Spatiotemporal Contrastive Learning of Facial Expressions in Videos
원문 초록
We propose a self-supervised contrastive learning approach for facial expression recognition (FER) in videos. We propose a novel temporal sampling-based augmentation scheme to be utilized in addition to standard spatial augmentations used for contrastive learning. Our proposed temporal augmentation scheme randomly picks from one of three temporal sampling techniques: (1) pure random sampling, (2) uniform sampling, and (3) sequential sampling. This is followed by a combination of up to three standard spatial augmentations. We then use a deep R(2+1)D network for FER, which we train in a self-supervised fashion based on the augmentations and subsequently fine-tune. Experiments are performed on the Oulu-CASIA dataset and the performance is compared to other works in FER. The results indicate that our method achieves an accuracy of 89.4%, setting a new state-of-the-art by outperforming other works. Additional experiments and analysis confirm the considerable contribution of the proposed temporal augmentation versus the existing spatial ones.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Multimodal Prompt Alignment for Facial Expression Recognition
EfficientFER: EfficientNetv2 Based Deep Learning Approach for Facial Expression Recognition
TKFNet: Learning Texture Key Factor Driven Feature for Facial Expression Recognition
Unsupervised Multiview Contrastive Language-Image Joint Learning with Pseudo-Labeled Prompts Via Vision-Language Model for 3D/4D Facial Expression Recognition
Achieving 3D Attention via Triplet Squeeze and Excitation Block
SDAFE: A Dual-filter Stable Diffusion Data Augmentation Method for Facial Expression Recognition
토론
이 논문과 연결된 포럼 글이 아직 없습니다.