{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T08:38:05Z","timestamp":1742978285359,"version":"3.40.3"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031500688"},{"type":"electronic","value":"9783031500695"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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\/978-3-031-50069-5_2","type":"book-chapter","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T06:02:34Z","timestamp":1705644154000},"page":"3-15","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Leveraging Computer Vision Networks for\u00a0Guitar Tablature Transcription"],"prefix":"10.1007","author":[{"given":"Charbel","family":"El Achkar","sequence":"first","affiliation":[]},{"given":"Rapha\u00ebl","family":"Couturier","sequence":"additional","affiliation":[]},{"given":"Abdallah","family":"Makhoul","sequence":"additional","affiliation":[]},{"given":"Talar","family":"At\u00e9chian","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,1,20]]},"reference":[{"key":"2_CR1","unstructured":"Baevski, A., Auli, M.: Adaptive input representations for neural language modeling. arXiv preprint arXiv:1809.10853 (2018)"},{"issue":"3","key":"2_CR2","doi-asserted-by":"publisher","first-page":"915","DOI":"10.1109\/TASL.2011.2174227","volume":"20","author":"AM Barbancho","year":"2012","unstructured":"Barbancho, A.M., Klapuri, A., Tardon, L.J., Barbancho, I.: Automatic transcription of guitar chords and fingering from audio. IEEE Trans. Audio Speech Lang. Process. 20(3), 915\u2013921 (2012). https:\/\/doi.org\/10.1109\/TASL.2011.2174227","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"issue":"6","key":"2_CR3","doi-asserted-by":"publisher","first-page":"1857","DOI":"10.1109\/TASL.2012.2191281","volume":"20","author":"I Barbancho","year":"2012","unstructured":"Barbancho, I., Tardon, L.J., Sammartino, S., Barbancho, A.M.: Inharmonicity-based method for the automatic generation of guitar tablature. IEEE Trans. Audio Speech Lang. Process. 20(6), 1857\u20131868 (2012). https:\/\/doi.org\/10.1109\/TASL.2012.2191281","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"2_CR4","doi-asserted-by":"crossref","unstructured":"Bayoudh, K., Knani, R., Hamdaoui, F., Mtibaa, A.: A survey on deep multimodal learning for computer vision: advances, trends, applications, and datasets. The Visual Computer, pp. 1\u201332 (2021)","DOI":"10.1007\/s00371-021-02166-7"},{"key":"2_CR5","doi-asserted-by":"crossref","unstructured":"Cwitkowitz, F., Hirvonen, T., Klapuri, A.: Fretnet: Continuous-valued pitch contour streaming for polyphonic guitar tablature transcription. arXiv preprint arXiv:2212.03023 (2022)","DOI":"10.1109\/ICASSP49357.2023.10094825"},{"key":"2_CR6","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"2_CR7","doi-asserted-by":"publisher","first-page":"752","DOI":"10.1007\/978-3-030-92310-5_87","volume-title":"Neural Information Processing","author":"C El Achkar","year":"2021","unstructured":"El Achkar, C., Couturier, R., At\u00e9chian, T., Makhoul, A.: Combining reduction and dense blocks for music genre classification. In: Mantoro, T., Lee, M., Ayu, M.A., Wong, K.W., Hidayanto, A.N. (eds.) Neural Information Processing, pp. 752\u2013760. Springer, Cham (2021)"},{"key":"2_CR8","unstructured":"Fuentes, B., Badeau, R., Richard, G.: Blind harmonic adaptive decomposition applied to supervised source separation. In: 2012 Proceedings of the 20th European Signal Processing Conference (EUSIPCO), pp. 2654\u20132658 (2012)"},{"key":"2_CR9","doi-asserted-by":"publisher","unstructured":"G\u00f3mez, J.S., Abe\u00dfer, J., Cano, E.: Jazz Solo Instrument classification with convolutional neural networks, source separation, and transfer learning. In: Proceedings of the 19th International Society for Music Information Retrieval Conference, pp. 577\u2013584. ISMIR, Paris, France, September 2018. https:\/\/doi.org\/10.5281\/zenodo.1492481","DOI":"10.5281\/zenodo.1492481"},{"issue":"1","key":"2_CR10","doi-asserted-by":"publisher","first-page":"208","DOI":"10.1109\/TASLP.2016.2632307","volume":"25","author":"Y Han","year":"2017","unstructured":"Han, Y., Kim, J., Lee, K.: Deep convolutional neural networks for predominant instrument recognition in polyphonic music. IEEE\/ACM Trans. Audio Speech Lang. Process. 25(1), 208\u2013221 (2017). https:\/\/doi.org\/10.1109\/TASLP.2016.2632307","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"2_CR11","doi-asserted-by":"publisher","unstructured":"Humphrey, E.J., Bello, J.P.: From music audio to chord tablature: Teaching deep convolutional networks toplay guitar. In: 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6974\u20136978 (2014). https:\/\/doi.org\/10.1109\/ICASSP.2014.6854952","DOI":"10.1109\/ICASSP.2014.6854952"},{"key":"2_CR12","doi-asserted-by":"crossref","unstructured":"Kim, S., Hayashi, T., Toda, T.: Note-level automatic guitar transcription using attention mechanism. In: 2022 30th European Signal Processing Conference (EUSIPCO), pp. 229\u2013233. IEEE (2022)","DOI":"10.23919\/EUSIPCO55093.2022.9909659"},{"issue":"5","key":"2_CR13","doi-asserted-by":"publisher","first-page":"2065","DOI":"10.1007\/s00371-022-02465-7","volume":"39","author":"J Li","year":"2023","unstructured":"Li, J., Wei, L., Wen, Y., Liu, X., Wang, H.: An approach to continuous hand movement recognition using semg based on features fusion. Vis. Comput. 39(5), 2065\u20132079 (2023)","journal-title":"Vis. Comput."},{"key":"2_CR14","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"2_CR15","doi-asserted-by":"publisher","unstructured":"Maaiveld, T., Driedger, J., Yela, D., Mero\u00f1o-Pe\u00f1uela, A.: Automatic tablature estimation with convolutional neural networks: Approaches and limitations (04 2021). https:\/\/doi.org\/10.13140\/RG.2.2.13906.48320","DOI":"10.13140\/RG.2.2.13906.48320"},{"key":"2_CR16","unstructured":"Schl\u00fcter, J., Lehner, B.: Zero-mean convolutions for level-invariant singing voice detection, September 2018"},{"issue":"5","key":"2_CR17","doi-asserted-by":"publisher","first-page":"927","DOI":"10.1109\/TASLP.2016.2533858","volume":"24","author":"S Sigtia","year":"2016","unstructured":"Sigtia, S., Benetos, E., Dixon, S.: An end-to-end neural network for polyphonic piano music transcription. IEEE\/ACM Trans. Audio Speech Lang. Process. 24(5), 927\u2013939 (2016). https:\/\/doi.org\/10.1109\/TASLP.2016.2533858","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"2_CR18","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.: Inception-v4, inception-resnet and the impact of residual connections on learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 31 (2017)","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"2_CR19","unstructured":"Tan, M., Le, Q.: Efficientnet: Rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning, pp. 6105\u20136114. PMLR (2019)"},{"key":"2_CR20","unstructured":"Tuohy, D.R., Potter, W.D.: An evolved neural network\/hc hybrid for tablature creation in ga-based guitar arranging. In: International Conference on Mathematics and Computing (2006)"},{"key":"2_CR21","unstructured":"Vaswani, A., et al.: Attention is all you need. Advances in neural information processing systems 30 (2017)"},{"key":"2_CR22","unstructured":"Wang, Q., et al.: Learning deep transformer models for machine translation. arXiv preprint arXiv:1906.01787 (2019)"},{"key":"2_CR23","doi-asserted-by":"publisher","unstructured":"Wiggins, A., Kim, Y.: Guitar Tablature Estimation with a Convolutional Neural Network. In: Proceedings of the 20th International Society for Music Information Retrieval Conference, pp. 284\u2013291. ISMIR, Delft, The Netherlands, November 2019. https:\/\/doi.org\/10.5281\/zenodo.3527800","DOI":"10.5281\/zenodo.3527800"},{"issue":"2","key":"2_CR24","first-page":"43","volume":"7","author":"A Wiggins","year":"2020","unstructured":"Wiggins, A., Kim, Y.: Towards unsupervised acoustic guitar transcription. J. 7(2), 43\u201355 (2020)","journal-title":"Towards unsupervised acoustic guitar transcription. J."},{"key":"2_CR25","doi-asserted-by":"publisher","unstructured":"Xi, Q., Bittner, R.M., Pauwels, J., Ye, X., Bello, J.P.: Guitarset, August 2019. https:\/\/doi.org\/10.5281\/zenodo.3371780","DOI":"10.5281\/zenodo.3371780"},{"key":"2_CR26","unstructured":"Zeghoud, S., et al.: Real-time spatial normalization for dynamic gesture classification. The Visual Computer, pp. 1\u201313 (2022)"}],"container-title":["Lecture Notes in Computer Science","Advances in Computer Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-50069-5_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T06:02:52Z","timestamp":1705644172000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-50069-5_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031500688","9783031500695"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-50069-5_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"20 January 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CGI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Computer Graphics International Conference","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shanghai","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":"28 August 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cgi2023","order":10,"name":"conference_id","label":"Conference ID","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":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"385","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":"149","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":"39% - 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","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","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}