AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

Deep Learning for Visual Speech Analysis: A Survey

Changchong Sheng, Gangyao Kuang, Liang Bai, Chenping Hou, Yulan Guo, Xin Xu, Matti Pietikäinen, Li Liu

TPAMI 2024 · Vision-language and multimodal › Cross-modal learning · approach: Audio-visual speech separation · 88 citations (OpenAlex)

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 changedWhereMeasuredEffect
use multi-stage knowledge distillationC3D-ResNet18 + MS-TCN · LRWaccuracy: 85.3 -> 87.7Improved
add cross-modal mutual learning with audio in trainingC3D-ResNet18 · LRWaccuracy: 87.7 -> 88.5Improved
add cross-modal mutual learning with audio in trainingC3D-ResNet18 · LRW-1000accuracy: 48.0 -> 50.5Improved
use seq2seq loss instead of CTC lossAfouras et al. Transformer · LRS2CER: 54.7 -> 48.3Improved
use seq2seq loss instead of CTC lossAfouras et al. Transformer · LRS3WER: 66.3 -> 58.9Improved
replace 2D CNN with visual transformer and sub-word outputPrajwal et al. · LRS3WER: 43.3 -> 30.7Improved
replace 2D CNN with visual transformer and sub-word outputPrajwal et al. · LRS2WER: 37.9 -> 22.6Improved
use BiGRU backend with C3D front end instead of ST-CNN CTCXu et al. · GRIDWER: 4.8 -> 2.9Improved
use MS-TCN backend instead of BiLSTMMartinez et al. · LRWaccuracy: 83.5 -> 85.3Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy