New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[R(2+1)D] A Closer Look at Spatiotemporal Convolutions for Action Recognition #3

Closed

jinsoo9595 opened this issue Jul 28, 2022 · 0 comments

Assignees

Owner

jinsoo9595 commented Jul 28, 2022

3D CNN의 computation을 줄이기 위한 방법론 → (2+1)D CNN
- → 하지만 long-term 영상의 경우 멀리 떨어진 feature간 연관성이 떨어짐
- (2+1)D CNN = 2D CNN은 spatial conv + 1D CNN temporal conv

jinsoo9595 self-assigned this

jinsoo9595 closed this as completed

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment