Papers with Code · CC BY-SA 4.0

CAS-VSR-W1k (LRW-1000)

아카이브 평가 9건 · 마지막 적재/변경 2026-10-30

원본 데이터셋 링크 1

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 58.2	SyncVSR: Data-Efficient Visual Speech Recognition with End-to-End Crossmodal Audio Token Synchronization 2024-06-18	코드 1
3D-ResNet + Bi-GRU + MixUp + Label Smooth + Cosine LR (Word Boundary)	Top-1 Accuracy 55.7%	Learn an Effective Lip Reading Model without Pains 2020-11-15	코드 1
3D Conv + ResNet-18 + MS-TCN + Multi-Head Visual-Audio Memory	Top-1 Accuracy 53.8	Distinguishing Homophenes Using Multi-Head Visual-Audio Memory for Lip Reading 2022-04-04	코드 1
3D Conv + ResNet-18 + Bi-GRU + Visual-Audio Memory	Top-1 Accuracy 50.82%	Multi-modality Associative Bridging through Memory: Speech Sound Recollected from Face Video 2022-04-04	코드 1
3D-ResNet + Bi-GRU + MixUp + Label Smooth + Cosine LR	Top-1 Accuracy 48.3%	Learn an Effective Lip Reading Model without Pains 2020-11-15	코드 1
3D Conv + ResNet-18 + Bi-GRU (Face Cutout)	Top-1 Accuracy 45.24%	Can We Read Speech Beyond the Lips? Rethinking RoI Selection for Deep Visual Speech Recognition 2020-03-06	코드 1
DFTN	Top-1 Accuracy 41.93%	Deformation Flow Based Two-Stream Network for Lip Reading 2020-03-12	코드 1
GLMIM	Top-1 Accuracy 38.79%	Mutual Information Maximization for Effective Lip Reading 2020-03-13	코드 1
PCPG	Top-1 Accuracy 38.7%	Pseudo-Convolutional Policy Gradient for Sequence-to-Sequence Lip-Reading 2020-03-09	연결 없음