{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,12]],"date-time":"2024-09-12T01:46:55Z","timestamp":1726105615381},"publisher-location":"Cham","reference-count":18,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030638191"},{"type":"electronic","value":"9783030638207"}],"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"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-63820-7_63","type":"book-chapter","created":{"date-parts":[[2020,11,18]],"date-time":"2020-11-18T09:12:07Z","timestamp":1605690727000},"page":"554-561","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["SpotFast Networks with Memory Augmented Lateral Transformers for Lipreading"],"prefix":"10.1007","author":[{"ORCID":"http:\/\/orcid.org\/0000-0001-5567-3104","authenticated-orcid":false,"given":"Peratham","family":"Wiriyathammabhum","sequence":"first","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,11,17]]},"reference":[{"key":"63_CR1","doi-asserted-by":"crossref","unstructured":"Afouras, T., Chung, J.S., Senior, A., Vinyals, O., Zisserman, A.: Deep audio-visual speech recognition. IEEE Trans. Pattern Anal. Mach. Intell. (2018)","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"63_CR2","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1016\/j.specom.2017.07.001","volume":"95","author":"HL Bear","year":"2017","unstructured":"Bear, H.L., Harvey, R.: Phoneme-to-viseme mappings: the good, the bad, and the ugly. Speech Commun. 95, 40\u201367 (2017)","journal-title":"Speech Commun."},{"key":"63_CR3","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? a new model and the kinetics dataset. In: proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"63_CR4","doi-asserted-by":"crossref","unstructured":"Chung, J.S., Senior, A., Vinyals, O., Zisserman, A.: Lip reading sentences in the wild. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3444\u20133453. IEEE (2017)","DOI":"10.1109\/CVPR.2017.367"},{"key":"63_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1007\/978-3-319-54184-6_6","volume-title":"Computer Vision \u2013 ACCV 2016","author":"JS Chung","year":"2017","unstructured":"Chung, J.S., Zisserman, A.: Lip reading in the wild. In: Lai, S.-H., Lepetit, V., Nishino, K., Sato, Y. (eds.) ACCV 2016. LNCS, vol. 10112, pp. 87\u2013103. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-54184-6_6"},{"key":"63_CR6","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K.: Slowfast networks for video recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 6202\u20136211 (2019)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"63_CR7","unstructured":"Lample, G., Sablayrolles, A., Ranzato, M., Denoyer, L., J\u00e9gou, H.: Large memory layers with product keys. In: Advances in Neural Information Processing Systems, pp. 8546\u20138557 (2019)"},{"issue":"3","key":"63_CR8","doi-asserted-by":"publisher","first-page":"213","DOI":"10.3758\/BF03204377","volume":"28","author":"VA Mann","year":"1980","unstructured":"Mann, V.A., Repp, B.H.: Influence of vocalic context on perception of the [$$\\int $$]-[s] distinction. Percept. Psychophys. 28(3), 213\u2013228 (1980)","journal-title":"Percept. Psychophys."},{"issue":"5588","key":"63_CR9","doi-asserted-by":"publisher","first-page":"746","DOI":"10.1038\/264746a0","volume":"264","author":"H McGurk","year":"1976","unstructured":"McGurk, H., MacDonald, J.: Hearing lips and seeing voices. Nature 264(5588), 746 (1976)","journal-title":"Nature"},{"key":"63_CR10","doi-asserted-by":"crossref","unstructured":"Petridis, S., Stafylakis, T., Ma, P., Cai, F., Tzimiropoulos, G., Pantic, M.: End-to-end audiovisual speech recognition. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6548\u20136552. IEEE (2018)","DOI":"10.1109\/ICASSP.2018.8461326"},{"key":"63_CR11","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1016\/j.cviu.2018.10.003","volume":"176","author":"T Stafylakis","year":"2018","unstructured":"Stafylakis, T., Khan, M.H., Tzimiropoulos, G.: Pushing the boundaries of audiovisual word recognition using residual networks and LSTMs. Comput. Vis. Image Underst. 176, 22\u201332 (2018)","journal-title":"Comput. Vis. Image Underst."},{"key":"63_CR12","doi-asserted-by":"publisher","first-page":"3652","DOI":"10.21437\/Interspeech.2017-85","volume":"2017","author":"T Stafylakis","year":"2017","unstructured":"Stafylakis, T., Tzimiropoulos, G.: Combining residual networks with LSTMs for lipreading. Proc. Interspeech 2017, 3652\u20133656 (2017)","journal-title":"Proc. Interspeech"},{"key":"63_CR13","unstructured":"Taylor, S.L., Mahler, M., Theobald, B.J., Matthews, I.: Dynamic units of visual speech. In: Proceedings of the ACM SIGGRAPH\/Eurographics Symposium on Computer Animation, pp. 275\u2013284. Eurographics Association (2012)"},{"key":"63_CR14","unstructured":"Thangthai, K.: Computer lipreading via hybrid deep neural network hidden Markov models. Ph.D. thesis, University of East Anglia (2018)"},{"key":"63_CR15","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3d convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4489\u20134497 (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"63_CR16","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"63_CR17","unstructured":"Weng, X., Kitani, K.: Learning spatio-temporal features with two-stream deep 3D CNNs for lipreading. BMVC (2019). https:\/\/bmvc2019.org\/wp-content\/uploads\/papers\/0016-paper.pdf"},{"key":"63_CR18","doi-asserted-by":"crossref","unstructured":"Zhang, X., Cheng, F., Wang, S.: Spatio-temporal fusion based convolutional sequence learning for lip reading. In: The IEEE International Conference on Computer Vision (ICCV), October 2019","DOI":"10.1109\/ICCV.2019.00080"}],"container-title":["Communications in Computer and Information Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-63820-7_63","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,24]],"date-time":"2021-04-24T10:25:12Z","timestamp":1619259912000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-63820-7_63"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030638191","9783030638207"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-63820-7_63","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"17 November 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bangkok","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Thailand","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 November 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 November 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.apnns.org\/ICONIP2020","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-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":"618","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":"187","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":"189","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":"30% - 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":"3.18","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":"3.68","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)"}},{"value":"Due to COVID-19 pandemic the conference was held virtually.","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)"}}]}}