Skip to content
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.

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

Skip-Convolution Processing #836

Closed
HoBeom opened this issue Aug 6, 2021 · 0 comments
Closed

Skip-Convolution Processing #836

HoBeom opened this issue Aug 6, 2021 · 0 comments
Labels
enhancement New feature or request

Comments

@HoBeom
Copy link
Contributor

HoBeom commented Aug 6, 2021

Describe the feature
Skip Convolution and Dynamic Kernel Distillation for video base estimation
Video id mapping is required for video base estimation, such as posetrack17,18 in xtcocotools

Motivation
Skip-Convolutions for Efficient Video Processing CVPR2021 show that video computation can be effectively possible by introducing skip convolution.
A similar study was introduced in Dynamic Kernel Distillation for Efficient Pose Estimation in Videos ICCV2019

Additional context
https://github.com/Qualcomm-AI-research/Skip-Conv

Do I have to request it to mmcv?

@jin-s13 jin-s13 added the enhancement New feature or request label Aug 6, 2021
@jin-s13 jin-s13 closed this as completed Dec 7, 2021
HAOCHENYE pushed a commit to HAOCHENYE/mmpose that referenced this issue Jun 27, 2023
* update doc

* update doc

* Update mmengine/structures/base_data_element.py

* Update mmengine/structures/base_data_element.py

* Apply suggestions from code review

Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request
Projects
None yet
Development

No branches or pull requests

2 participants