{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,11]],"date-time":"2026-10-11T13:29:14Z","timestamp":1791725354878,"version":"4.3.4"},"reference-count":56,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2024,6,11]],"date-time":"2024-06-11T00:00:00Z","timestamp":1718064000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,6,11]],"date-time":"2024-06-11T00:00:00Z","timestamp":1718064000000},"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":["Vis Comput"],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.1007\/s00371-024-03515-y","type":"journal-article","created":{"date-parts":[[2024,6,11]],"date-time":"2024-06-11T12:12:20Z","timestamp":1718107940000},"page":"1957-1969","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["Mini-3DCvT: a lightweight lip-reading method based on 3D convolution visual transformer"],"prefix":"10.1007","volume":"41","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1598-819X","authenticated-orcid":false,"given":"Huijuan","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Boyan","family":"Cui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Quanbo","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gangqiang","family":"Pu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xueli","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,6,11]]},"reference":[{"issue":"2","key":"3515_CR1","doi-asserted-by":"publisher","first-page":"212","DOI":"10.1121\/1.1907309","volume":"26","author":"WH Sumby","year":"1954","unstructured":"Sumby, W.H., Pollack, I.: Visual contribution to speech intelligibility in noise. J. Acoust. Soc. Am. 26(2), 212\u2013215 (1954)","journal-title":"J. Acoust. Soc. Am."},{"key":"3515_CR2","doi-asserted-by":"crossref","unstructured":"Watanabe, T., Katsurada, K., Kanazawa, Y.: Lip reading from multi view facial images using 3D-AAM. In: Asian Conference on Computer Vision, pp. 303\u2013316 (2016)","DOI":"10.1007\/978-3-319-54427-4_23"},{"key":"3515_CR3","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1016\/j.jml.2015.06.008","volume":"85","author":"M Baart","year":"2015","unstructured":"Baart, M., Samuel, A.G.: Turning a blind eye to the lexicon: ERPs show no cross-talk between lip-read and lexical context during speech sound processing. J. Mem. Lang. 85, 42\u201359 (2015)","journal-title":"J. Mem. Lang."},{"key":"3515_CR4","doi-asserted-by":"crossref","unstructured":"Mathulaprangsan, S., Wang, C.-Y., Kusum, A.Z., Tai, T.-C., Wang, J.-C.: A survey of visual lip reading and lip-password verification. In: Proceedings of the International Conference on Orange Technology (ICOT), pp. 22\u201325 (2015)","DOI":"10.1109\/ICOT.2015.7498485"},{"key":"3515_CR5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052","author":"TR Afouras","year":"2018","unstructured":"Afouras, T.R., Chung, J.S., Senior, A., Vinyals, O., Zisserman, A.: \u2018Deep audio-visual speech recognition. IEEE Trans. Pattern Anal. Mach. Intell. (2018). https:\/\/doi.org\/10.1109\/TPAMI.2018.2889052","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3515_CR6","doi-asserted-by":"crossref","unstructured":"Chen, L., Maddox, R.K., Duan, Z., Xu, C.: Hierarchical cross-modal talking face generation with dynamic pixel-wise loss. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7832\u20137841 (2019)","DOI":"10.1109\/CVPR.2019.00802"},{"key":"3515_CR7","doi-asserted-by":"crossref","unstructured":"Prajwal, K.R., Mukhopadhyay, R., Namboodiri, V.P., Jawahar, C.V.: Learning individual speaking styles for accurate lip to speech synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13796\u201313805 (2020)","DOI":"10.1109\/CVPR42600.2020.01381"},{"key":"3515_CR8","doi-asserted-by":"crossref","unstructured":"Ding, R., Pang, C., Liu, H.: Audio-visual keyword spotting based on multidimensional convolutional neural network. In: Proceedings of the 25th IEEE International Conference on Image Processing (ICIP), pp. 4138\u20134142 (2018)","DOI":"10.1109\/ICIP.2018.8451096"},{"key":"3515_CR9","doi-asserted-by":"publisher","first-page":"89010J","DOI":"10.1117\/12.2029464","volume":"8901","author":"R Bowden","year":"2013","unstructured":"Bowden, R., Cox, S., Harvey, R., Lan, Y., Theobald, B.J.: Recent developments in automated lip-reading. Proc. SPIE 8901, 89010J (2013)","journal-title":"Proc. SPIE"},{"issue":"9","key":"3515_CR10","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., Pietik\u00e4inen, M.: A review of recent advances in visual speech decoding. Image Vis. Comput. 32(9), 590\u2013605 (2014)","journal-title":"Image Vis. Comput."},{"issue":"2","key":"3515_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2008\/810362","volume":"2008","author":"R Seymour","year":"2008","unstructured":"Seymour, R., Stewart, D., Ming, J.: Comparison of image transformbased features for visual speech recognition in clean and corrupted videos. EURASIP J. Image Video Process. 2008(2), 1\u20139 (2008)","journal-title":"EURASIP J. Image Video Process."},{"issue":"7","key":"3515_CR12","doi-asserted-by":"publisher","first-page":"3041","DOI":"10.1007\/s00371-022-02511-4","volume":"39","author":"G Pu","year":"2023","unstructured":"Pu, G., Wang, H.: Review on research progress of machine lip reading. Vis. Comput. 39(7), 3041\u20133057 (2023)","journal-title":"Vis. Comput."},{"key":"3515_CR13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_32","volume-title":"Zero-shot keyword spotting for visual speech recognition in-the-wild","author":"T Stafylakis","year":"2018","unstructured":"Stafylakis, T., Tzimiropoulos, G.: Zero-shot keyword spotting for visual speech recognition in-the-wild. Springer, Cham (2018)"},{"key":"3515_CR14","doi-asserted-by":"crossref","unstructured":"Feng, D., Yang, S., Shan, S., et al.: An efficient software for building lip reading models without pains (2021)","DOI":"10.1109\/ICMEW53276.2021.9456014"},{"key":"3515_CR15","doi-asserted-by":"crossref","unstructured":"Afouras, T., Chung, J.S., Zisserman, A.: My lips are concealed: audio-visual speech enhancement through obstruction (2019). arXiv preprint https:\/\/arxiv.org\/abs\/1907.04975","DOI":"10.21437\/Interspeech.2019-3114"},{"key":"3515_CR16","doi-asserted-by":"crossref","unstructured":"Kim, M., Hong, J., Park, S.J., Ro, Y.M.: Multi-modality associative bridging through memory: speech sound recollected from face video. In: Proceedings of the IEEE\/CVF Conference on Computer Vision (ICCV), pp. 296\u2013306 (2021)","DOI":"10.1109\/ICCV48922.2021.00036"},{"key":"3515_CR17","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 (AAAI), pp. 1174\u20131182 (2022)","DOI":"10.1609\/aaai.v36i1.20003"},{"key":"3515_CR18","doi-asserted-by":"crossref","unstructured":"Xu, B., Lu, C., Guo, Y., et al.: Discriminative multi-modality speech recognition (2020)","DOI":"10.1109\/CVPR42600.2020.01444"},{"key":"3515_CR19","doi-asserted-by":"crossref","unstructured":"Petridis, S., Stafylakis, T., Ma, P., et al.: End-to-end audiovisual speech recognition (2018)","DOI":"10.1109\/ICASSP.2018.8461326"},{"key":"3515_CR20","doi-asserted-by":"crossref","unstructured":"Zhang, X., Cheng, F., Shilin, W.: Spatio-temporal fusion based convolutional sequence learning for lip reading. In: Proceedings of the IEEE\/CVF Conference on Computer Vision (ICCV), pp. 713\u2013722 (2019)","DOI":"10.1109\/ICCV.2019.00080"},{"key":"3515_CR21","unstructured":"Luo, M., Yang, S., Shan, S., Chen, X.: Synchronous bidirectional learning for multilingual lip reading. In: Proceedings of the BMVC (2020)"},{"issue":"12","key":"3515_CR22","doi-asserted-by":"publisher","first-page":"1111","DOI":"10.16451\/j.cnki.issn1003-6059.202212006","volume":"35","author":"F Xue","year":"2022","unstructured":"Xue, F., Hong, Z., Li, S., Li, Y., Xie, Y.: Chinese lip-reading based on vision transformer. Pattern Recognit. Artif. Intell. 35(12), 1111\u20131121 (2022). https:\/\/doi.org\/10.16451\/j.cnki.issn1003-6059.202212006","journal-title":"Pattern Recognit. Artif. Intell."},{"key":"3515_CR23","doi-asserted-by":"crossref","unstructured":"Petridis, S., Wang, Y., Li, Z., Pantic, M.: End-to-end multi-view lip reading. In: Proceedings of the British Machine Vision Conference (2017)","DOI":"10.5244\/C.31.161"},{"key":"3515_CR24","doi-asserted-by":"crossref","unstructured":"Xiao, J., Yang, S., Zhang, Y., Shan, S., Chen, X.: Deformation flow based two-stream network for lip reading. In: Proceedings of the 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG), pp. 364\u2013370 (2020)","DOI":"10.1109\/FG47880.2020.00132"},{"key":"3515_CR25","doi-asserted-by":"crossref","unstructured":"Martinez, B., Ma, P., Petridis, S., Pantic, M.: Lipreading using temporal convolutional networks. In: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. 6319\u20136323 (2020)","DOI":"10.1109\/ICASSP40776.2020.9053841"},{"key":"3515_CR26","unstructured":"Ma, P., Martinez, B., Petridis, S., Pantic, M.: Towards practical lipreading with distilled and efficient models (2020). https:\/\/arxiv.org\/abs\/2007.06504"},{"key":"3515_CR27","doi-asserted-by":"crossref","unstructured":"Liu, L., et al.: Viewing from frequency domain: A DCT-based information enhancement network for video person re-identification. In: Proceedings of the 29th ACM International Conference on Multimedia (2021)","DOI":"10.1145\/3474085.3475566"},{"key":"3515_CR28","doi-asserted-by":"publisher","first-page":"6266","DOI":"10.1109\/TIP.2021.3093759","volume":"30","author":"X Yang","year":"2021","unstructured":"Yang, X., et al.: A two-stream dynamic pyramid representation model for video-based person re-identification. IEEE Trans. Image Process. 30, 6266\u20136276 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"3515_CR29","doi-asserted-by":"crossref","unstructured":"Liu, J., et al.: Spatial-temporal correlation and topology learning for person re-identification in videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.00435"},{"key":"3515_CR30","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: Pyramid spatial-temporal aggregation for video-based person re-identification. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.01181"},{"key":"3515_CR31","doi-asserted-by":"publisher","first-page":"7237","DOI":"10.1109\/TMM.2024.3362136","volume":"26","author":"X Yang","year":"2024","unstructured":"Yang, X., et al.: STFE: a comprehensive video-based person re-identification network based on spatio-temporal feature enhancement. IEEE Trans. Multimed. 26, 7237\u20137249 (2024)","journal-title":"IEEE Trans. Multimed."},{"key":"3515_CR32","unstructured":"Aswani, A.V., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., Polosukhin, I.: Attention is all you need. In: Proceedings of the NIPS (2017)"},{"key":"3515_CR33","unstructured":"Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the NAACL (2019)"},{"key":"3515_CR34","doi-asserted-by":"crossref","unstructured":"Mahajan, D., Girshick, R., Ramanathan, V., He, K., Maaten, L.: Exploring the limits of weakly supervised pretraining. In: Proceedings of the European Conference on Computer Vision (2018)","DOI":"10.1007\/978-3-030-01216-8_12"},{"key":"3515_CR35","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Sgju, G.H.: An image is worth 16\u00d716 words: transformers for image recognition at scale. In: Proceedings of the International Conference on Learning Representations (2021)"},{"issue":"7","key":"3515_CR36","doi-asserted-by":"publisher","first-page":"4593","DOI":"10.1007\/s00371-022-02611-1","volume":"39","author":"Q Zhang","year":"2023","unstructured":"Zhang, Q., Ge, Y., Zhang, C., et al.: TPRNet: camouflaged object detection via transformer-induced progressive refinement network. Vis. Comput. 39(7), 4593\u20134607 (2023)","journal-title":"Vis. Comput."},{"issue":"7","key":"3515_CR37","doi-asserted-by":"publisher","first-page":"4721","DOI":"10.1007\/s00371-022-02620-0","volume":"39","author":"X Zhu","year":"2023","unstructured":"Zhu, X., Lu, J., Ren, H., et al.: A transformer\u2013CNN for deep image inpainting forensics. Vis. Comput. 39(7), 4721\u20134735 (2023)","journal-title":"Vis. Comput."},{"key":"3515_CR38","doi-asserted-by":"crossref","unstructured":"Wu, H., Xiao, B., Codella, N., Liu, M., Dai, X., Yuan, L., Zhang, L.: CvT: introducing convolutions to vision transformers (2021). https:\/\/arxiv.org\/abs\/2103.15808","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"3515_CR39","doi-asserted-by":"publisher","first-page":"77205","DOI":"10.1109\/ACCESS.2022.3193231","volume":"10","author":"GP Wang","year":"2022","unstructured":"Wang, G.P., Chen, T.: A lip reading method based on 3D convolutional vision transformer. IEEE Access 10, 77205\u201377212 (2022). https:\/\/doi.org\/10.1109\/ACCESS.2022.3193231","journal-title":"IEEE Access"},{"issue":"06","key":"3515_CR40","first-page":"1229","volume":"40","author":"F Zhou","year":"2017","unstructured":"Zhou, F., Jin, L., Dong, J.: A review of convolutional neural network research. J. Comput. Sci. 40(06), 1229\u20131251 (2017)","journal-title":"J. Comput. Sci."},{"issue":"06","key":"3515_CR41","first-page":"1229","volume":"40","author":"F Zhou","year":"2017","unstructured":"Zhou, F., Jin, L., Dong, J.: A survey of convolution neural networks. Chin. J. Comput. 40(06), 1229\u20131251 (2017)","journal-title":"Chin. J. Comput."},{"key":"3515_CR42","unstructured":"Dehghani, M., Gouws, S., Vinyals, O., et al.: Universal transformers (2019)"},{"key":"3515_CR43","unstructured":"Lan, Z., Chen, M., Goodman, S., et al.: ALBERT: a lite BERT for self-supervised learning of language representations"},{"key":"3515_CR44","unstructured":"Hinton, G., Dean, J., Vinyals, O.: Distilling the knowledge in a neural network (2014)"},{"key":"3515_CR45","doi-asserted-by":"crossref","unstructured":"Jiao, X., et al.: Tinybert: distilling BERT for natural language understanding (2019). arXiv preprint https:\/\/arxiv.org\/abs\/1909.10351","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"3515_CR46","unstructured":"Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization"},{"key":"3515_CR47","unstructured":"Hendrycks, D., Gimpel, K.: Gaussian error linear units (GELUs)"},{"key":"3515_CR48","doi-asserted-by":"crossref","unstructured":"Chollet, F.: Xception: deep learning with depthwise separable convolutions (2017)","DOI":"10.1109\/CVPR.2017.195"},{"key":"3515_CR49","doi-asserted-by":"crossref","unstructured":"Yuan, K., Guo, S., Liu, Z., et al.: Incorporating convolution designs into visual transformers (2021)","DOI":"10.1109\/ICCV48922.2021.00062"},{"key":"3515_CR50","doi-asserted-by":"crossref","unstructured":"Jiao, X., Yin, Y., Shang, L., et al.: TinyBERT: distilling BERT for natural language understanding (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"3515_CR51","doi-asserted-by":"crossref","unstructured":"Sun, Z., Yu, H., Song, X., et al.: Mobilebert: a compact taskagnostic BERT for resource-limited devices (2020)","DOI":"10.18653\/v1\/2020.acl-main.195"},{"key":"3515_CR52","doi-asserted-by":"crossref","unstructured":"Zhang, J., Peng, H., Wu, K., et al.: MiniViT: Compressing vision transformers with weight multiplexing (2022)","DOI":"10.1109\/CVPR52688.2022.01183"},{"key":"3515_CR53","doi-asserted-by":"crossref","unstructured":"Chung, J.S., Zisserman, A.: Lip reading in the wild. In: Asian Conference on Computer Vision (2016)","DOI":"10.1007\/978-3-319-54184-6_6"},{"key":"3515_CR54","doi-asserted-by":"crossref","unstructured":"Yang, S., Zhang, Y., Feng, D., Yang, M., Wang, C., Xiao, J., Long, K., Shan, S., Chen, X.: LRW-1000: a naturally-distributed large-scale benchmark for lip reading in the Wild. In: 2019 14th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2019)","DOI":"10.1109\/FG.2019.8756582"},{"key":"3515_CR55","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., et al.: Mixup: beyond empirical risk minimization (2018)"},{"key":"3515_CR56","doi-asserted-by":"crossref","unstructured":"Yun, S., Han, D., Chun, S., et al.: CutMix: regularization strategy to train strong classifiers with localizable features (2019)","DOI":"10.1109\/ICCV.2019.00612"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03515-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-024-03515-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03515-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,12]],"date-time":"2025-02-12T14:52:50Z","timestamp":1739371970000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-024-03515-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,11]]},"references-count":56,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,2]]}},"alternative-id":["3515"],"URL":"https:\/\/doi.org\/10.1007\/s00371-024-03515-y","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6,11]]},"assertion":[{"value":"26 May 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 June 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no conflict of interest to declare that are relevant to the content of this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}