{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T06:31:49Z","timestamp":1774074709582,"version":"3.50.1"},"reference-count":62,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFF1203900"],"award-info":[{"award-number":["2023YFF1203900"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFF1203903"],"award-info":[{"award-number":["2023YFF1203903"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62332019"],"award-info":[{"award-number":["62332019"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076250"],"award-info":[{"award-number":["62076250"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1016\/j.neunet.2025.107783","type":"journal-article","created":{"date-parts":[[2025,7,2]],"date-time":"2025-07-02T02:51:22Z","timestamp":1751424682000},"page":"107783","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":2,"special_numbering":"C","title":["MsDUNE: A multi-scale masked temporal fusion framework for speaker-independent lipreading via Dirichlet uncertainty estimation"],"prefix":"10.1016","volume":"191","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7140-450X","authenticated-orcid":false,"given":"Jinghan","family":"Wu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5417-508X","authenticated-orcid":false,"given":"Xingwei","family":"An","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yakun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Changyan","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xingyu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2147-9888","authenticated-orcid":false,"given":"Erwei","family":"Yin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2025.107783_b1","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1016\/j.neunet.2023.02.032","article-title":"Successes and critical failures of neural networks in capturing human-like speech recognition","volume":"162","author":"Adolfi","year":"2023","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2025.107783_b2","doi-asserted-by":"crossref","unstructured":"Almajai, I., Cox, S., Harvey, R., & Lan, Y. (2016). Improved speaker independent lip reading using speaker adaptive training and deep neural networks. In Proceedings of the IEEE international conference on acoustics, speech and signal processing (pp. 2722\u20132726).","DOI":"10.1109\/ICASSP.2016.7472172"},{"key":"10.1016\/j.neunet.2025.107783_b3","unstructured":"Ba, J., & Kingma, D. (2015). Adam: A Method for Stochastic Optimization. In Proceedings of the international conference on learning representations (pp. 1\u201315)."},{"key":"10.1016\/j.neunet.2025.107783_b4","doi-asserted-by":"crossref","unstructured":"Bakry, A., & Elgammal, A. (2013). Mkpls: Manifold kernel partial least squares for lipreading and speaker identification. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 684\u2013691).","DOI":"10.1109\/CVPR.2013.94"},{"issue":"9","key":"10.1016\/j.neunet.2025.107783_b5","doi-asserted-by":"crossref","first-page":"3711","DOI":"10.1109\/TNNLS.2019.2945992","article-title":"Xflow: Cross-modal deep neural networks for audiovisual classification","volume":"31","author":"Cangea","year":"2019","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.neunet.2025.107783_b6","doi-asserted-by":"crossref","unstructured":"Chang, O., Liao, H., Serdyuk, D., Shahy, A., & Siohan, O. (2024). Conformer is All You Need for Visual Speech Recognition. In Proceedings of the IEEE international conference on acoustics, speech and signal processing (pp. 10136\u201310140).","DOI":"10.1109\/ICASSP48485.2024.10446532"},{"key":"10.1016\/j.neunet.2025.107783_b7","unstructured":"Charpentier, B., Z\u00fcgner, D., & G\u00fcnnemann, S. (2020). Posterior network: Uncertainty estimation without ood samples via density-based pseudo-counts. In Proceedings of the annual conference on neural information processing systems (pp. 1356\u20131367)."},{"key":"10.1016\/j.neunet.2025.107783_b8","doi-asserted-by":"crossref","unstructured":"Chung, J. S., & Zisserman, A. (2017). Lip reading in the wild. In Proceedings of the Asian conference on computer vision (pp. 87\u2013103).","DOI":"10.1007\/978-3-319-54184-6_6"},{"issue":"2","key":"10.1016\/j.neunet.2025.107783_b9","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1111\/j.2517-6161.1968.tb00722.x","article-title":"A generalization of Bayesian inference","volume":"30","author":"Dempster","year":"1968","journal-title":"Journal of the Royal Statistical Society. Series B. Statistical Methodology"},{"key":"10.1016\/j.neunet.2025.107783_b10","doi-asserted-by":"crossref","unstructured":"Feng, D., Yang, S., & Shan, S. (2021). An Efficient Software for Building LIP Reading Models Without Pains. In Proceedings of the IEEE international conference on multimedia & expo workshops (pp. 1\u20132).","DOI":"10.1109\/ICMEW53276.2021.9456014"},{"key":"10.1016\/j.neunet.2025.107783_b11","doi-asserted-by":"crossref","unstructured":"Fenghour, S., Chen, D., & Xiao, P. (2019). Contour mapping for speaker-independent lip reading system. In Proceedings of the international conference on machine vision (pp. 282\u2013289).","DOI":"10.1117\/12.2522936"},{"issue":"1","key":"10.1016\/j.neunet.2025.107783_b12","first-page":"723","article-title":"A kernel two-sample test","volume":"13","author":"Gretton","year":"2012","journal-title":"Journal of Machine Learning Research"},{"issue":"2","key":"10.1016\/j.neunet.2025.107783_b13","doi-asserted-by":"crossref","first-page":"2551","DOI":"10.1109\/TPAMI.2022.3171983","article-title":"Trusted multi-view classification with dynamic evidential fusion","volume":"45","author":"Han","year":"2022","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2025.107783_b14","doi-asserted-by":"crossref","unstructured":"Hao, B., Zhou, D., Li, X., Zhang, X., Xie, L., Wu, J., & Yin, E. (2025). LipGen: Viseme-Guided Lip Video Generation for Enhancing Visual Speech Recognition. In Proceedings of the IEEE international conference on acoustics, speech, and signal processing (pp. 1\u20135).","DOI":"10.1109\/ICASSP49660.2025.10889163"},{"key":"10.1016\/j.neunet.2025.107783_b15","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 770\u2013778).","DOI":"10.1109\/CVPR.2016.90"},{"key":"10.1016\/j.neunet.2025.107783_b16","doi-asserted-by":"crossref","unstructured":"Hu, D., Li, X., et al. (2016). Temporal multimodal learning in audiovisual speech recognition. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 3574\u20133582).","DOI":"10.1109\/CVPR.2016.389"},{"key":"10.1016\/j.neunet.2025.107783_b17","doi-asserted-by":"crossref","unstructured":"Huang, Y., Liang, X., & Fang, C. (2021). CALLip: Lipreading using contrastive and attribute learning. In Proceedings of the ACM international conference on multimedia (pp. 2492\u20132500).","DOI":"10.1145\/3474085.3475420"},{"key":"10.1016\/j.neunet.2025.107783_b18","doi-asserted-by":"crossref","unstructured":"Kim, M., Kim, H., & Ro, Y. M. (2022). Speaker-adaptive lip reading with user-dependent padding. In Proceedings of the European conference on computer vision (pp. 576\u2013593).","DOI":"10.1007\/978-3-031-20059-5_33"},{"key":"10.1016\/j.neunet.2025.107783_b19","unstructured":"Kim, H. H., Yu, S., Yuan, S., & Tomasi, C. (2022). Cross-attention transformer for video interpolation. In Proceedings of the Asian conference on computer vision (pp. 320\u2013337)."},{"key":"10.1016\/j.neunet.2025.107783_b20","doi-asserted-by":"crossref","unstructured":"Koumparoulis, A., & Potamianos, G. (2022). Accurate and Resource-Efficient Lipreading with Efficientnetv2 and Transformers. In Proceedings of the IEEE international conference on acoustics, speech and signal processing (pp. 8467\u20138471).","DOI":"10.1109\/ICASSP43922.2022.9747729"},{"key":"10.1016\/j.neunet.2025.107783_b21","doi-asserted-by":"crossref","unstructured":"Lea, C., Flynn, M. D., Vidal, R., Reiter, A., & Hager, G. D. (2017). Temporal convolutional networks for action segmentation and detection. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 156\u2013165).","DOI":"10.1109\/CVPR.2017.113"},{"key":"10.1016\/j.neunet.2025.107783_b22","doi-asserted-by":"crossref","first-page":"2707","DOI":"10.1109\/TASLP.2023.3294705","article-title":"Audio-visual end-to-end multi-channel speech separation, dereverberation and recognition","volume":"31","author":"Li","year":"2023","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"key":"10.1016\/j.neunet.2025.107783_b23","doi-asserted-by":"crossref","first-page":"1941","DOI":"10.1109\/TASLP.2024.3375641","article-title":"Unified Cross-Modal attention: Robust Audio-Visual speech recognition and beyond","volume":"32","author":"Li","year":"2024","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"issue":"12","key":"10.1016\/j.neunet.2025.107783_b24","doi-asserted-by":"crossref","first-page":"6999","DOI":"10.1109\/TNNLS.2021.3084827","article-title":"A survey of convolutional neural networks: analysis, applications, and prospects","volume":"33","author":"Li","year":"2021","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"1","key":"10.1016\/j.neunet.2025.107783_b25","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1007\/s00530-023-01226-3","article-title":"Generalizing sentence-level lipreading to unseen speakers: a two-stream end-to-end approach","volume":"30","author":"Li","year":"2024","journal-title":"Multimedia Systems"},{"key":"10.1016\/j.neunet.2025.107783_b26","doi-asserted-by":"crossref","first-page":"8415","DOI":"10.1007\/s10489-024-05623-7","article-title":"A transformer-encoder-based multimodal multi-attention fusion network for sentiment analysis","volume":"54","author":"Liu","year":"2024","journal-title":"Applied Intelligence: The International Journal of Artificial Intelligence, Neural Networks, and Complex Problem-Solving Technologies"},{"key":"10.1016\/j.neunet.2025.107783_b27","series-title":"Proceedings of the IEEE international conference on acoustics, speech and signal processing","first-page":"1","article-title":"Auto-avsr: Audio-visual speech recognition with automatic labels","author":"Ma","year":"2023"},{"key":"10.1016\/j.neunet.2025.107783_b28","doi-asserted-by":"crossref","unstructured":"Ma, P., Petridis, S., & Pantic, M. (2021). End-to-end audio-visual speech recognition with conformers. In Proceedings of the IEEE international conference on acoustics, speech and signal processing (pp. 7613\u20137617).","DOI":"10.1109\/ICASSP39728.2021.9414567"},{"issue":"11","key":"10.1016\/j.neunet.2025.107783_b29","doi-asserted-by":"crossref","first-page":"930","DOI":"10.1038\/s42256-022-00550-z","article-title":"Visual speech recognition for multiple languages in the wild","volume":"4","author":"Ma","year":"2022","journal-title":"Nature Machine Intelligence"},{"key":"10.1016\/j.neunet.2025.107783_b30","unstructured":"Malinin, A., & Gales, M. (2018). Predictive uncertainty estimation via prior networks. In Proceedings of the annual conference on neural information processing systems (pp. 1\u201312)."},{"key":"10.1016\/j.neunet.2025.107783_b31","doi-asserted-by":"crossref","unstructured":"Martinez, B., Ma, P., Petridis, S., & Pantic, M. (2020). Lipreading Using Temporal Convolutional Networks. In Proceedings of the IEEE international conference on acoustics, speech and signal processing (pp. 6319\u20136323).","DOI":"10.1109\/ICASSP40776.2020.9053841"},{"issue":"2","key":"10.1016\/j.neunet.2025.107783_b32","doi-asserted-by":"crossref","first-page":"198","DOI":"10.1109\/34.982900","article-title":"Extraction of visual features for lipreading","volume":"24","author":"Matthews","year":"2002","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2025.107783_b33","doi-asserted-by":"crossref","unstructured":"Mo, S., & Morgado, P. (2024). Unveiling the Power of Audio-Visual Early Fusion Transformers with Dense Interactions through Masked Modeling. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 27186\u201327196).","DOI":"10.1109\/CVPR52733.2024.02567"},{"key":"10.1016\/j.neunet.2025.107783_b34","doi-asserted-by":"crossref","unstructured":"Mo, S., & Tian, Y. (2023). Audio-visual grouping network for sound localization from mixtures. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 10565\u201310574).","DOI":"10.1109\/CVPR52729.2023.01018"},{"key":"10.1016\/j.neunet.2025.107783_b35","doi-asserted-by":"crossref","unstructured":"Pan, X., Chen, P., Gong, Y., Zhou, H., Wang, X., & Lin, Z. (2022). Leveraging Unimodal Self-Supervised Learning for Multimodal Audio-Visual Speech Recognition. In Proceedings of the 60th annual meeting of the association for computational linguistics (volume 1: long papers) (pp. 4491\u20134503).","DOI":"10.18653\/v1\/2022.acl-long.308"},{"key":"10.1016\/j.neunet.2025.107783_b36","doi-asserted-by":"crossref","unstructured":"Petridis, S., Li, Z., & Pantic, M. (2017). End-to-end visual speech recognition with LSTMS. In Proceedings of the IEEE international conference on acoustics, speech and signal processing (pp. 2592\u20132596).","DOI":"10.1109\/ICASSP.2017.7952625"},{"key":"10.1016\/j.neunet.2025.107783_b37","doi-asserted-by":"crossref","unstructured":"Petridis, S., Shen, J., Cetin, D., & Pantic, M. (2018). Visual-Only Recognition of Normal, Whispered and Silent Speech. In Proceedings of the IEEE international conference on acoustics, speech and signal processing (pp. 6219\u20136223).","DOI":"10.1109\/ICASSP.2018.8461596"},{"key":"10.1016\/j.neunet.2025.107783_b38","doi-asserted-by":"crossref","unstructured":"Petridis, S., Stafylakis, T., Ma, P., Cai, F., Tzimiropoulos, G., & Pantic, M. (2018). End-to-end audiovisual speech recognition. In Proceedings of the IEEE international conference on acoustics, speech and signal processing (pp. 6548\u20136552).","DOI":"10.1109\/ICASSP.2018.8461326"},{"key":"10.1016\/j.neunet.2025.107783_b39","doi-asserted-by":"crossref","first-page":"421","DOI":"10.1016\/j.patrec.2020.01.022","article-title":"End-to-end visual speech recognition for small-scale datasets","volume":"131","author":"Petridis","year":"2020","journal-title":"Pattern Recognition Letters"},{"key":"10.1016\/j.neunet.2025.107783_b40","doi-asserted-by":"crossref","unstructured":"Prajwal, K., Afouras, T., & Zisserman, A. (2022). Sub-word level lip reading with visual attention. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 5162\u20135172).","DOI":"10.1109\/CVPR52688.2022.00510"},{"key":"10.1016\/j.neunet.2025.107783_b41","doi-asserted-by":"crossref","first-page":"334","DOI":"10.1016\/j.neucom.2019.10.076","article-title":"Multi-scale feature fusion residual network for single image super-resolution","volume":"379","author":"Qin","year":"2020","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neunet.2025.107783_b42","doi-asserted-by":"crossref","first-page":"494","DOI":"10.1016\/j.neunet.2023.01.027","article-title":"Emphasizing unseen words: New vocabulary acquisition for end-to-end speech recognition","volume":"161","author":"Qu","year":"2023","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2025.107783_b43","unstructured":"Sensoy, M., Kaplan, L., & Kandemir, M. (2018). Evidential deep learning to quantify classification uncertainty. In Proceedings of the annual conference on neural information processing systems (pp. 1\u201311)."},{"issue":"9","key":"10.1016\/j.neunet.2025.107783_b44","doi-asserted-by":"crossref","first-page":"6001","DOI":"10.1109\/TPAMI.2024.3376710","article-title":"Deep learning for visual speech analysis: A survey","volume":"46","author":"Sheng","year":"2024","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2025.107783_b45","unstructured":"Shi, B., Hsu, W.-N., Lakhotia, K., & Mohamed, A. (2022). Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction. In Proceedings of the international conference on learning representations (pp. 1\u201312)."},{"key":"10.1016\/j.neunet.2025.107783_b46","doi-asserted-by":"crossref","unstructured":"Shillingford, B., Assael, Y., Hoffman, M. W., Paine, T., Hughes, C., Prabhu, U., Liao, H., Sak, H., Rao, K., Bennett, L., Mulville, M., Denil, M., Coppin, B., Laurie, B., Senior, A., & de Freitas, N. (2019). Large-Scale Visual Speech Recognition. In Proceedings of the Interspeech (pp. 4135\u20134139).","DOI":"10.21437\/Interspeech.2019-1669"},{"key":"10.1016\/j.neunet.2025.107783_b47","unstructured":"Sutskever, I., Martens, J., & Hinton, G. E. (2011). Generating text with recurrent neural networks. In Proceedings of the international conference on machine learning (pp. 1017\u20131024)."},{"key":"10.1016\/j.neunet.2025.107783_b48","doi-asserted-by":"crossref","unstructured":"Tang, Z., Qiu, Z., Hao, Y., Hong, R., & Yao, T. (2023). 3D human pose estimation with spatio-temporal criss-cross attention. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 4790\u20134799).","DOI":"10.1109\/CVPR52729.2023.00464"},{"key":"10.1016\/j.neunet.2025.107783_b49","doi-asserted-by":"crossref","unstructured":"Tao, F., & Busso, C. (2014). Lipreading approach for isolated digits recognition under whisper and neutral speech. In Proceedings of the INTERSPEECH (pp. 1154\u20131158).","DOI":"10.21437\/Interspeech.2014-294"},{"key":"10.1016\/j.neunet.2025.107783_b50","doi-asserted-by":"crossref","unstructured":"Thangthai, K., & Harvey, R. W. (2018). Building Large-vocabulary Speaker-independent Lipreading Systems. In Proceedings of the INTERSPEECH (pp. 2648\u20132652).","DOI":"10.21437\/Interspeech.2018-2112"},{"key":"10.1016\/j.neunet.2025.107783_b51","doi-asserted-by":"crossref","unstructured":"Wand, M., & Schmidhuber, J. (2017). Improving Speaker-Independent Lipreading with Domain-Adversarial Training. In Proceedings of the INTERSPEECH (pp. 3662\u20133666).","DOI":"10.21437\/Interspeech.2017-421"},{"issue":"1","key":"10.1016\/j.neunet.2025.107783_b52","doi-asserted-by":"crossref","first-page":"6757","DOI":"10.1038\/s41467-023-42444-7","article-title":"Uncertainty-inspired open set learning for retinal anomaly identification","volume":"14","author":"Wang","year":"2023","journal-title":"Nature Communications"},{"key":"10.1016\/j.neunet.2025.107783_b53","doi-asserted-by":"crossref","unstructured":"Wang, W., Tran, D., & Feiszli, M. (2020). What makes training multi-modal classification networks hard?. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 12695\u201312705).","DOI":"10.1109\/CVPR42600.2020.01271"},{"key":"10.1016\/j.neunet.2025.107783_b54","unstructured":"Wu, L., Zhang, X., Zhang, Y., Zheng, C., Liu, T., Xie, L., Yan, Y., & Yin, E. (2024). Landmark-Guided Cross-Speaker Lip Reading with Mutual Information Regularization. In Proceedings of the joint international conference on computational linguistics, language resources and evaluation (pp. 10023\u201310033)."},{"key":"10.1016\/j.neunet.2025.107783_b55","doi-asserted-by":"crossref","unstructured":"Wu, J., Zhang, Y., Zhang, X., Zheng, C., Yan, Y., & Yin, E. (2023). Improving Visual Speech Recognition for Small-Scale Datasets via Speaker Embedding. In Proceedings of the international conference on software engineering and computer science (pp. 206\u2013211).","DOI":"10.1109\/CSECS60003.2023.10428144"},{"issue":"9","key":"10.1016\/j.neunet.2025.107783_b56","doi-asserted-by":"crossref","first-page":"4507","DOI":"10.1109\/TCSVT.2023.3282224","article-title":"LipFormer: Learning to lipread unseen speakers based on Visual-Landmark transformers","volume":"33","author":"Xue","year":"2023","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.neunet.2025.107783_b57","doi-asserted-by":"crossref","unstructured":"Yang, C.-C., Fan, W.-C., Yang, C.-F., & Wang, Y.-C. F. (2022). Cross-modal mutual learning for audio-visual speech recognition and manipulation. In Proceedings of the AAAI conference on artificial intelligence (pp. 3036\u20133044).","DOI":"10.1609\/aaai.v36i3.20210"},{"key":"10.1016\/j.neunet.2025.107783_b58","first-page":"1","article-title":"A small-sized object detection oriented multi-scale feature fusion approach with application to defect detection","volume":"71","author":"Zeng","year":"2022","journal-title":"IEEE Transactions on Instrumentation and Measurement"},{"key":"10.1016\/j.neunet.2025.107783_b59","doi-asserted-by":"crossref","unstructured":"Zhang, X., Cheng, F., & Wang, S. (2019). Spatio-temporal fusion based convolutional sequence learning for lip reading. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 713\u2013722).","DOI":"10.1109\/ICCV.2019.00080"},{"key":"10.1016\/j.neunet.2025.107783_b60","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.111407","article-title":"Reliable fault diagnosis using evidential aggregated residual network under varying working conditions and noise interference","volume":"286","author":"Zhou","year":"2024","journal-title":"Knowledge-Based Systems"},{"key":"10.1016\/j.neunet.2025.107783_b61","doi-asserted-by":"crossref","first-page":"4986","DOI":"10.1109\/TMM.2022.3185894","article-title":"COutfitGAN: Learning to synthesize compatible outfits supervised by silhouette masks and fashion styles","volume":"25","author":"Zhou","year":"2023","journal-title":"IEEE Transactions on Multimedia"},{"issue":"4","key":"10.1016\/j.neunet.2025.107783_b62","doi-asserted-by":"crossref","first-page":"5226","DOI":"10.1109\/TNNLS.2022.3202842","article-title":"Learning to synthesize compatible fashion items using semantic alignment and collocation classification: An outfit generation framework","volume":"35","author":"Zhou","year":"2024","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S089360802500663X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S089360802500663X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T20:55:00Z","timestamp":1756846500000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S089360802500663X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":62,"alternative-id":["S089360802500663X"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2025.107783","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2025,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"MsDUNE: A multi-scale masked temporal fusion framework for speaker-independent lipreading via Dirichlet uncertainty estimation","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2025.107783","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"107783"}}