Awesome Dynamic Facial Expression Recognition

Benchmarks

• DFEW [ACM MM 2020]
• FERV39k [CVPR 2022]
• MAFW [ACM MM 2022]
• CAER [ICCV 2021]
• AFEW [IEEE Multimedia 2012]

Comparison of State-of-the-Art

Methods	Venues	Years	DFEW		FERV39k		MAFW
			UAR	WAR	UAR	WAR	UAR	WAR
C3D	-	-	42.74	53.54	22.68	31.69	31.17	42.25
P3D	-	-	43.97	54.47	23.20	33.39	-	-
I3D-RGB	-	-	43.40	54.27	30.17	38.78	-	-
3D-ResNet18	-	-	46.52	58.27	26.67	37.57	-	-
R(2+1)D	-	-	42.79	53.22	31.55	41.28	-	-
ResNet18-LSTM	-	-	51.32	63.85	30.92	42.95	28.08	39.38
R18-ViT (w/ pre-train)	-	-	55.76	67.56	38.35	48.43	35.80	47.72
EC-STFL[1]	ACM MM	2020	45.35	56.51	-	-	-	-
Former-DFER[2]	ACM MM	2021	53.69	65.70	37.20	46.85	31.16	43.27
NR-DFERNet[3]	arXiv	2022	54.21	68.19	33.99	45.97	-	-
DPCNet[4]	ACM MM	2022	57.11	66.32	-	-	-	-
T-ESFL[5]	ACM MM	2022	-	-	-	-	33.28	48.18
EST[6]	PR	2023	53.94	65.85	-	-	-	-
Logo-Form[7]	ICASSP	2023	54.21	66.98	38.22	48.13	-	-
GCA+IAL[8]	AAAI	2023	55.71	69.24	35.82	48.54	-	-
CLIPER[9]	arXiv	2023	57.56	70.84	41.23	51.34	-	-
MSCM[10]	PR	2023	58.49	70.16	-	-	-	-
AEN[11]	CVPRW	2023	56.66	69.37	38.18	47.88	-	-
M3DFEL[12]	CVPR	2023	56.10	69.25	35.94	47.67	-	-
MAE-DFER[13]	ACM MM	2023	63.41	74.43	43.12	52.07	41.62	54.31
DFER-CLIP[14]	BMVC	2023	59.61	71.25	41.27	51.65	39.89	52.55
S2D[15]	Arxiv	2023	61.82	76.03	41.28	52.56	41.86	57.37
A$^3$lign-DFER[16]	arXiv	2024	64.09	74.02	41.87	51.79	42.07	53.24
S4D	arXiv	2024	66.80	76.68	43.41	53.65	43.72	58.44

References

2020

1. Jiang X, Zong Y, Zheng W, Tang C, Xia W, Lu C, Liu J. DFEW: A Large-scale Database for Recognizing Dynamic Facial Expressions in the Wild. ACM MM, 2020. [Paper]

2021

2. Zhao Z, Liu Q. Former-DFER: Dynamic Facial Expression Recognition Transformer. ACM MM, 2021. [Paper] [Code]

2022

3. Li H, Sui M, Zhu Z. NR-DFERNet: Noise-Robust Network for Dynamic Facial Expression Recognition. arXiv, 2022.[Paper]
4. Wang Y, Sun Y, Song W, Gao S, Huang Y, Chen Z, Ge W, Zhang W. DPCNet: Dual Path Multi-Excitation Collaborative Network for Facial Expression Representation Learning in Videos. ACM MM, 2022. [Paper]
5. Liu Y, Dai W, Feng C, Wang W, Yin G, Zeng J, Shan S. MAFW: A Large-scale, Multi-modal, Compound Affective Database for Dynamic Facial Expression Recognition in the Wild. ACM MM, 2022. [Paper]

2023

6. Liu Y, Wang W, Feng C, Zhang H, Chen Z, Zhan Y. Expression snippet transformer for robust video-based facial expression recognition. Pattern Recognition. Pattern Recognition, 2023. [Paper]
7. Ma F, Sun B, Li S. Logo-Former: Local-Global Spatio-Temporal Transformer for Dynamic Facial Expression Recognition. ICASSP, 2023. [Paper]
8. Li H, Niu H, Zhu Z, Zhao F. Intensity-Aware Loss for Dynamic Facial Expression Recognition in the Wild. AAAI, 2023. [Paper] [Code]
9. Li H, Niu H, Zhu Z, Zhao F. CLIPER: A Unified Vision-Language Framework for In-the-Wild Facial Expression Recognition. arXiv, 2023. [Paper]
10. Li T, Chan KL, Tjahjadi T. Multi-Scale Correlation Module for Video-based Facial Expression Recognition in the Wild. Pattern Recognition, 2023. [Paper]
11. Lee B, Shin H, Ku B, Ko H. Frame Level Emotion Guided Dynamic Facial Expression Recognition With Emotion Grouping. CVPRW, 2023. [Paper]
12. Wang H, Li B, Wu S, Shen S, Liu F, Ding S, Zhou A. Rethinking the Learning Paradigm for Dynamic Facial Expression Recognition. CVPR, 2023. [Paper] [Code]
13. Sun L, Lian Z, Liu B, Tao J. MAE-DFER: Efficient Masked Autoencoder for Self-supervised Dynamic Facial Expression Recognition. ACM MM, 2023. [Paper] [Code]
14. Zhao Z, Patras I. Prompting Visual-Language Models for Dynamic Facial Expression Recognition. BMVC, 2023. [Paper] [Code]
15. Chen, Yin, et al. "From Static to Dynamic: Adapting Landmark-Aware Image Models for Facial Expression Recognition in Videos." arXiv preprint arXiv:2312.05447 (2023). [Paper] [Code]
16. Tao, Zeng, et al. "A $^{3} $ lign-DFER: Pioneering Comprehensive Dynamic Affective Alignment for Dynamic Facial Expression Recognition with CLIP." arXiv preprint arXiv:2403.04294 (2024) [Paper]