{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T23:32:15Z","timestamp":1743118335400,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":28,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819984312"},{"type":"electronic","value":"9789819984329"}],"license":[{"start":{"date-parts":[[2023,12,24]],"date-time":"2023-12-24T00:00:00Z","timestamp":1703376000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,12,24]],"date-time":"2023-12-24T00:00:00Z","timestamp":1703376000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-981-99-8432-9_32","type":"book-chapter","created":{"date-parts":[[2023,12,23]],"date-time":"2023-12-23T08:02:17Z","timestamp":1703318537000},"page":"400-411","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["End-to-End Optical Music Recognition with\u00a0Attention Mechanism and\u00a0Memory Units Optimization"],"prefix":"10.1007","author":[{"given":"Ruichen","family":"He","sequence":"first","affiliation":[]},{"given":"Junfeng","family":"Yao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,12,24]]},"reference":[{"key":"32_CR1","unstructured":"Shatri, E., Fazekas, G.: Optical music recognition: state of the art and major challenges (2020). arXiv:abs\/2006.07885"},{"key":"32_CR2","doi-asserted-by":"publisher","unstructured":"Pacha, A., Calvo-Zaragoza, J., Jan Haji\u010d, J.: Learning notation graph construction for full- pipeline optical music recognition. In: Proceedings of the 20th International Society for Music Information Retrieval Conference, pp. 75\u201382. ISMIR, Delft, The Netherlands (2019). https:\/\/doi.org\/10.5281\/zenodo.3527744","DOI":"10.5281\/zenodo.3527744"},{"key":"32_CR3","doi-asserted-by":"crossref","unstructured":"Dorfer, M., Arzt, A., Widmer, G.: Learning audio-sheet music correspondences for score identification and offline alignment. In: International Society for Music Information Retrieval Conference (2017)","DOI":"10.5334\/tismir.12"},{"key":"32_CR4","unstructured":"Moss, F.C., K\u00f6ster, M., Femminis, M., M\u00e9trailler, C., Bavaud, F.: Digitizing a 19th-century music theory debate for computational analysis, vol. 2989, pp. 12. 159\u2013170. CEUR Workshop Proceedings (2021). http:\/\/infoscience.epfl.ch\/record\/289818"},{"key":"32_CR5","doi-asserted-by":"publisher","unstructured":"G\u00e9raud, T.: A morphological method for music score staff removal. In: 2014 IEEE International Conference on Image Processing (ICIP), pp. 2599\u20132603 (2014). https:\/\/doi.org\/10.1109\/ICIP.2014.7025526","DOI":"10.1109\/ICIP.2014.7025526"},{"key":"32_CR6","unstructured":"Edirisooriya, S., Dong, H.W., McAuley, J., Berg-Kirkpatrick, T.: An empirical evaluation of end-to-end polyphonic optical music recognition (2021)"},{"key":"32_CR7","doi-asserted-by":"crossref","unstructured":"Dosovitskiy, A., et al.: FlowNet: learning optical flow with convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.316"},{"key":"32_CR8","doi-asserted-by":"publisher","unstructured":"Pacha, A., Eidenberger, H.: Towards a universal music symbol classifier. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol. 02, pp. 35\u201336 (2017). https:\/\/doi.org\/10.1109\/ICDAR.2017.265","DOI":"10.1109\/ICDAR.2017.265"},{"key":"32_CR9","doi-asserted-by":"publisher","unstructured":"Raphael, C., Wang, J.: New approaches to optical music recognition. In: Proceedings of the 12th International Society for Music Information Retrieval Conference, pp. 305\u2013310. ISMIR, Miami, United States (2011). https:\/\/doi.org\/10.5281\/zenodo.1414856","DOI":"10.5281\/zenodo.1414856"},{"key":"32_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1007\/978-3-642-12242-2_42","volume-title":"Applications of Evolutionary Computation","author":"MA Kaliakatsos-Papakostas","year":"2010","unstructured":"Kaliakatsos-Papakostas, M.A., Epitropakis, M.G., Vrahatis, M.N.: Musical composer identification through probabilistic and feedforward neural networks. In: Di Chio, C., Brabazon, A., Di Caro, G.A., Ebner, M., Farooq, M., Fink, A., Grahl, J., Greenfield, G., Machado, P., O\u2019Neill, M., Tarantino, E., Urquhart, N. (eds.) EvoApplications 2010. LNCS, vol. 6025, pp. 411\u2013420. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-12242-2_42"},{"key":"32_CR11","doi-asserted-by":"publisher","unstructured":"R\u00edos-Vila, A., Calvo-Zaragoza, J., I\u00f1esta, J.M.: Exploring the two-dimensional nature of music notation for score recognition with end-to-end approaches. In: 2020 17th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 193\u2013198 (2020). https:\/\/doi.org\/10.1109\/ICFHR2020.2020.00044","DOI":"10.1109\/ICFHR2020.2020.00044"},{"issue":"4","key":"32_CR12","doi-asserted-by":"publisher","first-page":"606","DOI":"10.3390\/app8040606","volume":"8","author":"CZ Jorge","year":"2018","unstructured":"Jorge, C.Z., David, R.: End-to-end neural optical music recognition of monophonic scores. Appl. Sci. 8(4), 606 (2018)","journal-title":"Appl. Sci."},{"key":"32_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1007\/978-3-030-31321-0_13","volume-title":"Pattern Recognition and Image Analysis","author":"M Alfaro-Contreras","year":"2019","unstructured":"Alfaro-Contreras, M., Calvo-Zaragoza, J., I\u00f1esta, J.M.: Approaching end-to-end optical music recognition for homophonic scores. In: Morales, A., Fierrez, J., S\u00e1nchez, J.S., Ribeiro, B. (eds.) IbPRIA 2019. LNCS, vol. 11868, pp. 147\u2013158. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-31321-0_13"},{"key":"32_CR14","doi-asserted-by":"publisher","unstructured":"Hankinson, A., Roland, P., Fujinaga, I.: The music encoding initiative as a document- encoding framework. In: Proceedings of the 12th International Society for Music Information Retrieval Conference, pp. 293\u2013298. ISMIR, Miami, United States (2011). https:\/\/doi.org\/10.5281\/zenodo.1417609","DOI":"10.5281\/zenodo.1417609"},{"key":"32_CR15","unstructured":"Kim, S., Lee, H., Park, S., Lee, J., Choi, K.: Deep composer classification using symbolic representation (2020)"},{"key":"32_CR16","unstructured":"Pinheiro, P.H.O., Collobert, R.: Recurrent convolutional neural networks for scene parsing (2013). arXiv:abs\/1306.2795"},{"key":"32_CR17","unstructured":"Tsai, T.J., Ji, K.: Composer style classification of piano sheet music images using language model pretraining (2020). arXiv:abs\/2007.14587"},{"key":"32_CR18","doi-asserted-by":"publisher","first-page":"470","DOI":"10.1007\/978-3-031-04881-4_37","volume-title":"Pattern Recognition and Image Analysis","author":"A R\u00edos-Vila","year":"2022","unstructured":"R\u00edos-Vila, A., I\u00f1esta, J.M., Calvo-Zaragoza, J.: On the use of transformers for end-to-end optical music recognition. In: Pinho, A.J., Georgieva, P., Teixeira, L.F., S\u00e1nchez, J.A. (eds.) Pattern Recognition and Image Analysis, pp. 470\u2013481. Springer International Publishing, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-04881-4_37"},{"key":"32_CR19","unstructured":"Merity, S., Keskar, N.S., Socher, R.: Regularizing and optimizing LSTM language models (2017). arXiv:abs\/1708.02182"},{"key":"32_CR20","unstructured":"Melis, G., Kocisk\u00fd, T., Blunsom, P.: Mogrifier LSTM (2019). arXiv:abs\/1909.01792"},{"key":"32_CR21","doi-asserted-by":"publisher","unstructured":"Wang, Q., Wu, B., Zhu, P., Li, P., Zuo, W., Hu, Q.: ECA-Net: efficient channel attention for deep convolutional neural networks. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11531\u201311539 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.01155","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"32_CR22","doi-asserted-by":"publisher","unstructured":"Tuggener, L., Elezi, I., Schmidhuber, J., Pelillo, M., Stadelmann, T.: Deepscores-a dataset for segmentation, detection and classification of tiny objects. In: 2018 24th International Conference on Pattern Recognition (ICPR), pp. 3704\u20133709 (2018). https:\/\/doi.org\/10.1109\/ICPR.2018.8545307","DOI":"10.1109\/ICPR.2018.8545307"},{"key":"32_CR23","unstructured":"Shatri, E., Fazekas, G.: DoReMi: first glance at a universal OMR dataset (2021). arXiv:bs\/2107.07786"},{"key":"32_CR24","doi-asserted-by":"publisher","unstructured":"Liu, A., et al.: Residual recurrent CRNN for end-to-end optical music recognition on monophonic scores. In: Proceedings of the 2021 Workshop on Multi-Modal Pre-Training for Multimedia Understanding, MMPT \u201921, pp. 23\u201327. Association for Computing Machinery, New York (2021). https:\/\/doi.org\/10.1145\/3463945.3469056","DOI":"10.1145\/3463945.3469056"},{"key":"32_CR25","doi-asserted-by":"publisher","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7132\u20137141 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00745","DOI":"10.1109\/CVPR.2018.00745"},{"key":"32_CR26","doi-asserted-by":"publisher","unstructured":"Liu, Y., Chen, H., Shen, C., He, T., Jin, L., Wang, L.: ABCNet: real-time scene text spotting with adaptive Bezier-curve network. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9806\u20139815 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00983","DOI":"10.1109\/CVPR42600.2020.00983"},{"key":"32_CR27","series-title":"Lecture Notes in Computer Science()","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-01234-2_1","volume-title":"Computer Vision - ECCV 2018","author":"S Woo","year":"2018","unstructured":"Woo, S., Park, J., Lee, J.Y., Kweon, I.S.: CBAM: convolutional block attention module. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision - ECCV 2018. Lecture Notes in Computer Science(), vol. 11211, pp. 3\u201319. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_1"},{"key":"32_CR28","doi-asserted-by":"crossref","unstructured":"Dai, Y., Gieseke, F., Oehmcke, S., Wu, Y., Barnard, K.: Attentional feature fusion. In: 2021 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 3559\u20133568 (2020)","DOI":"10.1109\/WACV48630.2021.00360"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-8432-9_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,23]],"date-time":"2023-12-23T08:06:50Z","timestamp":1703318810000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-8432-9_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,24]]},"ISBN":["9789819984312","9789819984329"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-8432-9_32","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023,12,24]]},"assertion":[{"value":"24 December 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Xiamen","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/prcv2023.xmu.edu.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1420","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"532","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"37% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3,78","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3,69","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}