Research map / Architectures and efficiency / RNNs and normalization
Understanding Pictograph with Facial Features: End-to-End Sentence-Level Lip Reading of Chinese
Xiaobing Zhang, Haigang Gong, Xili Dai, Fan Yang, Nianbo Liu, Ming Liu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| replace WLAS with LipCH-Net | lip reading · CCTV | sentence-level accuracy: 36.7% -> 50.2% | Improved |
| end-to-end training of Picture-to-Pinyin (ablation) | VGG-M+ResNet+2-LSTM+CTC · CCTV | PAR: 44.2% -> 46.3% | Improved |
| use CTC instead of softmax loss (ablation) | Picture-to-Pinyin · CCTV | PAR: 29.7% -> 44.2% | Improved |
| use ResNet instead of 6-layer DNN (ablation) | Picture-to-Pinyin · CCTV | PAR: 36.7% -> 41.2% | Improved |
| use 3D conv instead of 2D (VGG-M) (ablation) | Picture-to-Pinyin · CCTV | PAR: 41.2% -> 35.1% | Hurt |
| use bidirectional LSTM instead of unidirectional (ablation) | Picture-to-Pinyin · CCTV | PAR: 44.2% -> 41.4% | Hurt |
| use GRU instead of LSTM in Picture-to-Pinyin (ablation) | Picture-to-Pinyin · CCTV | PAR: 44.2% -> 34.8% | Hurt |
| add auxiliary data pretraining (ablation) | Pinyin-to-Hanzi · CCTV | HAR: 35.4% -> 39.8% | Improved |
| add scheduled sampling (ablation) | Pinyin-to-Hanzi · CCTV | HAR: 39.8% -> 40.2% | Improved |
| add decoder attention (ablation) | Pinyin-to-Hanzi · CCTV | HAR: 40.2% -> 45.7% | Improved |
| add curriculum learning (ablation) | LipCH-Net · CCTV | HAR: 42.7% -> 43.1% | Improved |
| add encoder attention for joint training (ablation) | LipCH-Net · CCTV | HAR: 43.1% -> 50.2% | Improved |
Closest papers by meaning
- Language Without Borders: A Dataset and Benchmark for Code-Switching Lip Reading (NeurIPS 2024 · similarity 0.89)
- Sub-Word Level Lip Reading With Visual Attention (CVPR 2022 · similarity 0.87)
- Deep Audio-Visual Speech Recognition (TPAMI 2018 · similarity 0.87)
- Personalized Lip Reading: Adapting to Your Unique Lip Movements with Vision and Language (AAAI 2025 · similarity 0.84)
- CVLUE: A New Benchmark Dataset for Chinese Vision-Language Understanding Evaluation (AAAI 2025 · similarity 0.84)
- LipVoicer: Generating Speech from Silent Videos Guided by Lip Reading (ICLR 2024 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
