body movements from MIDI performance","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Li","year":"2018"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00790"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054463"},{"key":"ref24","first-page":"115","article-title":"Identifying expressive semantics in orchestral conducting kinematics","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Huang","year":"2019"},{"key":"ref25","first-page":"85","article-title":"Joint analysis of mode and playing technique in guqin performance with machine learning","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Huang","year":"2020"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbiomech.2016.05.007"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3389\/fspor.2020.00050"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20014"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_25"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1136\/bjsports-2014-093546"},{"key":"ref32","article-title":"Youtube-8m: A large-scale video classification benchmark","author":"Abu-El-Haija","year":"2016"},{"key":"ref33","article-title":"Guide to the carnegie mellon university multimodal activity (CMU-MMAC)) database","author":"Torre","year":"2009"},{"key":"ref34","article-title":"Lets dance: Learning from online dance videos","author":"Castro","year":"2018"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-34234-9_41"},{"key":"ref36","first-page":"113","article-title":"Semi-supervised violin fingering generation using variational autoencoders","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Cheung","year":"2021"},{"key":"ref37","article-title":"C-motion wiki documentation tutorial: Plug-in gait full-body","year":"2023"},{"key":"ref38","article-title":"Vicon software","year":"2024"},{"key":"ref39","article-title":"QTM qualisys track manager","year":"2024"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201302"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s00034-009-9130-7"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21105\/joss.03391"},{"key":"ref44","first-page":"84","article-title":"Intuitive analysis, creation and manipulation of midi data with pretty_midi","volume-title":"Proc. 15th Int. Soc. Music Inf. Retrieval Conf. Late Breaking Demo Papers","author":"Raffel","year":"2014"},{"key":"ref45","first-page":"255","article-title":"Joint beat and downbeat tracking with recurrent neural networks","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Bck","year":"2016"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682870"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747048"},{"key":"ref48","first-page":"486","article-title":"Multi-task learning of tempo and beat: Learning one to improve the other","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Bck","year":"2019"},{"key":"ref49","article-title":"Dancing to music","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lee","year":"2019"},{"key":"ref50","first-page":"172","volume-title":"Proc. 10th Sound Music Comput. Conf.","author":"Burger","year":"2013"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45103-X_50"},{"key":"ref52","article-title":"Mediapipe hands: On-device real-time hand tracking","author":"Zhang","year":"2020"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.79"},{"key":"ref55","article-title":"MIR_EVAL: A transparent implementation of common MIR metrics","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","volume":"10","author":"Raffel","year":"2014"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2973795"},{"key":"ref57","first-page":"809","article-title":"Analysis of expressive musical terms in violin using score-informed and expression-based audio features","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Li","year":"2015"},{"key":"ref58","first-page":"9","article-title":"Sparse cepstral, phase codes for guitar playing technique classification","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Su","year":"2014"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095225"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.3389\/fdigh.2018.00025"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-018-3758-9"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413848"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13310"},{"key":"ref64","article-title":"GANs trained by a two time-scale update rule converge to a local nash equilibrium","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Heusel","year":"2017"},{"key":"ref65","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn","author":"Radford","year":"2021"},{"key":"ref66","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6570655\/10304349\/10542439.pdf?arnumber=10542439","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,23]],"date-time":"2024-09-23T17:29:52Z","timestamp":1727112592000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10542439\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3407529","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}