Papers with Code · CC BY-SA 4.0

Lip Reading in the Wild

아카이브 평가 22건 · 마지막 적재/변경 2026-10-30

평가 기록

과거 수집 기록이며 최신 순위가 아닙니다. 데이터셋 버전·split·실험 조건과 지표 방향이 검증되지 않은 결과는 직접 비교할 수 없습니다. 날짜는 논문 날짜이며 최신 평가일을 뜻하지 않습니다.

표가 화면보다 넓으면 좌우로 스크롤하여 논문과 구현 링크를 확인하세요.

원본 기록 순서 · 순위 미부여
모델	원본 지표·값	논문	구현
SyncVSR (Word Boundary)	Top-1 Accuracy 95.0	SyncVSR: Data-Efficient Visual Speech Recognition with End-to-End Crossmodal Audio Token Synchronization 2024-06-18	코드 1
3D Conv + ResNet-18 + DC-TCN + KD (Ensemble & Word Boundary)	Top-1 Accuracy 94.1	Training Strategies for Improved Lip-reading 2022-09-03	코드 1
SyncVSR	Top-1 Accuracy 93.2	SyncVSR: Data-Efficient Visual Speech Recognition with End-to-End Crossmodal Audio Token Synchronization 2024-06-18	코드 1
AVCRFormer	Top-1 Accuracy 89.57	Audio-Visual Speech Recognition based on Regulated Transformer and Spatio-Temporal Fusion Strategy for Driver Assistive Systems 2024-05-09	코드 1
3D Conv + EfficientNetV2 + Transformer + TCN	Top-1 Accuracy 89.52	Accurate and Resource-Efficient Lipreading with Efficientnetv2 and Transformers 2022-05-23	연결 없음
Vosk + MediaPipe + LS + MixUp + SA + 3DResNet-18 + BiLSTM + Cosine WR	Top-1 Accuracy 88.7	Visual Speech Recognition in a Driver Assistance System 2022-08-29	연결 없음
3D Conv + ResNet-18 + MS-TCN + Multi-Head Visual-Audio Memory	Top-1 Accuracy 88.5	Distinguishing Homophenes Using Multi-Head Visual-Audio Memory for Lip Reading 2022-04-04	코드 1
3D Conv + ResNet-18 + MS-TCN + KD (Ensemble)	Top-1 Accuracy 88.5	Towards Practical Lipreading with Distilled and Efficient Models 2020-07-13	코드 1
3D-ResNet + Bi-GRU + MixUp + Label Smoothing + Cosine LR (Word Boundary)	Top-1 Accuracy 88.4	Learn an Effective Lip Reading Model without Pains 2020-11-15	코드 1
3D-ResNet + Bi-GRU + MixUp + Label Smoothing + Cosine LR	Top-1 Accuracy 85.5	Learn an Effective Lip Reading Model without Pains 2020-11-15	코드 1
3D Conv + ResNet-18 + Bi-GRU + Visual-Audio Memory	Top-1 Accuracy 85.4	Multi-modality Associative Bridging through Memory: Speech Sound Recollected from Face Video 2022-04-04	코드 1
3D Conv + ResNet-18 + MS-TCN	Top-1 Accuracy 85.30	Lipreading using Temporal Convolutional Networks 2020-01-23	코드 1 · 코드 2
3D Conv + ResNet-18 + Bi-GRU(Face Cutout)	Top-1 Accuracy 85.02	Can We Read Speech Beyond the Lips? Rethinking RoI Selection for Deep Visual Speech Recognition 2020-03-06	코드 1
MoCo + Wav2Vec by SJTU LUMIA	Top-1 Accuracy 85.0	Leveraging Unimodal Self-Supervised Learning for Multimodal Audio-Visual Speech Recognition 2022-02-24	코드 1
3D Conv + P3D-ResNet50 + TCN	Top-1 Accuracy 84.80	Discriminative Multi-modality Speech Recognition 2020-05-12	코드 1 · 코드 2
3D Conv + ResNet-18 + Bi-GRU	Top-1 Accuracy 84.41	Mutual Information Maximization for Effective Lip Reading 2020-03-13	코드 1
SpotFast + Transformer + Product-Key memory	Top-1 Accuracy 84.4	SpotFast Networks with Memory Augmented Lateral Transformers for Lipreading 2020-05-21	코드 1
DFTN	Top-1 Accuracy 84.13	Deformation Flow Based Two-Stream Network for Lip Reading 2020-03-12	코드 1
PCPG	Top-1 Accuracy 83.5	Pseudo-Convolutional Policy Gradient for Sequence-to-Sequence Lip-Reading 2020-03-09	연결 없음
3D Conv + ResNet-34 + Bi-GRU	Top-1 Accuracy 83.39	End-to-end Audiovisual Speech Recognition 2018-02-18	코드 1 · 코드 2
Multi-grained + Bi-ConvLSTM	Top-1 Accuracy 83.34	Multi-Grained Spatio-temporal Modeling for Lip-reading 2019-08-30	연결 없음
3D Conv + ResNet-34 + Bi-LSTM	Top-1 Accuracy 83.00	Combining Residual Networks with LSTMs for Lipreading 2017-03-12	코드 1 · 코드 2 · 코드 3 · 코드 4