{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T18:07:24Z","timestamp":1771956444196,"version":"3.50.1"},"publisher-location":"Cham","reference-count":45,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031200670","type":"print"},{"value":"9783031200687","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-20068-7_14","type":"book-chapter","created":{"date-parts":[[2022,11,10]],"date-time":"2022-11-10T08:06:38Z","timestamp":1668067598000},"page":"240-256","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Deep Radial Embedding for\u00a0Visual Sequence Learning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0696-2468","authenticated-orcid":false,"given":"Yuecong","family":"Min","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0976-0834","authenticated-orcid":false,"given":"Peiqi","family":"Jiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanan","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaotao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Lei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2757-9900","authenticated-orcid":false,"given":"Xiujuan","family":"Chai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3024-4404","authenticated-orcid":false,"given":"Xilin","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,11,11]]},"reference":[{"key":"14_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1007\/978-3-030-58621-8_3","volume-title":"Computer Vision \u2013 ECCV 2020","author":"S Albanie","year":"2020","unstructured":"Albanie, S., et al.: BSL-1K: scaling up co-articulated sign language recognition using mouthing cues. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12356, pp. 35\u201353. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58621-8_3"},{"key":"14_CR2","unstructured":"Bahdanau, D., Cho, K.H., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: International Conference on Learning Representations (2015)"},{"key":"14_CR3","doi-asserted-by":"crossref","unstructured":"Camgoz, N.C., Hadfield, S., Koller, O., Bowden, R.: Subunets: end-to-end hand shape and continuous sign language recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3075\u20133084 (2017)","DOI":"10.1109\/ICCV.2017.332"},{"key":"14_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"697","DOI":"10.1007\/978-3-030-58586-0_41","volume-title":"Computer Vision \u2013 ECCV 2020","author":"KL Cheng","year":"2020","unstructured":"Cheng, K.L., Yang, Z., Chen, Q., Tai, Y.-W.: Fully convolutional networks for continuous sign language recognition. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12369, pp. 697\u2013714. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58586-0_41"},{"key":"14_CR5","doi-asserted-by":"crossref","unstructured":"Cihan Camgoz, N., Hadfield, S., Koller, O., Bowden, R.: Subunets: end-to-end hand shape and continuous sign language recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3056\u20133065 (2017)","DOI":"10.1109\/ICCV.2017.332"},{"key":"14_CR6","doi-asserted-by":"crossref","unstructured":"Cui, R., Liu, H., Zhang, C.: Recurrent convolutional neural networks for continuous sign language recognition by staged optimization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7361\u20137369 (2017)","DOI":"10.1109\/CVPR.2017.175"},{"issue":"7","key":"14_CR7","doi-asserted-by":"publisher","first-page":"1880","DOI":"10.1109\/TMM.2018.2889563","volume":"21","author":"R Cui","year":"2019","unstructured":"Cui, R., Liu, H., Zhang, C.: A deep neural framework for continuous sign language recognition by iterative training. IEEE Trans. Multimedia 21(7), 1880\u20131891 (2019)","journal-title":"IEEE Trans. Multimedia"},{"key":"14_CR8","doi-asserted-by":"crossref","unstructured":"Deng, J., Guo, J., Xue, N., Zafeiriou, S.: Arcface: additive angular margin loss for deep face recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4690\u20134699 (2019)","DOI":"10.1109\/CVPR.2019.00482"},{"issue":"2","key":"14_CR9","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes (VOC) challenge. Int. J. Comput. Vision 88(2), 303\u2013338 (2010)","journal-title":"Int. J. Comput. Vision"},{"key":"14_CR10","doi-asserted-by":"crossref","unstructured":"Graves, A., Fern\u00e1ndez, S., Gomez, F., Schmidhuber, J.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: Proceedings of International Conference on Machine Learning, pp. 369\u2013376 (2006)","DOI":"10.1145\/1143844.1143891"},{"key":"14_CR11","unstructured":"Graves, A., Jaitly, N.: Towards end-to-end speech recognition with recurrent neural networks. In: Proceedings of the International Conference on Machine Learning, pp. 1764\u20131772. PMLR (2014)"},{"issue":"5","key":"14_CR12","doi-asserted-by":"publisher","first-page":"855","DOI":"10.1109\/TPAMI.2008.137","volume":"31","author":"A Graves","year":"2008","unstructured":"Graves, A., Liwicki, M., Fern\u00e1ndez, S., Bertolami, R., Bunke, H., Schmidhuber, J.: A novel connectionist system for unconstrained handwriting recognition. IEEE Trans. Pattern Anal. Mach. Intell. 31(5), 855\u2013868 (2008)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"14_CR13","doi-asserted-by":"crossref","unstructured":"Hadian, H., Sameti, H., Povey, D., Khudanpur, S.: End-to-end speech recognition using lattice-free mmi. In: Interspeech, pp. 12\u201316 (2018)","DOI":"10.21437\/Interspeech.2018-1423"},{"key":"14_CR14","doi-asserted-by":"crossref","unstructured":"Hao, A., Min, Y., Chen, X.: Self-mutual distillation learning for continuous sign language recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 11303\u201311312 (2021)","DOI":"10.1109\/ICCV48922.2021.01111"},{"key":"14_CR15","unstructured":"Jaderberg, M., Simonyan, K., Vedaldi, A., Zisserman, A.: Synthetic data and artificial neural networks for natural scene text recognition. arXiv preprint arXiv:1406.2227 (2014)"},{"key":"14_CR16","doi-asserted-by":"crossref","unstructured":"Karatzas, D., et al.: ICDAR 2013 robust reading competition. In: 2013 12th International Conference on Document Analysis and Recognition, pp. 1484\u20131493. IEEE (2013)","DOI":"10.1109\/ICDAR.2013.221"},{"key":"14_CR17","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1016\/j.cviu.2015.09.013","volume":"141","author":"O Koller","year":"2015","unstructured":"Koller, O., Forster, J., Ney, H.: Continuous sign language recognition: towards large vocabulary statistical recognition systems handling multiple signers. Comput. Vis. Image Underst. 141, 108\u2013125 (2015)","journal-title":"Comput. Vis. Image Underst."},{"key":"14_CR18","doi-asserted-by":"crossref","unstructured":"Koller, O., Zargaran, S., Ney, H.: Re-sign: re-aligned end-to-end sequence modelling with deep recurrent CNN-HMMs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4297\u20134305 (2017)","DOI":"10.1109\/CVPR.2017.364"},{"issue":"11","key":"14_CR19","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"key":"14_CR20","doi-asserted-by":"crossref","unstructured":"Lee, C.Y., Osindero, S.: Recursive recurrent nets with attention modeling for OCR in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2231\u20132239 (2016)","DOI":"10.1109\/CVPR.2016.245"},{"key":"14_CR21","doi-asserted-by":"crossref","unstructured":"Li, D., Rodriguez, C., Yu, X., Li, H.: Word-level deep sign language recognition from video: a new large-scale dataset and methods comparison. In: Proceedings of the IEEE Winter Conference on Applications of Computer Vision, pp. 1459\u20131469 (2020)","DOI":"10.1109\/WACV45572.2020.9093512"},{"key":"14_CR22","doi-asserted-by":"publisher","first-page":"107392","DOI":"10.1016\/j.patcog.2020.107392","volume":"105","author":"H Li","year":"2020","unstructured":"Li, H., Wang, W.: Reinterpreting CTC training as iterative fitting. Pattern Recogn. 105, 107392 (2020)","journal-title":"Pattern Recogn."},{"key":"14_CR23","first-page":"831","volume":"31","author":"H Liu","year":"2018","unstructured":"Liu, H., Jin, S., Zhang, C.: Connectionist temporal classification with maximum entropy regularization. Adv. Neural. Inf. Process. Syst. 31, 831\u2013841 (2018)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"14_CR24","doi-asserted-by":"crossref","unstructured":"Liu, W., Chen, C., Wong, K.Y.K., Su, Z., Han, J.: Star-net: a spatial attention residue network for scene text recognition. In: Proceedings of the British Machine Vision Conference, vol. 2, p. 7 (2016)","DOI":"10.5244\/C.30.43"},{"key":"14_CR25","doi-asserted-by":"crossref","unstructured":"Liu, W., Wen, Y., Yu, Z., Li, M., Raj, B., Song, L.: Sphereface: deep hypersphere embedding for face recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 212\u2013220 (2017)","DOI":"10.1109\/CVPR.2017.713"},{"key":"14_CR26","unstructured":"Liu, W., Wen, Y., Yu, Z., Yang, M.: Large-margin softmax loss for convolutional neural networks. In: Proceedings of the International Conference on Machine Learning, vol. 2, p. 7 (2016)"},{"issue":"2","key":"14_CR27","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1007\/s10032-004-0134-3","volume":"7","author":"SM Lucas","year":"2005","unstructured":"Lucas, S.M., Panaretos, A., Sosa, L., et al.: ICDAR 2003 robust reading competitions: entries, results, and future directions. Int. J. Doc. Anal. Recognit. 7(2), 105\u2013122 (2005)","journal-title":"Int. J. Doc. Anal. Recognit."},{"key":"14_CR28","doi-asserted-by":"crossref","unstructured":"Meng, Q., Zhao, S., Huang, Z., Zhou, F.: Magface: a universal representation for face recognition and quality assessment. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 14225\u201314234 (2021)","DOI":"10.1109\/CVPR46437.2021.01400"},{"key":"14_CR29","doi-asserted-by":"crossref","unstructured":"Min, Y., Hao, A., Chai, X., Chen, X.: Visual alignment constraint for continuous sign language recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 11542\u201311551 (2021)","DOI":"10.1109\/ICCV48922.2021.01134"},{"key":"14_CR30","doi-asserted-by":"crossref","unstructured":"Mishra, A., Alahari, K., Jawahar, C.: Scene text recognition using higher order language priors. In: Proceedings of the British Machine Vision Conference (2012)","DOI":"10.5244\/C.26.127"},{"key":"14_CR31","unstructured":"Parde, C.J., et al.: Deep convolutional neural network features and the original image. arXiv preprint arXiv:1611.01751 (2016)"},{"key":"14_CR32","doi-asserted-by":"crossref","unstructured":"Pu, J., Zhou, W., Hu, H., Li, H.: Boosting continuous sign language recognition via cross modality augmentation. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 1497\u20131505 (2020)","DOI":"10.1145\/3394171.3413931"},{"issue":"2","key":"14_CR33","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1109\/5.18626","volume":"77","author":"LR Rabiner","year":"1989","unstructured":"Rabiner, L.R.: A tutorial on hidden Markov models and selected applications in speech recognition. Proc. IEEE 77(2), 257\u2013286 (1989)","journal-title":"Proc. IEEE"},{"key":"14_CR34","unstructured":"Ranjan, R., Castillo, C.D., Chellappa, R.: L2-constrained softmax loss for discriminative face verification. arXiv preprint arXiv:1703.09507 (2017)"},{"issue":"11","key":"14_CR35","doi-asserted-by":"publisher","first-page":"2298","DOI":"10.1109\/TPAMI.2016.2646371","volume":"39","author":"B Shi","year":"2016","unstructured":"Shi, B., Bai, X., Yao, C.: An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition. IEEE Trans. Pattern Anal. Mach. Intell. 39(11), 2298\u20132304 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"14_CR36","doi-asserted-by":"crossref","unstructured":"Shi, B., Wang, X., Lyu, P., Yao, C., Bai, X.: Robust scene text recognition with automatic rectification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4168\u20134176 (2016)","DOI":"10.1109\/CVPR.2016.452"},{"key":"14_CR37","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"14_CR38","doi-asserted-by":"crossref","unstructured":"Wang, F., Xiang, X., Cheng, J., Yuille, A.L.: Normface: L2 hypersphere embedding for face verification. In: Proceedings of the 25th ACM International Conference on Multimedia, pp. 1041\u20131049 (2017)","DOI":"10.1145\/3123266.3123359"},{"key":"14_CR39","doi-asserted-by":"crossref","unstructured":"Wang, H., et al.: Cosface: large margin cosine loss for deep face recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5265\u20135274 (2018)","DOI":"10.1109\/CVPR.2018.00552"},{"key":"14_CR40","unstructured":"Wang, K., Babenko, B., Belongie, S.: End-to-end scene text recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1457\u20131464. IEEE (2011)"},{"key":"14_CR41","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"499","DOI":"10.1007\/978-3-319-46478-7_31","volume-title":"Computer Vision \u2013 ECCV 2016","author":"Y Wen","year":"2016","unstructured":"Wen, Y., Zhang, K., Li, Z., Qiao, Yu.: A discriminative feature learning approach for deep face recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9911, pp. 499\u2013515. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46478-7_31"},{"key":"14_CR42","doi-asserted-by":"crossref","unstructured":"Xie, Z., Huang, Y., Zhu, Y., Jin, L., Liu, Y., Xie, L.: Aggregation cross-entropy for sequence recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6538\u20136547 (2019)","DOI":"10.1109\/CVPR.2019.00670"},{"key":"14_CR43","doi-asserted-by":"crossref","unstructured":"Zeyer, A., Beck, E., Schl\u00fcter, R., Ney, H.: CTC in the context of generalized full-sum hmm training. In: Interspeech, pp. 944\u2013948 (2017)","DOI":"10.21437\/Interspeech.2017-1073"},{"key":"14_CR44","unstructured":"Zeyer, A., Schl\u00fcter, R., Ney, H.: Why does CTC result in peaky behavior? arXiv preprint arXiv:2105.14849 (2021)"},{"key":"14_CR45","doi-asserted-by":"crossref","unstructured":"Zhou, H., Zhou, W., Zhou, Y., Li, H.: Spatial-temporal multi-cue network for continuous sign language recognition. In: Proceedings of the Association for the Advancement of Artificial Intelligence, pp. 13009\u201313016 (2020)","DOI":"10.1609\/aaai.v34i07.7001"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20068-7_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,10]],"date-time":"2022-11-10T08:10:53Z","timestamp":1668067853000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20068-7_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200670","9783031200687"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20068-7_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"11 November 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","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":"1645","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":"28% - 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":"3.21","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":"3.91","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)"}}]}}