Papers with Code · CC BY-SA 4.0

RAF-DB

아카이브 평가 35건 · 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
ResEmoteNet	Overall Accuracy 94.76	ResEmoteNet: Bridging Accuracy and Loss Reduction in Facial Emotion Recognition 2024-09-01	코드 1
FMAE	Overall Accuracy 93.45	Representation Learning and Identity Adversarial Training for Facial Behavior Understanding 2024-07-15	코드 1
QCS	Overall Accuracy 93.02	QCS: Feature Refining from Quadruplet Cross Similarity for Facial Expression Recognition 2024-11-04	코드 1
Norface	Overall Accuracy 92.97	Norface: Improving Facial Expression Analysis by Identity Normalization 2024-07-22	코드 1
S2D	Overall Accuracy 92.57	From Static to Dynamic: Adapting Landmark-Aware Image Models for Facial Expression Recognition in Videos 2023-12-09	코드 1 · 코드 2
BTN	Overall Accuracy 92.54 Avg. Accuracy 87.3	Batch Transformer: Look for Attention in Batch 2024-07-05	연결 없음
GReFEL	Overall Accuracy 92.47	GReFEL: Geometry-Aware Reliable Facial Expression Learning under Bias and Imbalanced Data Distribution 2024-10-21	연결 없음
DDAMFN++	Overall Accuracy 92.34	A Dual-Direction Attention Mixed Feature Network for Facial Expression Recognition 2023-08-25	코드 1
DCJT	Overall Accuracy 92.24	Joint Training on Multiple Datasets With Inconsistent Labeling Criteria for Facial Expression Recognition 2024-04-02	코드 1
POSTER++	Overall Accuracy 92.21	POSTER++: A simpler and stronger facial expression recognition network 2023-01-28	코드 1
APViT	Overall Accuracy 91.98	Vision Transformer with Attentive Pooling for Robust Facial Expression Recognition 2022-12-11	코드 1
DDAMFN	Overall Accuracy 91.35	A Dual-Direction Attention Mixed Feature Network for Facial Expression Recognition 2023-08-25	코드 1
ViT-base + MAE	Overall Accuracy 91.07	Emotion Separation and Recognition from a Facial Expression by Generating the Poker Face with Vision Transformers 2022-07-22	연결 없음
LFNSB	Overall Accuracy 91.07	A Lightweight Model Enhancing Facial Expression Recognition with Spatial Bias and Cosine-Harmony Loss 2024-08-01	코드 1
ExpLLM	Overall Accuracy 91.03	ExpLLM: Towards Chain of Thought for Facial Expression Recognition 2024-09-04	코드 1
EAC(ResNet-50)	Overall Accuracy 90.35	Learn From All: Erasing Attention Consistency for Noisy Label Facial Expression Recognition 2022-07-21	코드 1
Ada-DF	Overall Accuracy 90.04	A Dual-Branch Adaptive Distribution Fusion Framework for Real-World Facial Expression Recognition 2023-05-05	코드 1
DAN	Overall Accuracy 89.70	Distract Your Attention: Multi-head Cross Attention Network for Facial Expression Recognition 2021-09-15	코드 1 · 코드 2
RUL (ResNet-18)	Overall Accuracy 88.98	Relative Uncertainty Learning for Facial Expression Recognition 2021-12-01	코드 1
PSR	Overall Accuracy 88.98	Pyramid With Super Resolution for In-the-Wild Facial Expression Recognition 2020-07-17	코드 1
FerNeXt	Overall Accuracy 88.56	FerNeXt: Facial Expression Recognition Using ConvNeXt with Channel Attention 2023-10-20	코드 1
EfficientFace	Overall Accuracy 88.36	Robust Lightweight Facial Expression Recognition Network with Label Distribution Training 2021-05-18	코드 1
MA-Net	Overall Accuracy 88.36	Learning Deep Global Multi-scale and Local Attention Features for Facial Expression Recognition in the Wild 2021-07-05	코드 1
DACL (ResNet-18)	Overall Accuracy 87.78 Avg. Accuracy 80.44	Facial Expression Recognition in the Wild via Deep Attentive Center Loss 2021-01-07	코드 1
MixAugment	Overall Accuracy 87.54 Avg. Accuracy 77.30	MixAugment & Mixup: Augmentation Methods for Facial Expression Recognition 2022-05-09	연결 없음
ViT-base	Overall Accuracy 87.22	Emotion Separation and Recognition from a Facial Expression by Generating the Poker Face with Vision Transformers 2022-07-22	연결 없음
ViT-tiny	Overall Accuracy 87.03	Emotion Separation and Recognition from a Facial Expression by Generating the Poker Face with Vision Transformers 2022-07-22	연결 없음
Ad-Corre	Overall Accuracy 86.96	Ad-Corre: Adaptive Correlation-Based Loss for Facial Expression Recognition in the Wild 2022-03-03	코드 1
RAN (ResNet-18)	Overall Accuracy 86.9	Region Attention Networks for Pose and Occlusion Robust Facial Expression Recognition 2019-05-10	코드 1
C-EXPR-NET	Avg. Accuracy 87.5	Multi-Label Compound Expression Recognition: C-EXPR Database & Network 2023-01-01	연결 없음