{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T18:33:09Z","timestamp":1770748389987,"version":"3.50.0"},"publisher-location":"Cham","reference-count":16,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030412982","type":"print"},{"value":"9783030412999","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-41299-9_32","type":"book-chapter","created":{"date-parts":[[2020,2,22]],"date-time":"2020-02-22T04:02:51Z","timestamp":1582344171000},"page":"412-422","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Modality-Specific Learning Rate Control for Multimodal Classification"],"prefix":"10.1007","author":[{"given":"Naotsuna","family":"Fujimori","sequence":"first","affiliation":[]},{"given":"Rei","family":"Endo","sequence":"additional","affiliation":[]},{"given":"Yoshihiko","family":"Kawai","sequence":"additional","affiliation":[]},{"given":"Takahiro","family":"Mochizuki","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,2,23]]},"reference":[{"key":"32_CR1","doi-asserted-by":"crossref","unstructured":"Gallo, I., Calefati, A., Nawaz, S.: Multimodal classification fusion in real-world scenarios. In: Proceedings of the 14th IAPR International Conference on Document Analysis and Recognition, pp. 36\u201341 (2017)","DOI":"10.1109\/ICDAR.2017.326"},{"key":"32_CR2","doi-asserted-by":"crossref","unstructured":"Kim, E., McCoy, K.F.: Multimodal deep learning using images and text for information graphic classification. In: Proceedings of the 20th International ACM SIGACCESS Conference on Computers and Accessibility, pp. 143\u2013148 (2018)","DOI":"10.1145\/3234695.3236357"},{"key":"32_CR3","unstructured":"Ngiam, J., Khosla, A., Kim, M., Nam, J., Lee, H., Ng, A.Y.: Multimodal deep learning. In: Getoor, L., Scheffer, T. (eds.) Proceedings of the 28th International Conference on Machine Learning, pp. 689\u2013696. Omnipress, USA (2011)"},{"key":"32_CR4","doi-asserted-by":"crossref","unstructured":"Palaskar, S., Sanabria, R., Metze, F.: End-to-end multimodal speech recognition. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 5774\u20135778 (2018)","DOI":"10.1109\/ICASSP.2018.8462439"},{"key":"32_CR5","doi-asserted-by":"crossref","unstructured":"Yu, Z., Yu, J., Fan, J., Tao, D.: Multi-modal factorized bilinear pooling with co-attention learning for visual question answering. In: Proceedings of the International Conference on Computer Vision, pp. 1839\u20131848 (2017)","DOI":"10.1109\/ICCV.2017.202"},{"key":"32_CR6","unstructured":"Peng, G., et al.: Dynamic fusion with intra- and inter- modality attention flow for visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6639\u20136648 (2019)"},{"issue":"8","key":"32_CR7","doi-asserted-by":"publisher","first-page":"1583","DOI":"10.1109\/TPAMI.2016.2537340","volume":"38","author":"D Wu","year":"2016","unstructured":"Wu, D., et al.: Deep dynamic neural networks for multimodal gesture segmentation and recognition. IEEE Trans. Pattern Anal. Mach. Intell. 38(8), 1583\u20131597 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"32_CR8","doi-asserted-by":"crossref","unstructured":"Abavisani, M., Joze, H.R.V., Patel, V.M.: Improving the performance of unimodal dynamic hand-gesture recognition with multimodal training. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1165\u20131174 (2019)","DOI":"10.1109\/CVPR.2019.00126"},{"key":"32_CR9","unstructured":"Arevalo, J., Solorio, T., Montes-y-G\u00f3mez, M., Gonz\u00e1lez, F.A.: Gated multimodal units for information fusion. In: 5th International Conference on Learning Representations Workshop (2017)"},{"key":"32_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"575","DOI":"10.1007\/978-3-030-11024-6_44","volume-title":"Computer Vision \u2013 ECCV 2018 Workshops","author":"V Vielzeuf","year":"2019","unstructured":"Vielzeuf, V., Lechervy, A., Pateux, S., Jurie, F.: CentralNet: a multilayer approach for multimodal fusion. In: Leal-Taix\u00e9, L., Roth, S. (eds.) ECCV 2018. LNCS, vol. 11134, pp. 575\u2013589. Springer, Cham (2019). \nhttps:\/\/doi.org\/10.1007\/978-3-030-11024-6_44"},{"key":"32_CR11","unstructured":"Loshchilov, I., Hutter, F.: SGDR: stochastic gradient descent with warm restarts. In: Proceedings of the International Conference on Learning Representations (2017)"},{"key":"32_CR12","doi-asserted-by":"crossref","unstructured":"Smith, L.N.: Cyclical learning rates for training neural networks. In: Proceedings of the IEEE Winter Conference on Applications of Computer Vision, pp. 464\u2013472 (2017)","DOI":"10.1109\/WACV.2017.58"},{"key":"32_CR13","unstructured":"Zeiler, M.D.: ADADELTA: an adaptive learning rate method. arXiv preprint \narXiv:1212.5701\n\n (2012)"},{"key":"32_CR14","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: The 3rd International Conference on Learning Representations (2015)"},{"key":"32_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1007\/978-3-642-35289-8_5","volume-title":"Neural Networks: Tricks of the Trade","author":"L Prechelt","year":"2012","unstructured":"Prechelt, L.: Early stopping\u2014but when? In: Montavon, G., Orr, G.B., M\u00fcller, K.-R. (eds.) Neural Networks: Tricks of the Trade. LNCS, vol. 7700, pp. 53\u201367. Springer, Heidelberg (2012). \nhttps:\/\/doi.org\/10.1007\/978-3-642-35289-8_5"},{"issue":"3","key":"32_CR16","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vis."}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-41299-9_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,2,22]],"date-time":"2020-02-22T04:09:45Z","timestamp":1582344585000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-41299-9_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030412982","9783030412999"],"references-count":16,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-41299-9_32","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"23 February 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Auckland","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Zealand","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 November 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 November 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"acpr2019a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.acpr2019.org\/","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":"easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"214","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":"125","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":"58% - 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":"2","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)"}},{"value":"for ACPR 2019 Workshops volume accepted 17 full papers and 6 short papers","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}