{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T08:06:12Z","timestamp":1784102772224,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":22,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819234196","type":"print"},{"value":"9789819234202","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T00:00:00Z","timestamp":1784160000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T00:00:00Z","timestamp":1784160000000},"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":[[2027]]},"DOI":"10.1007\/978-981-92-3420-2_25","type":"book-chapter","created":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T07:22:12Z","timestamp":1784100132000},"page":"287-298","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Mining Fine-Grained Articulatory Cues: High-Order Structural Synthesis for Robust Lip Reading"],"prefix":"10.1007","author":[{"given":"Jiahao","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qifei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Liao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenjuan","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guangming","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiubo","family":"Liang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,16]]},"reference":[{"key":"25_CR1","first-page":"87","volume-title":"Asian Conference on Computer Vision","author":"JS Chung","year":"2016","unstructured":"Chung, J.S., Zisserman, A.: Lip reading in the wild. In: Asian Conference on Computer Vision, pp. 87\u2013103. Springer International Publishing, Cham (2016)"},{"key":"25_CR2","doi-asserted-by":"publisher","first-page":"6548","DOI":"10.1109\/ICASSP.2018.8461326","volume-title":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"S Petridis","year":"2018","unstructured":"Petridis, S., Stafylakis, T., Ma, P., et al.: End-to-end audiovisual speech recognition. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6548\u20136552. IEEE (2018)"},{"issue":"1","key":"25_CR3","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1109\/TPAMI.2012.59","volume":"35","author":"S Ji","year":"2012","unstructured":"Ji, S., Xu, W., Yang, M., et al.: 3D convolutional neural networks for human action recognition. IEEE Trans. Pattern Anal. Mach. Intell. 35(1), 221\u2013231 (2012)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"25_CR4","first-page":"770","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"K He","year":"2016","unstructured":"He, K., Zhang, X., Ren, S., et al.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)"},{"key":"25_CR5","first-page":"6319","volume-title":"ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"B Martinez","year":"2020","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), pp. 6319\u20136323. IEEE (2020)"},{"key":"25_CR6","first-page":"8467","volume-title":"ICASSP 2022\u20132022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"A Koumparoulis","year":"2022","unstructured":"Koumparoulis, A., Potamianos, G.: Accurate and resource-efficient lipreading with efficientnetv2 and transformers. In: ICASSP 2022\u20132022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 8467\u20138471. IEEE (2022)"},{"key":"25_CR7","first-page":"7132","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"J Hu","year":"2018","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)"},{"key":"25_CR8","first-page":"3","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"S Woo","year":"2018","unstructured":"Woo, S., Park, J., Lee, J.Y., et al.: Cbam: Convolutional block attention module. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 3\u201319 (2018)"},{"key":"25_CR9","first-page":"2070","volume-title":"Proceedings of the IEEE International Conference on Computer Vision","author":"P Li","year":"2017","unstructured":"Li, P., Xie, J., Wang, Q., et al.: Is second-order information helpful for large-scale visual recognition? In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2070\u20132078 (2017)"},{"key":"25_CR10","first-page":"3024","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Z Gao","year":"2019","unstructured":"Gao, Z., Xie, J., Wang, Q., et al.: Global second-order pooling convolutional networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3024\u20133033 (2019)"},{"key":"25_CR11","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":"25_CR12","first-page":"1971","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops","author":"Y Cao","year":"2019","unstructured":"Cao, Y., Xu, J., Lin, S., et al.: Gcnet: non-local networks meet squeeze-excitation networks and beyond. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops, pp. 1971\u20131980 (2019)"},{"key":"25_CR13","first-page":"1","volume-title":"2024 International Joint Conference on Neural Networks (IJCNN)","author":"J Jiang","year":"2024","unstructured":"Jiang, J., Zhao, Z., Yang, Y., et al.: Gslip: a global lip-reading framework with solid dilated convolutions. In: 2024 International Joint Conference on Neural Networks (IJCNN), pp. 1\u20138. IEEE (2024)"},{"key":"25_CR14","first-page":"378","volume-title":"International Conference on Intelligent Computing","author":"F Bai","year":"2025","unstructured":"Bai, F., Li, W., Lu, M., et al.: LipMSTA: multi-scale Spatio-temporal attention for lip-Reading. In: International Conference on Intelligent Computing, pp. 378\u2013389. Springer Nature Singapore, Singapore (2025)"},{"key":"25_CR15","unstructured":"Bai, S., Kolter, J.O., Koltun, V.: An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv preprint arXiv:1803.01271 (2018)"},{"key":"25_CR16","first-page":"2857","volume-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","author":"P Ma","year":"2021","unstructured":"Ma, P., Wang, Y., Shen, J., et al.: Lip-reading with densely connected temporal convolutional networks. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2857\u20132866 (2021)"},{"key":"25_CR17","first-page":"947","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"P Li","year":"2018","unstructured":"Li, P., Xie, J., Wang, Q., et al.: Towards faster training of global covariance pooling networks by iterative matrix square root normalization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 947\u2013955 (2018)"},{"key":"25_CR18","first-page":"20094","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"G Tan","year":"2022","unstructured":"Tan, G., Wang, Y., Han, H., et al.: Multi-grained spatio-temporal features perceived network for event-based lip-reading. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20094\u201320103 (2022)"},{"key":"25_CR19","doi-asserted-by":"publisher","first-page":"356","DOI":"10.1109\/FG47880.2020.00134","volume-title":"2020 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020)","author":"Y Zhang","year":"2020","unstructured":"Zhang, Y., Yang, S., Xiao, J., et al.: Can we read speech beyond the lips? rethinking roi selection for deep visual speech recognition. In: 2020 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020), pp. 356\u2013363. IEEE (2020)"},{"key":"25_CR20","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., et al.: mixup: beyond empirical risk minimization. arXiv preprint arXiv:1710.09412 (2017)"},{"key":"25_CR21","first-page":"7608","volume-title":"ICASSP 2021\u20132021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"P Ma","year":"2021","unstructured":"Ma, P., Martinez, B., Petridis, S., et al.: Towards practical lipreading with distilled and efficient models. In: ICASSP 2021\u20132021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7608\u20137612. IEEE (2021)"},{"key":"25_CR22","first-page":"8472","volume-title":"ICASSP 2022\u20132022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"P Ma","year":"2022","unstructured":"Ma, P., Wang, Y., Petridis, S., et al.: Training strategies for improved lip-reading. In: ICASSP 2022\u20132022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 8472\u20138476. IEEE (2022)"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-3420-2_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T07:22:16Z","timestamp":1784100136000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-3420-2_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,16]]},"ISBN":["9789819234196","9789819234202"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-3420-2_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,16]]},"assertion":[{"value":"16 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Toronto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2026a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2026\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}