{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,27]],"date-time":"2025-09-27T13:49:53Z","timestamp":1758980993986,"version":"3.37.3"},"reference-count":34,"publisher":"IEEE","funder":[{"DOI":"10.13039\/100010663","name":"European Research Council (ERC)","doi-asserted-by":"publisher","award":["670035"],"award-info":[{"award-number":["670035"]}],"id":[{"id":"10.13039\/100010663","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,8,23]]},"DOI":"10.23919\/eusipco54536.2021.9616287","type":"proceedings-article","created":{"date-parts":[[2021,12,8]],"date-time":"2021-12-08T21:55:53Z","timestamp":1639000553000},"page":"356-360","source":"Crossref","is-referenced-by-count":4,"title":["Multi-modal Conditional Bounding Box Regression for Music Score Following"],"prefix":"10.23919","author":[{"given":"Florian","family":"Henkel","sequence":"first","affiliation":[]},{"given":"Gerhard","family":"Widmer","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","article-title":"SGDR: Stochastic Gradient Descent with Warm Restarts","author":"loshchilov","year":"0","journal-title":"Proc of the 5th Int Conference on Learning Representations (ICLR)"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015015"},{"key":"ref31","article-title":"Exact solutions to the nonlinear dynamics of learning in deep linear neural networks","author":"saxe","year":"2013","journal-title":"ArXiv Preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00065"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-21945-5"},{"key":"ref10","article-title":"Robust Polyphonic Midi Score Following with Hidden Markov Models","author":"schwarz","year":"0","journal-title":"International Computer Music Conference"},{"key":"ref11","article-title":"An On-Line Time Warping Algorithm for Tracking Musical Performances","author":"dixon","year":"0","journal-title":"Proc of the 19th Int Joint Conference on Artificial Intelligence (IJCAI)"},{"key":"ref12","article-title":"Towards Score Following in Sheet Music Images","author":"dorfer","year":"0","journal-title":"Proc of the 17th Int Society for Music Information Retrieval Conference (ISMIR)"},{"key":"ref13","article-title":"Learning to Listen, Read, and Follow: Score following as a Reinforcement Learning Game","author":"dorfer","year":"0","journal-title":"Proc of the 19th Int Society for Music Information Retrieval Conference (ISMIR)"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.5334\/tismir.31"},{"key":"ref15","article-title":"Learning to Read and Follow Music in Complete Score Sheet Images","author":"henkel","year":"0","journal-title":"Proc of the 21st Int Society for Music Information Retrieval Conference (ISMIR)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.5334\/tismir.12"},{"key":"ref18","article-title":"Audio-Conditioned U-Net for Position Estimation in Full Sheet Images","author":"henkel","year":"0","journal-title":"Proc of the 2nd Int Workshop on Reading Music Systems"},{"key":"ref19","article-title":"FiLM: Visual reasoning with a general conditioning layer","author":"perez","year":"0","journal-title":"Proc of the 32nd AAAI Conference on Artificial Intelligence"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.23919\/Eusipco47968.2020.9287625"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2017.8081512"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1155\/2011\/384651"},{"key":"ref6","article-title":"Automatic Page Turning for Musicians via Real-Time Machine Listening","author":"arzt","year":"0","journal-title":"Proc of the 18th Eur Conference on Artificial Intelligence (ECAI)"},{"key":"ref29","article-title":"Decoupled Weight Decay Regularization","author":"loshchilov","year":"0","journal-title":"Proc of the 7th Int Conference on Learning Representations (ICLR)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134092"},{"journal-title":"Flexible and Robust Music Tracking","year":"2016","author":"arzt","key":"ref8"},{"key":"ref7","article-title":"Artificial Intelligence in the Concertgebouw","author":"arzt","year":"0","journal-title":"Proc of the 24th Int Joint Conference on Artificial Intelligence (IJCAI)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1661258"},{"key":"ref9","article-title":"Au-toregressive Hidden Semi-Markov Model of Symbolic Music for Score Following","author":"nakamura","year":"0","journal-title":"Proc of the 16th Int Society for Music Information Retrieval Conference (ISMIR)"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5946373"},{"key":"ref20","article-title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","author":"ren","year":"2015","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref22","article-title":"TResNet: High Performance GPU-Dedicated Architecture","author":"ridnik","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_7"},{"key":"ref24","article-title":"Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)","author":"clevert","year":"0","journal-title":"Proc of the 4th Int Conference on Learning Representations (ICLR)"},{"key":"ref23","article-title":"Layer Normalization","author":"ba","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref26","article-title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","author":"ioffe","year":"0","journal-title":"Proc of the International Conference on Machine Learning (ICML)"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"}],"event":{"name":"2021 29th European Signal Processing Conference (EUSIPCO)","start":{"date-parts":[[2021,8,23]]},"location":"Dublin, Ireland","end":{"date-parts":[[2021,8,27]]}},"container-title":["2021 29th European Signal Processing Conference (EUSIPCO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9615915\/9615917\/09616287.pdf?arnumber=9616287","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,2,15]],"date-time":"2022-02-15T06:44:21Z","timestamp":1644907461000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9616287\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,23]]},"references-count":34,"URL":"https:\/\/doi.org\/10.23919\/eusipco54536.2021.9616287","relation":{},"subject":[],"published":{"date-parts":[[2021,8,23]]}}}