{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,11]],"date-time":"2025-04-11T08:51:37Z","timestamp":1744361497589,"version":"3.40.3"},"publisher-location":"Cham","reference-count":18,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030866075"},{"type":"electronic","value":"9783030866082"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[[2021]]},"DOI":"10.1007\/978-3-030-86608-2_52","type":"book-chapter","created":{"date-parts":[[2021,9,9]],"date-time":"2021-09-09T05:02:56Z","timestamp":1631163776000},"page":"474-482","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Channel Enhanced Temporal-Shift Module for Efficient Lipreading"],"prefix":"10.1007","author":[{"given":"Hao","family":"Li","sequence":"first","affiliation":[]},{"given":"Mutallip","family":"Mamut","sequence":"additional","affiliation":[]},{"given":"Nurbiya","family":"Yadikar","sequence":"additional","affiliation":[]},{"given":"Yali","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Kurban","family":"Ubul","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,9,8]]},"reference":[{"issue":"9","key":"52_CR1","doi-asserted-by":"publisher","first-page":"590","DOI":"10.1016\/j.imavis.2014.06.004","volume":"32","author":"Z Zhou","year":"2014","unstructured":"Zhou, Z., Zhao, G., Hong, X., et al.: A review of recent advances in visual speech decoding. Image Vis. Comput. 32(9), 590\u2013605 (2014)","journal-title":"Image Vis. Comput."},{"key":"52_CR2","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Zhao, G., Pietik\u00e4inen, M.: Towards a practical lipreading system. In: CVPR 2011, 137\u2013144. IEEE (2011)","DOI":"10.1109\/CVPR.2011.5995345"},{"issue":"1","key":"52_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TPAMI.2013.173","volume":"36","author":"Z Zhou","year":"2013","unstructured":"Zhou, Z., Hong, X., Zhao, G., et al.: A compact representation of visual speech data using latent variables. IEEE Trans. Pattern Anal. Mach. Intell. 36(1), 1 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"52_CR4","doi-asserted-by":"crossref","unstructured":"Pei, Y., Kim, T.K., Zha, H.: Unsupervised random forest manifold alignment for lipreading. In: Proceedings of the IEEE International Conference on Computer Vision, 129\u2013136 (2013)","DOI":"10.1109\/ICCV.2013.23"},{"issue":"3","key":"52_CR5","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1023\/A:1011352422845","volume":"4","author":"G Potamianos","year":"2001","unstructured":"Potamianos, G., Neti, C., Iyengar, G., et al.: A cascade visual front end for speaker independent automatic speechreading. Int. J. Speech Technol. 4(3), 193\u2013208 (2001)","journal-title":"Int. J. Speech Technol."},{"key":"52_CR6","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":"52_CR7","doi-asserted-by":"crossref","unstructured":"Yang, S., Zhang, Y., Feng, D., et al.: LRW-1000: a naturally-distributed large-scale benchmark for lip reading in the wild. arXiv e-prints arXiv:1810.06990 (2018)","DOI":"10.1109\/FG.2019.8756582"},{"key":"52_CR8","doi-asserted-by":"crossref","unstructured":"Stafylakis, T., Tzimiropoulos, G.: Combining residual networks with LSTMs for lipreading. arXiv preprint arXiv:1703.04105 (2017)","DOI":"10.21437\/Interspeech.2017-85"},{"key":"52_CR9","unstructured":"Weng, X., Kitani, K.: Learning spatio-temporal features with two-stream deep 3D CNNS for lipreading. arXiv preprint arXiv:1905.02540 (2019)"},{"key":"52_CR10","unstructured":"Feng, D., Yang, S., Shan, S., et al.: Learn an effective lip reading model without pains. arXiv preprint arXiv:2011.07557 (2020)"},{"key":"52_CR11","doi-asserted-by":"crossref","unstructured":"Lin, J., Gan, C., Han, S.: Tsm: Temporal shift module for efficient video understanding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7083\u20137093 (2019)","DOI":"10.1109\/ICCV.2019.00718"},{"key":"52_CR12","doi-asserted-by":"crossref","unstructured":"Martinez, B., Ma, P., Petridis, S., et al.: Lipreading using temporal convolutional networks. In: ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 6319\u20136323. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9053841"},{"key":"52_CR13","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Yang, S., Xiao, J., et al.: Can we read speech beyond the lips? rethinking roi selection for deep visual speech recognition. arXiv preprint arXiv:2003.03206 (2020)","DOI":"10.1109\/FG47880.2020.00134"},{"key":"52_CR14","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"52_CR15","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":"52_CR16","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 \u2013 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.) ECCV 2018. LNCS, vol. 11211, pp. 3\u201319. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_1"},{"key":"52_CR17","doi-asserted-by":"crossref","unstructured":"Hou, Q., Zhou, D., Feng, J.: Coordinate attention for efficient mobile network design. arXiv preprint arXiv:2103.02907 (2021)","DOI":"10.1109\/CVPR46437.2021.01350"},{"key":"52_CR18","unstructured":"Wang, C.: Multi-grained spatio-temporal modeling for lip-reading. arXiv preprint arXiv:1908.1161 (2019)"}],"container-title":["Lecture Notes in Computer Science","Biometric Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-86608-2_52","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,8]],"date-time":"2023-01-08T21:44:18Z","timestamp":1673214258000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-86608-2_52"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030866075","9783030866082"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-86608-2_52","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"8 September 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CCBR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Biometric Recognition","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":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccbr2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ccbr99.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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"72","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":"53","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":"74% - 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":"2.3","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":"2.1","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":"Full papers are up to 11 pages long.","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)"}}]}}