[Enhance] support spatial-temporal detection demo

[hukkai]

Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily got feedback.
If you do not understand some items, don't worry, just make the pull request and seek help from maintainers.

Motivation

Please describe the motivation of this PR and the goal you want to achieve through this PR.

Modification

Please briefly describe what modification is made in this PR.

BC-breaking (Optional)

Does the modification introduces changes that break the back-compatibility of this repo?
If so, please describe how it breaks the compatibility and how users should modify their codes to keep compatibility with this PR.

Use cases (Optional)

If this PR introduces a new feature, it is better to list some use cases here, and update the documentation.

Checklist

1. Pre-commit or other linting tools should be used to fix the potential lint issues.
2. The modification should be covered by complete unit tests. If not, please add more unit tests to ensure the correctness.
3. If the modification has potential influence on downstream projects, this PR should be tested with downstream projects, like MMDet or MMCls.
4. The documentation should be modified accordingly, like docstring or example tutorials.

[hukkai]

mmdet still not support FastRCNN.

[codecov]

Codecov Report

Base: 75.75% // Head: 76.65% // Increases project coverage by +0.89% 🎉

Coverage data is based on head (1b47adb) compared to base (9c23a07).
Patch coverage: 0.00% of modified lines in pull request are covered.

❗ Current head 1b47adb differs from pull request most recent head 8c762ca. Consider uploading reports for the commit 8c762ca to get more accurate results

Additional details and impacted files

@@             Coverage Diff             @@
##           dev-1.x    #2019      +/-   ##
===========================================
+ Coverage    75.75%   76.65%   +0.89%     
===========================================
  Files          135      139       +4     
  Lines         9764     9964     +200     
  Branches      1604     1631      +27     
===========================================
+ Hits          7397     7638     +241     
+ Misses        2020     1972      -48     
- Partials       347      354       +7     

Flag	Coverage Δ
unittests	76.65% <0.00%> (+0.89%)	⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

Impacted Files	Coverage Δ
mmaction/apis/inference.py	43.75% <0.00%> (ø)
mmaction/models/backbones/stgcn.py	90.36% <0.00%> (-0.75%)	⬇️
mmaction/models/utils/graph.py	88.49% <0.00%> (-0.68%)	⬇️
mmaction/models/backbones/swin.py	93.06% <0.00%> (-0.22%)	⬇️
mmaction/models/necks/tpn.py	87.86% <0.00%> (-0.07%)	⬇️
mmaction/utils/collect_env.py	40.00% <0.00%> (ø)
mmaction/models/losses/base.py	93.75% <0.00%> (ø)
mmaction/models/backbones/x3d.py	89.79% <0.00%> (ø)
mmaction/models/backbones/tanet.py	96.42% <0.00%> (ø)
mmaction/models/backbones/resnet.py	93.33% <0.00%> (ø)
... and 30 more

Help us with your feedback. Take ten seconds to tell us how you rate us. Have a feature suggestion? Share it here.

☔ View full report at Codecov.
📢 Do you have feedback about the report comment? Let us know in this issue.

[Dai-Wenxun]

Add docstrings and type hints for the demo, please.

[Dai-Wenxun]

Add the output video.