{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T11:06:24Z","timestamp":1785927984317,"version":"3.56.0"},"publisher-location":"New York, NY, USA","reference-count":50,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612460","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:30Z","timestamp":1698391650000},"page":"747-756","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["Slow-Fast Time Parameter Aggregation Network for Class-Incremental Lip Reading"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-2394-3518","authenticated-orcid":false,"given":"Xueyi","family":"Zhang","sequence":"first","affiliation":[{"name":"National University of Defense Technology & Shenzhen Research Institute of Big Data, School of Data Science, The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen), Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3375-2458","authenticated-orcid":false,"given":"Chengwei","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9002-2630","authenticated-orcid":false,"given":"Tao","family":"Wang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Machine Perception, Shenzhen Graduate School, Peking University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4696-0432","authenticated-orcid":false,"given":"Jun","family":"Tang","sequence":"additional","affiliation":[{"name":"School of systems engineering, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8025-3766","authenticated-orcid":false,"given":"Songyang","family":"Lao","sequence":"additional","affiliation":[{"name":"School of systems engineering, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9158-9401","authenticated-orcid":false,"given":"Haizhou","family":"Li","sequence":"additional","affiliation":[{"name":"Shenzhen Research Institute of Big Data, School of Data Science, The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen), Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Andrew Senior, Oriol Vinyals, and Andrew Zisserman.","author":"Afouras Triantafyllos","year":"2018","unstructured":"Triantafyllos Afouras, Joon Son Chung, Andrew Senior, Oriol Vinyals, and Andrew Zisserman. 2018. Deep audio-visual speech recognition. IEEE transactions on pattern analysis and machine intelligence 44, 12 (2018), 8717--8727."},{"key":"e_1_3_2_2_2_1","volume-title":"Lipnet: End-to-end sentence-level lipreading. arXiv preprint arXiv:1611.01599","author":"Assael Yannis M","year":"2016","unstructured":"Yannis M Assael, Brendan Shillingford, Shimon Whiteson, and Nando De Freitas. 2016. Lipnet: End-to-end sentence-level lipreading. arXiv preprint arXiv:1611.01599 (2016)."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00812"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_33"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3277018"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3109530"},{"key":"e_1_3_2_2_8_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00907"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414659"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_2_13_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"e_1_3_2_2_15_1","volume-title":"Proceedings of the ieee\/cvf conference on computer vision and pattern recognition. 7872--7881","author":"Li Chao","year":"2019","unstructured":"Chao Li, Qiaoyong Zhong, Di Xie, and Shiliang Pu. 2019. Collaborative spatiotem-poral feature learning for video action recognition. In Proceedings of the ieee\/cvf conference on computer vision and pattern recognition. 7872--7881."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00099"},{"key":"e_1_3_2_2_17_1","volume-title":"Preserving earlier knowledge in continual learning with the help of all previous feature extractors. arXiv preprint arXiv:2104.13614","author":"Li Zhuoyun","year":"2021","unstructured":"Zhuoyun Li, Changhong Zhong, Sijia Liu, Ruixuan Wang, and Wei-Shi Zheng. 2021. Preserving earlier knowledge in continual learning with the help of all previous feature extractors. arXiv preprint arXiv:2104.13614 (2021)."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_21"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01345"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415063"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746706"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053841"},{"key":"e_1_3_2_2_24_1","volume-title":"Class-incremental learning: survey and performance evaluation on image classification","author":"Masana Marc","year":"2022","unstructured":"Marc Masana, Xialei Liu, Bart\u0140omiej Twardowski, Mikel Menta, Andrew D Bagdanov, and Joost van de Weijer. 2022. Class-incremental learning: survey and performance evaluation on image classification. IEEE Transactions on Pattern Analysis and Machine Intelligence (2022)."},{"key":"e_1_3_2_2_25_1","volume-title":"Distance-based image classification: Generalizing to new classes at near-zero cost","author":"Mensink Thomas","year":"2013","unstructured":"Thomas Mensink, Jakob Verbeek, Florent Perronnin, and Gabriela Csurka. 2013. Distance-based image classification: Generalizing to new classes at near-zero cost. IEEE transactions on pattern analysis and machine intelligence 35, 11 (2013), 2624--2637."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461326"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00510"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.587"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475415"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"e_1_3_2_2_31_1","volume-title":"International conference on machine learning. PMLR, 6105--6114","author":"Tan Mingxing","year":"2019","unstructured":"Mingxing Tan and Quoc Le. 2019. Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning. PMLR, 6105--6114."},{"key":"e_1_3_2_2_32_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01845"},{"key":"e_1_3_2_2_34_1","volume-title":"Tel Aviv","author":"Wang Fu-Yun","year":"2022","unstructured":"Fu-Yun Wang, Da-Wei Zhou, Han-Jia Ye, and De-Chuan Zhan. 2022. Foster: Feature boosting and compression for class-incremental learning. In Computer Vision-ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part XXV. Springer, 398--414."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00193"},{"key":"e_1_3_2_2_36_1","first-page":"3347","article-title":"Learning spatiotemporal and motion features in a unified 2d network for action recognition","volume":"45","author":"Wang Mengmeng","year":"2022","unstructured":"Mengmeng Wang, Jiazheng Xing, Jing Su, Jun Chen, and Yong Liu. 2022. Learning spatiotemporal and motion features in a unified 2d network for action recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence 45, 3 (2022), 3347--3362.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_2_37_1","volume-title":"International Conference on Machine Learning. PMLR, 23965--23998","author":"Wortsman Mitchell","year":"2022","unstructured":"Mitchell Wortsman, Gabriel Ilharco, Samir Ya Gadre, Rebecca Roelofs, Raphael Gontijo-Lopes, Ari S Morcos, Hongseok Namkoong, Ali Farhadi, Yair Carmon, Simon Kornblith, et al. 2022. Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time. In International Conference on Machine Learning. PMLR, 23965--23998."},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16401"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00046"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00303"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00805"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00883"},{"key":"e_1_3_2_2_43_1","volume-title":"Lifelong learning with dynamically expandable networks. arXiv preprint arXiv:1708.01547","author":"Yoon Jaehong","year":"2017","unstructured":"Jaehong Yoon, Eunho Yang, Jeongtae Lee, and Sung Ju Hwang. 2017. Lifelong learning with dynamically expandable networks. arXiv preprint arXiv:1708.01547 (2017)."},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01227"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00692"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00080"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859810"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3072041"},{"key":"e_1_3_2_2_49_1","volume-title":"A model or 603 exemplars: Towards memory-efficient class-incremental learning. arXiv preprint arXiv:2205.13218","author":"Zhou Da-Wei","year":"2022","unstructured":"Da-Wei Zhou, Qi-Wei Wang, Han-Jia Ye, and De-Chuan Zhan. 2022. A model or 603 exemplars: Towards memory-efficient class-incremental learning. arXiv preprint arXiv:2205.13218 (2022)."},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01453"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612460","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612460","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:06:48Z","timestamp":1755821208000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612460"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":50,"alternative-id":["10.1145\/3581783.3612460","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612460","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}