Is Space-Time Attention All You Need for Video Understanding?
- https://arxiv.org/pdf/2102.05095
- https://proceedings.mlr.press/v139/bertasius21a/bertasius21a-supp.pdf
ViViT: A Video Vision Transformer
- 2021: 2600회 인용
- https://openaccess.thecvf.com/content/ICCV2021/papers/Arnab_ViViT_A_Video_Vision_Transformer_ICCV_2021_paper.pdf
Multiscale Vision Transformers
- 2021: 1500 회 인용
- https://openaccess.thecvf.com/content/ICCV2021/papers/Fan_Multiscale_Vision_Transformers_ICCV_2021_paper.pdf
Video swin transformer
- 2022: 1900회 인용
- https://openaccess.thecvf.com/content/CVPR2022/papers/Liu_Video_Swin_Transformer_CVPR_2022_paper.pdf
모든 의사 결정 과정을 지나칠 정도로 모두 기록하고, 나중에 스스로 피드백 하는 것
0개의 댓글
