{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T11:27:56Z","timestamp":1768994876153,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":24,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819556274","type":"print"},{"value":"9789819556281","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-5628-1_15","type":"book-chapter","created":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T21:30:03Z","timestamp":1768944603000},"page":"212-225","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Towards Uyghur Lip-Reading: Dataset Development and\u00a0Attention-Enhanced Recognition with\u00a0ECA-S Module"],"prefix":"10.1007","author":[{"given":"Siyuan","family":"Wei","sequence":"first","affiliation":[]},{"given":"Zilong","family":"Xing","sequence":"additional","affiliation":[]},{"given":"Mutallip","family":"Mamut","sequence":"additional","affiliation":[]},{"given":"Kurban","family":"Ubul","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,1,21]]},"reference":[{"key":"15_CR1","doi-asserted-by":"publisher","first-page":"204518","DOI":"10.1109\/ACCESS.2020.3036865","volume":"8","author":"M Hao","year":"2020","unstructured":"Hao, M., Mamut, M., Yadikar, N., Aysa, A., Ubul, K.: A survey of research on lipreading technology. IEEE Access 8, 204518\u2013204544 (2020)","journal-title":"IEEE Access"},{"key":"15_CR2","doi-asserted-by":"crossref","unstructured":"Goldschen, A.J., Garcia, O.N., Petajan, E.: Continuous optical automatic speech recognition by lipreading. In: Proceedings of 1994 28th Asilomar Conference on Signals, Systems and Computers, vol. 1, pp. 572\u2013577. IEEE (1994)","DOI":"10.1109\/ACSSC.1994.471517"},{"key":"15_CR3","doi-asserted-by":"crossref","unstructured":"Wand, M., Schmidhuber, J., Vu, N.T.: Investigations on end-to-end audiovisual fusion. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 3041\u20133045. IEEE (2018)","DOI":"10.1109\/ICASSP.2018.8461900"},{"key":"15_CR4","doi-asserted-by":"crossref","unstructured":"Zhang, X., Gong, H., Dai, X., Yang, F., Liu, N., Liu, M.: Understanding pictograph with facial features: end-to-end sentence-level lip reading of Chinese. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, no. 01, pp. 9211\u20139218 (2019)","DOI":"10.1609\/aaai.v33i01.33019211"},{"key":"15_CR5","doi-asserted-by":"crossref","unstructured":"Wiriyathammabhum, P.: SpotFast networks with memory augmented lateral transformers for lipreading. In: International Conference on Neural Information Processing, pp. 554\u2013561. Springer (2020)","DOI":"10.1007\/978-3-030-63820-7_63"},{"key":"15_CR6","unstructured":"Chung, J.S., Zisserman, A.: Lip reading in the wild. In: Computer Vision\u2013ACCV 2016: 13th Asian Conference on Computer Vision, Taipei, Taiwan, November 20-24, 2016, Revised Selected Papers, Part II 13, pp. 87\u2013103. Springer (2017)"},{"key":"15_CR7","doi-asserted-by":"crossref","unstructured":"Son Chung, J., Senior, A., Vinyals, O., Zisserman, A.: Lip reading sentences in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6447\u20136456 (2017)","DOI":"10.1109\/CVPR.2017.367"},{"key":"15_CR8","doi-asserted-by":"crossref","unstructured":"Yang, S., et al.: LRW-1000: a naturally-distributed large-scale benchmark for lip reading in the wild. In: 2019 14th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2019), pp. 1\u20138. IEEE (2019)","DOI":"10.1109\/FG.2019.8756582"},{"key":"15_CR9","doi-asserted-by":"crossref","unstructured":"Wang, Q., Wu, B., Zhu, P., Li, P., Zuo, W., Hu, Q.: ECA-net: efficient channel attention for deep convolutional neural networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11534\u201311542 (2020)","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"15_CR10","doi-asserted-by":"crossref","unstructured":"Zhao, G., Pietik\u00e4inen, M., Hadid, A.: Local spatiotemporal descriptors for visual recognition of spoken phrases. In: Proceedings of the International Workshop on Human-centered Multimedia, pp. 57\u201366 (2007)","DOI":"10.1145\/1290128.1290138"},{"key":"15_CR11","doi-asserted-by":"crossref","unstructured":"Shilaskar, S., Iramani, H.: CTC-CNN-bidirectional LSTM based lip reading system. In: 2024 International Conference on Emerging Smart Computing and Informatics (ESCI), pp. 1\u20136. IEEE (2024)","DOI":"10.1109\/ESCI59607.2024.10497275"},{"key":"15_CR12","doi-asserted-by":"crossref","unstructured":"Xiang, Y., Mamut, M., Yadikar, N., Ibrahim, G., Ubul, K.: The collaboration of 3d convolutions and cro-tsm in lipreading. In: ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4890\u20134894. IEEE (2024)","DOI":"10.1109\/ICASSP48485.2024.10446453"},{"issue":"2","key":"15_CR13","doi-asserted-by":"publisher","first-page":"198","DOI":"10.1109\/34.982900","volume":"24","author":"I Matthews","year":"2002","unstructured":"Matthews, I., Cootes, T.F., Bangham, J.A., Cox, S., Harvey, R.: Extraction of visual features for lipreading. IEEE Trans. Pattern Anal. Mach. Intell. 24(2), 198\u2013213 (2002)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"15_CR14","doi-asserted-by":"crossref","unstructured":"Anina, I., Zhou, Z., Zhao, G., Pietik\u00e4inen, M.: Ouluvs2: a multi-view audiovisual database for non-rigid mouth motion analysis. In: 2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG), vol. 1, pp. 1\u20135. IEEE (2015)","DOI":"10.1109\/FG.2015.7163155"},{"key":"15_CR15","first-page":"1755","volume":"10","author":"DE King","year":"2009","unstructured":"King, D.E.: Dlib-ml: a machine learning toolkit. J. Mach. Learn. Res. 10, 1755\u20131758 (2009)","journal-title":"J. Mach. Learn. Res."},{"key":"15_CR16","doi-asserted-by":"crossref","unstructured":"Ma, P., Wang, Y., Shen, J., Petridis, S., Pantic, M.: 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)","DOI":"10.1109\/WACV48630.2021.00290"},{"key":"15_CR17","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":"15_CR18","doi-asserted-by":"crossref","unstructured":"Ma, P., Wang, Y., Petridis, S., Shen, J., Pantic, M.: Training strategies for improved lip-reading. In: ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 8472\u20138476. IEEE (2022)","DOI":"10.1109\/ICASSP43922.2022.9746706"},{"key":"15_CR19","doi-asserted-by":"crossref","unstructured":"Hao, M., Mamut, M., Yadikar, N., Aysa, A., Ubul, K.: How to use time information effectively? combining with time shift module for lipreading. In: ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7988\u20137992. IEEE (2021)","DOI":"10.1109\/ICASSP39728.2021.9414659"},{"key":"15_CR20","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":"15_CR21","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Yang, S., Xiao, J., Shan, S., Chen, X.: 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)","DOI":"10.1109\/FG47880.2020.00134"},{"key":"15_CR22","doi-asserted-by":"crossref","unstructured":"Yang, C.C., Fan, W.C., Yang, C.F., Wang, Y.C.F.: Cross-modal mutual learning for audio-visual speech recognition and manipulation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, no. 3, pp. 3036\u20133044 (2022)","DOI":"10.1609\/aaai.v36i3.20210"},{"key":"15_CR23","doi-asserted-by":"crossref","unstructured":"Kim, M., Yeo, J.H., Ro, Y.M.: Distinguishing homophenes using multi-head visual-audio memory for lip reading. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, no. 1, pp. 1174\u20131182 (2022)","DOI":"10.1609\/aaai.v36i1.20003"},{"key":"15_CR24","doi-asserted-by":"crossref","unstructured":"Martinez, B., Ma, P., Petridis, S., Pantic, M.: Lipreading using temporal convolutional networks. In: ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6319\u20136323. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9053841"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-5628-1_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T21:30:06Z","timestamp":1768944606000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-5628-1_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819556274","9789819556281"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-5628-1_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"21 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","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":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2025.prcv.cn\/index.asp","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}