{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T14:56:12Z","timestamp":1761404172206,"version":"build-2065373602"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","funder":[{"name":"National Natural Science Foundation of China","award":["62271307"],"award-info":[{"award-number":["62271307"]}]},{"name":"the robotic AI-Scientist platform of Chinese Academy of Sciences","award":[""],"award-info":[{"award-number":[""]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3728481.3762165","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T14:53:41Z","timestamp":1761404021000},"page":"40-48","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Landmark Guided Visual Feature Extractor for Visual Speech Recognition with Limited Resource"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7508-2341","authenticated-orcid":false,"given":"Lei","family":"Yang","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0860-6579","authenticated-orcid":false,"given":"Junshan","family":"Jin","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3409-6947","authenticated-orcid":false,"given":"Mingyuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2121-6076","authenticated-orcid":false,"given":"Yi","family":"He","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3241-6122","authenticated-orcid":false,"given":"Bofan","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8214-6809","authenticated-orcid":false,"given":"Shi-Lin","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,26]]},"reference":[{"key":"e_1_3_2_1_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, Vol. 44, 12 (2018), 8717-8727."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.116"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00229"},{"key":"e_1_3_2_1_4_1","volume-title":"ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 10136-10140","author":"Chang Oscar","year":"2024","unstructured":"Oscar Chang, Hank Liao, Dmitriy Serdyuk, Ankit Shahy, and Olivier Siohan. 2024. Conformer is All You Need for Visual Speech Recognition. In ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 10136-10140."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3652583.3658101"},{"key":"e_1_3_2_1_6_1","volume-title":"ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 1-5.","author":"Chen Chen","year":"2023","unstructured":"Chen Chen, Dong Wang, and Thomas Fang Zheng. 2023. CN-CVS: A mandarin audio-visual dataset for large vocabulary continuous visual to speech synthesis. In ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 1-5."},{"key":"e_1_3_2_1_7_1","volume-title":"22nd Annual Conference of the International Speech Communication Association","author":"Chen Hang","year":"2021","unstructured":"Hang Chen, Jun Du, Yu Hu, Li-Rong Dai, Bao-Cai Yin, and Chin-Hui Lee. 2021. Automatic Lip-Reading with Hierarchical Pyramidal Convolution and Self-Attention for Image Sequences with No Word Boundaries. In Interspeech 2021 (Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August - 3 September 2021). ISCA."},{"key":"e_1_3_2_1_8_1","first-page":"87","volume-title":"Taipei","author":"Chung Joon Son","year":"2017","unstructured":"Joon Son Chung and Andrew Zisserman. 2017. Lip reading in the wild. In Computer Vision-ACCV 2016: 13th Asian Conference on Computer Vision, Taipei, Taiwan, November 20-24, 2016, Revised Selected Papers, Part II 13. Springer, 87-103."},{"key":"e_1_3_2_1_9_1","volume-title":"ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 7988-7992","author":"Hao Mingfeng","year":"2021","unstructured":"Mingfeng Hao, Mutallip Mamut, Nurbiya Yadikar, Alimjan Aysa, and Kurban Ubul. 2021. 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). IEEE, 7988-7992."},{"key":"e_1_3_2_1_10_1","volume-title":"Speaker-Adaptive Lipreading Via Spatio-Temporal Information Learning. In ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 10411-10415","author":"He Yi","year":"2024","unstructured":"Yi He, Lei Yang, Hanyi Wang, Yun Zhu, and Shilin Wang. 2024b. Speaker-Adaptive Lipreading Via Spatio-Temporal Information Learning. In ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 10411-10415."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3405640"},{"key":"e_1_3_2_1_12_1","volume-title":"European Conference on Computer Vision. Springer, 576-593","author":"Kim Minsu","year":"2022","unstructured":"Minsu Kim, Hyunjun Kim, and Yong Man Ro. 2022a. Speaker-adaptive lip reading with user-dependent padding. In European Conference on Computer Vision. Springer, 576-593."},{"key":"e_1_3_2_1_13_1","volume-title":"European Conference on Computer Vision. Springer, 576-593","author":"Kim Minsu","year":"2022","unstructured":"Minsu Kim, Hyunjun Kim, and Yong Man Ro. 2022b. Speaker-adaptive lip reading with user-dependent padding. In European Conference on Computer Vision. Springer, 576-593."},{"key":"e_1_3_2_1_14_1","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision. 15359-15371","author":"Kim Minsu","year":"2023","unstructured":"Minsu Kim, Jeong Hun Yeo, Jeongsoo Choi, and Yong Man Ro. 2023. Lip reading for low-resource languages by learning and combining general speech knowledge and language-specific knowledge. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 15359-15371."},{"key":"e_1_3_2_1_15_1","first-page":"149","volume-title":"Proceedings of the 3rd Annual Meeting of the Special Interest Group on Under-resourced Languages@ LREC-COLING","author":"Kondo Fumiya","year":"2024","unstructured":"Fumiya Kondo and Satoshi Tamura. 2024. Inter-language Transfer Learning for Visual Speech Recognition toward Under-resourced Environments. In Proceedings of the 3rd Annual Meeting of the Special Interest Group on Under-resourced Languages@ LREC-COLING 2024. 149-154."},{"key":"e_1_3_2_1_16_1","volume-title":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE.","author":"Koumparoulis Alexandros","year":"2022","unstructured":"Alexandros Koumparoulis and Gerasimos Potamianos. 2022. Accurate and Resource-Efficient Lipreading with Efficientnetv2 and Transformers. In ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE."},{"key":"e_1_3_2_1_17_1","first-page":"881","volume-title":"18th International Conference on Pattern Recognition (ICPR'06)","volume":"3","author":"Leung SH","year":"2006","unstructured":"SH Leung, AWC Liew, WH Lau, and SL Wang. 2006. Automatic lipreading with limited training data. In 18th International Conference on Pattern Recognition (ICPR'06), Vol. 3. IEEE, 881-884."},{"key":"e_1_3_2_1_18_1","first-page":"1","article-title":"Generalizing sentence-level lipreading to unseen speakers: a two-stream end-to-end approach","volume":"30","author":"Li Yu","year":"2024","unstructured":"Yu Li, Feng Xue, Lin Wu, Yincen Xie, and Shujie Li. 2024. Generalizing sentence-level lipreading to unseen speakers: a two-stream end-to-end approach. Multimedia Systems, Vol. 30, 1 (Jan. 2024).","journal-title":"Multimedia Systems"},{"key":"e_1_3_2_1_19_1","first-page":"3520","article-title":"Lip Graph Assisted Audio-Visual Speech Recognition Using Bidirectional Synchronous Fusion","author":"Liu Hong","year":"2020","unstructured":"Hong Liu, Zhan Chen, and Bing Yang. 2020. Lip Graph Assisted Audio-Visual Speech Recognition Using Bidirectional Synchronous Fusion.. In INTERSPEECH. 3520-3524.","journal-title":"INTERSPEECH."},{"key":"e_1_3_2_1_20_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 18806-18815","author":"Liu Xubo","year":"2023","unstructured":"Xubo Liu, Egor Lakomkin, Konstantinos Vougioukas, Pingchuan Ma, Honglie Chen, Ruiming Xie, Morrie Doulaty, Niko Moritz, Jachym Kolar, Stavros Petridis, et al., 2023. Synthvsr: Scaling up visual speech recognition with synthetic supervision. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 18806-18815."},{"key":"e_1_3_2_1_21_1","volume-title":"Proceedings of the HCSNet Workshop on the Use of Vision in Human-Computer Interaction. Australian Computer Society, 79-85","author":"Lucey Patrick","year":"2007","unstructured":"Patrick Lucey and Subramanian Sridharan. 2007. Patch-based representation of visual speech. In Proceedings of the HCSNet Workshop on the Use of Vision in Human-Computer Interaction. Australian Computer Society, 79-85."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096889"},{"key":"e_1_3_2_1_23_1","volume-title":"Lira: Learning visual speech representations from audio through self-supervision. arXiv preprint arXiv:2106.09171","author":"Ma Pingchuan","year":"2021","unstructured":"Pingchuan Ma, Rodrigo Mira, Stavros Petridis, Bj\u00f6rn W Schuller, and Maja Pantic. 2021a. Lira: Learning visual speech representations from audio through self-supervision. arXiv preprint arXiv:2106.09171 (2021)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00550-z"},{"key":"e_1_3_2_1_25_1","volume-title":"ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 8472-8476","author":"Ma Pingchuan","year":"2022","unstructured":"Pingchuan Ma, Yujiang Wang, Stavros Petridis, Jie Shen, and Maja Pantic. 2022b. Training strategies for improved lip-reading. In ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 8472-8476."},{"key":"e_1_3_2_1_26_1","volume-title":"Lip-reading with Densely Connected Temporal Convolutional Networks. In 2021 IEEE Winter Conference on Applications of Computer Vision (WACV). IEEE.","author":"Ma Pingchuan","year":"2021","unstructured":"Pingchuan Ma, Yujiang Wang, Jie Shen, Stavros Petridis, and Maja Pantic. 2021b. Lip-reading with Densely Connected Temporal Convolutional Networks. In 2021 IEEE Winter Conference on Applications of Computer Vision (WACV). IEEE."},{"key":"e_1_3_2_1_27_1","volume-title":"2020 IEEE Fifth International Conference on Data Science in Cyberspace (DSC). IEEE, 78-81","author":"Ma Shihui","year":"2020","unstructured":"Shihui Ma, Shilin Wang, and Xiang Lin. 2020. A transformer-based model for sentence-level Chinese Mandarin lipreading. In 2020 IEEE Fifth International Conference on Data Science in Cyberspace (DSC). IEEE, 78-81."},{"key":"e_1_3_2_1_28_1","volume-title":"2022 IEEE International Conference on Image Processing (ICIP). IEEE, 2561-2565","author":"Ma Xinghua","year":"2022","unstructured":"Xinghua Ma and Shilin Wang. 2022. Chinese Mandarin Lipreading using Cascaded Transformers with Multiple Intermediate Representations. In 2022 IEEE International Conference on Image Processing (ICIP). IEEE, 2561-2565."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053841"},{"key":"e_1_3_2_1_30_1","first-page":"689","volume-title":"ICML","volume":"11","author":"Ngiam Jiquan","year":"2011","unstructured":"Jiquan Ngiam, Aditya Khosla, Mingyu Kim, Juhan Nam, Honglak Lee, Andrew Y Ng, et al., 2011. Multimodal deep learning.. In ICML, Vol. 11. 689-696."},{"key":"e_1_3_2_1_31_1","volume-title":"2007 IEEE 9th Workshop on Multimedia Signal Processing. IEEE, 264-267","author":"Papandreou George","year":"2007","unstructured":"George Papandreou, Athanassios Katsamanis, Vassilis Pitsikalis, and Petros Maragos. 2007. Multimodal fusion and learning with uncertain features applied to audiovisual speech recognition. In 2007 IEEE 9th Workshop on Multimedia Signal Processing. IEEE, 264-267."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.5555\/2209818.2210642"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952625"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"crossref","first-page":"6563","DOI":"10.1109\/TMM.2022.3210761","article-title":"Importance-aware information bottleneck learning paradigm for lip reading","volume":"25","author":"Sheng Changchong","year":"2022","unstructured":"Changchong Sheng, Li Liu, Wanxia Deng, Liang Bai, Zhong Liu, Songyang Lao, Gangyao Kuang, and Matti Pietik\u00e4inen. 2022. Importance-aware information bottleneck learning paradigm for lip reading. IEEE Transactions on Multimedia, Vol. 25 (2022), 6563-6574.","journal-title":"IEEE Transactions on Multimedia"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"e_1_3_2_1_36_1","first-page":"3652","volume-title":"18th Annual Conference of the International Speech Communication Association","author":"Stafylakis Themos","year":"2017","unstructured":"Themos Stafylakis and Georgios Tzimiropoulos. 2017. Combining Residual Networks with LSTMs for Lipreading. In Interspeech 2017, 18th Annual Conference of the International Speech Communication Association, Stockholm, Sweden, August 20-24, 2017. ISCA, 3652-3656."},{"key":"e_1_3_2_1_37_1","first-page":"10023","volume-title":"Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING","author":"Wu Linzhi","year":"2024","unstructured":"Linzhi Wu, Xingyu Zhang, Yakun Zhang, Changyan Zheng, Tiejun Liu, Liang Xie, Ye Yan, and Erwei Yin. 2024. Landmark-Guided Cross-Speaker Lip Reading with Mutual Information Regularization. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, and Nianwen Xue (Eds.). ELRA and ICCL, Torino, Italia, 10023-10033."},{"key":"e_1_3_2_1_38_1","first-page":"9","article-title":"LipFormer: Learning to Lipread Unseen Speakers Based on Visual-Landmark Transformers","volume":"33","author":"Xue Feng","year":"2023","unstructured":"Feng Xue, Yu Li, Deyin Liu, Yincen Xie, Lin Wu, and Richang Hong. 2023. LipFormer: Learning to Lipread Unseen Speakers Based on Visual-Landmark Transformers. IEEE Transactions on Circuits and Systems for Video Technology, Vol. 33, 9 (Sept. 2023), 4507-4517.","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"e_1_3_2_1_39_1","volume-title":"2004 IEEE International Symposium on Circuits and Systems (IEEE Cat. No. 04CH37512)","volume":"2","author":"Yan H","year":"2004","unstructured":"H Yan. 2004. A real-time automatic lipreading system. In 2004 IEEE International Symposium on Circuits and Systems (IEEE Cat. No. 04CH37512), Vol. 2. IEEE, II-101."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"crossref","first-page":"349","DOI":"10.1109\/TFUZZ.2023.3298323","article-title":"Fine-grained lip image segmentation using fuzzy logic and graph reasoning","volume":"32","author":"Yang Lei","year":"2023","unstructured":"Lei Yang, Shilin Wang, and Alan Wee-Chung Liew. 2023. Fine-grained lip image segmentation using fuzzy logic and graph reasoning. IEEE Transactions on Fuzzy Systems, Vol. 32, 2 (2023), 349-359.","journal-title":"IEEE Transactions on Fuzzy Systems"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.596"},{"key":"e_1_3_2_1_42_1","volume-title":"ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 10471-10475","author":"Yeo Jeong Hun","year":"2024","unstructured":"Jeong Hun Yeo, Minsu Kim, Shinji Watanabe, and Yong Man Ro. 2024. Visual Speech Recognition for Languages with Limited Labeled Data Using Automatic Labels from Whisper. In ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 10471-10475."},{"key":"e_1_3_2_1_43_1","volume-title":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence. International Joint Conferences on Artificial Intelligence Organization, 3634-3640","author":"Yu Bing","year":"2018","unstructured":"Bing Yu, Haoteng Yin, and Zhanxing Zhu. 2018. Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting. In Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence. International Joint Conferences on Artificial Intelligence Organization, 3634-3640."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00134"}],"event":{"name":"MM '25:The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 4th International Workshop on Multimodal Human Understanding for the Web and Social Media"],"original-title":[],"deposited":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T14:53:56Z","timestamp":1761404036000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3728481.3762165"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,26]]},"references-count":44,"alternative-id":["10.1145\/3728481.3762165","10.1145\/3728481"],"URL":"https:\/\/doi.org\/10.1145\/3728481.3762165","relation":{},"subject":[],"published":{"date-parts":[[2025,10,26]]},"assertion":[{"value":"2025-10-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}