论文笔记-Clip!!!

paper list:

  • CLIP: Learning Transferable Visual Models From Natural Language Supervision
  • ActionCLIP: A New Paradigm for Video Action Recognition

CLIP

Learning Transferable Visual Models From Natural Language Supervision

思路很简单,就是image和text做对比学习,zero shot能力强大。

ActionCLIP

作者

Xie Pan

发布于

2021-07-23

更新于

2021-09-24

许可协议

评论