Please use this identifier to cite or link to this item:
Title: DeepScores and Deep Watershed Detection : current state and open issues
Authors : Elezi, Ismail
Tuggener, Lukas
Pelillo, Marcello
Stadelmann, Thilo
Proceedings: Proceedings of the 1st International Workshop on Reading Music Systems
Pages : 13
Pages to: 14
Conference details: 1st International Workshop on Reading Music Systems at ISMIR 2018, Paris, France, 20 September 2018
Publisher / Ed. Institution : Society for Music Information Retrieval
Publisher / Ed. Institution: Paris
Issue Date: 20-Sep-2018
License (according to publishing contract) : CC BY-NC 4.0: Attribution - Non commercial 4.0 International
Type of review: Peer review (Publication)
Language : English
Subjects : Optical music recognition; Deep learning
Subject (DDC) : 004: Computer science
Abstract: This paper gives an overview of our current Optical Music Recognition (OMR) research. We recently released the OMR data set DeepScores as well as the object detection method Deep Watershed Detector. We are currently taking some additional steps to improve both of them. Here we summarize current and future efforts, aimed at improving usefulness on real-world tasks and tackling extreme class imbalance.
Departement: School of Engineering
Organisational Unit: Institute of Applied Information Technology (InIT)
Publication type: Conference Paper
DOI : 10.21256/zhaw-4777
Published as part of the ZHAW project : DeepScore: Digitales Notenpult mit musikalischem Verst√§ndnis durch Active Sheet Technologie
Appears in Collections:Publikationen School of Engineering

Files in This Item:
File Description SizeFormat 
2018_Elezi_DeepScores and Deep Watershed Detection_WORMS_proceedings.pdf2.15 MBAdobe PDFThumbnail

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.