1 code implementation • 25 Aug 2023 • Zengqun Zhao, Ioannis Patras
For the visual part, based on the CLIP image encoder, a temporal model consisting of several Transformer encoders is introduced for extracting temporal facial expression features, and the final feature embedding is obtained as a learnable "class" token.
Dynamic Facial Expression Recognition Facial Expression Recognition +1
1 code implementation • ACM International Conference on Multimedia 2021 • Zengqun Zhao, Qingshan Liu
Specifically, the proposed Former-DFER mainly consists of a convolutional spatial transformer (CS-Former) and a temporal transformer (T-Former).
Ranked #6 on Dynamic Facial Expression Recognition on FERV39k
1 code implementation • IEEE Transactions on Image Processing. 2021 • Zengqun Zhao, Qingshan Liu, Shanmin Wang
Specifically, the proposed network consists of three main components: a feature pre-extractor, a multi-scale module, and a local attention module.
Ranked #14 on Facial Expression Recognition (FER) on RAF-DB
Facial Expression Recognition Facial Expression Recognition (FER)
1 code implementation • AAAI Conference on Artificial Intelligence 2021 • Zengqun Zhao, Qingshan Liu, Feng Zhou
This paper presents an efficiently robust facial expression recognition (FER) network, named EfficientFace, which holds much fewer parameters but more robust to the FER in the wild.
Ranked #1 on Facial Expression Recognition (FER) on CAER