{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T00:30:20Z","timestamp":1726014620811},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,6,30]]},"DOI":"10.1109\/ijcnn60899.2024.10651281","type":"proceedings-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:35:05Z","timestamp":1725903305000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["CNN-Transformer Ensemble: Advancing Visual Piano Transcription with Global and Local Features"],"prefix":"10.1109","author":[{"given":"Yuqing","family":"Li","sequence":"first","affiliation":[{"name":"Huazhong University of Science and Technology,School of Electronic Information and Communications, Hubei Provincial Key Laboratory of Smart Internet Technology,Wuhan,China,430074"}]},{"given":"Ying","family":"Zhang","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology,School of Electronic Information and Communications, Hubei Provincial Key Laboratory of Smart Internet Technology,Wuhan,China,430074"}]},{"given":"Xianke","family":"Wang","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology,School of Electronic Information and Communications, Hubei Provincial Key Laboratory of Smart Internet Technology,Wuhan,China,430074"}]},{"given":"Ruimin","family":"Wu","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology,School of Electronic Information and Communications, Hubei Provincial Key Laboratory of Smart Internet Technology,Wuhan,China,430074"}]},{"given":"Wei","family":"Xu","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology,School of Electronic Information and Communications, Hubei Provincial Key Laboratory of Smart Internet Technology,Wuhan,China,430074"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s10844-013-0258-3"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/0-387-32845-9"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3121991"},{"key":"ref4","first-page":"246","article-title":"Sequence-to-sequence piano transcription with transformers","volume-title":"International Society for Music Information Retrieval Conference (ISMIR)","author":"Hawthorne"},{"journal-title":"Automatic piano transcription with hierarchical frequency-time transformer","year":"2023","author":"Toyama","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2473702"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-018-5803-1"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3409501.3409540"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053115"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00042"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IVCNZ.2013.6727030"},{"key":"ref13","article-title":"Detection of piano keys pressed in video","volume-title":"Tech. Rep","author":"Suteparuk","year":"2014"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1023\/b:visi.0000029664.99615.94"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2002.1017623"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSPW59220.2023.10193618"},{"key":"ref20","first-page":"23","article-title":"Onsets and frames: Dual-objective piano transcription","volume-title":"International Society for Music Information Retrieval Conference (ISMIR)","author":"Hawthorne"},{"key":"ref21","first-page":"315","article-title":"Evaluation of multiple-f0 estimation and tracking systems","author":"Bay","year":"2009","journal-title":"ISMIR"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.385"}],"event":{"name":"2024 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2024,6,30]]},"location":"Yokohama, Japan","end":{"date-parts":[[2024,7,5]]}},"container-title":["2024 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10649807\/10649898\/10651281.pdf?arnumber=10651281","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T07:36:24Z","timestamp":1725953784000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10651281\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/ijcnn60899.2024.10651281","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}