{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/multi-grained-spatio-temporal-modeling-for","title":"Multi-Grained Spatio-temporal Modeling for Lip-reading","arxiv_id":"1908.11618","date":"2019-08-30","proceeding":null,"authors":["Chenhao Wang"],"abstract":"Lip-reading aims to recognize speech content from videos via visual analysis of speakers' lip movements. This is a challenging task due to the existence of homophemes-words which involve identical or highly similar lip movements, as well as diverse lip appearances and motion patterns among the speakers. To address these challenges, we propose a novel lip-reading model which captures not only the nuance between words but also styles of different speakers, by a multi-grained spatio-temporal modeling of the speaking process. Specifically, we first extract both frame-level fine-grained features and short-term medium-grained features by the visual front-end, which are then combined to obtain discriminative representations for words with similar phonemes. Next, a bidirectional ConvLSTM augmented with temporal attention aggregates spatio-temporal information in the entire input sequence, which is expected to be able to capture the coarse-gained patterns of each word and robust to various conditions in speaker identity, lighting conditions, and so on. By making full use of the information from different levels in a unified framework, the model is not only able to distinguish words with similar pronunciations, but also becomes robust to appearance changes. We evaluate our method on two challenging word-level lip-reading benchmarks and show the effectiveness of the proposed method, which also demonstrate the above claims.","url_abs":"https://arxiv.org/abs/1908.11618v2","url_pdf":"https://arxiv.org/pdf/1908.11618v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"lip-reading","task_name":"Lip Reading"},{"task_slug":"lipreading","task_name":"Lipreading"}],"methods":[{"method_slug":"convlstm","method_name":"ConvLSTM"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/lipreading-on-lip-reading-in-the-wild","task":"Lipreading","dataset":"Lip Reading in the Wild","model":"Multi-grained + Bi-ConvLSTM","rank_in_archive_order":21,"of":22,"metrics":{"Top-1 Accuracy":"83.34"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1908.11618","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}