Landmark Guided Visual Feature Extractor for Visual Speech Recognition with Limited Resource
Open Access
- 26 October 2025
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 40-48
Abstract
No abstract availableFunding Information
- National Natural Science Foundation of China (62271307)
- the robotic AI-Scientist platform of Chinese Academy of Sciences ()
This publication has 13 references indexed in Scilit:
- Lip Feature Disentanglement for Visual Speaker Authentication in Natural ScenesIEEE Transactions on Circuits and Systems for Video Technology, 2024
- Fine-Grained Lip Image Segmentation Using Fuzzy Logic and Graph ReasoningIEEE Transactions on Fuzzy Systems, 2023
- Auto-AVSR: Audio-Visual Speech Recognition with Automatic Labels2023
- Visual speech recognition for multiple languages in the wildNature Machine Intelligence, 2022
- Can We Read Speech Beyond the Lips? Rethinking RoI Selection for Deep Visual Speech Recognition2020
- Lipreading Using Temporal Convolutional Networks2020
- How Far are We from Solving the 2D & 3D Face Alignment Problem? (and a Dataset of 230,000 3D Facial Landmarks)2017
- Lip Reading Sentences in the Wild2017
- End-to-end visual speech recognition with LSTMS2017
- WIDER FACE: A Face Detection Benchmark2016