[Feature] add DeciWatch for 10x efficiency improvement

[ailingzengzzz]

trafficstars

Motivation

DeciWatch is a simple baseline framework for video-based 2D/3D human pose estimation that can achieve 10× efficiency improvement over existing works without any performance degradation. paper: https://arxiv.org/pdf/2203.08713.pdf website: https://ailingzeng.site/deciwatch

Modification

add a file: deciwatch.py in mmpose/core/post_processing/temporal_filters/

BC-breaking (Optional)

Use cases (Optional)

Checklist

Before PR:

• [ ] I have read and followed the workflow indicated in the CONTRIBUTING.md to create this PR.
• [ ] Pre-commit or linting tools indicated in CONTRIBUTING.md are used to fix the potential lint issues.
• [ ] Bug fixes are covered by unit tests, the case that causes the bug should be added in the unit tests.
• [ ] New functionalities are covered by complete unit tests. If not, please add more unit tests to ensure correctness.
• [ ] The documentation has been modified accordingly, including docstring or example tutorials.

After PR:

• [ ] CLA has been signed and all committers have signed the CLA in this PR.

[codecov[bot]]

Codecov Report

Attention: 247 lines in your changes are missing coverage. Please review.

Files	Coverage Δ
.../core/post_processing/temporal_filters/__init__.py	100.00% <100.00%> (ø)
...core/post_processing/temporal_filters/deciwatch.py	17.11% <17.11%> (ø)

:loudspeaker: Thoughts on this report? Let us know!

[jin-s13]

Thanks @ailingzengzzz , is this PR ready for review now?

[ailingzengzzz]

Hi @jin-s13 , Not ready. I will update the API to use the model soon.

[rlleshi]

Is this PR still planned?

@jin-s13 kind ping. @ailingzengzzz @ly015