no code implementations • 2 Jun 2023 • Qiangchang Wang, Yilong Yin
We hope that this survey can shed light on future research in the computer vision field.
1 code implementation • 11 Dec 2022 • Fanglei Xue, Qiangchang Wang, Zichang Tan, Zhongsong Ma, Guodong Guo
The proposed APP is employed to select the most informative patches on CNN features, and ATP discards unimportant tokens in ViT.
Ranked #4 on Facial Expression Recognition (FER) on RAF-DB
Facial Expression Recognition Facial Expression Recognition (FER) +1
no code implementations • ICCV 2021 • Fanglei Xue, Qiangchang Wang, Guodong Guo
Second, to build rich relations between different local patches, the Vision Transformers (ViT) are used in FER, called ViT-FER.
Facial Expression Recognition Facial Expression Recognition (FER) +2
no code implementations • CVPR 2020 • Qiangchang Wang, Tianyi Wu, He Zheng, Guodong Guo
Meanwhile, a diverse learning is developed to encourage models to focus on different local patches and generate diverse local features.
no code implementations • 28 Nov 2017 • Qiangchang Wang, Guodong Guo, Mohammad Iqbal Nouyed
We propose a new deep network structure for unconstrained face recognition.