[FIX] Support empty tensor for selsa_aggregator

[Chop1]

see #370
see #375

(sorry for the double pr)

[GT9505]

Hi @Chop1, thanks for your contribution :)
Could you please update the PR based on the comments?
Then, We can merge this PR.

[GT9505]

All num_C_per_attention_block should be renamed to num_c_per_att_block
By the way, it is better to git commit in your local machine firstly. Then push it to the PR. The reason is that using commit suggestion may cause lint error.

[Chop1]

Thanks for the dedication and explanation.

[codecov]

Codecov Report

Merging #463 (759d9cf) into master (a14fcb3) will increase coverage by 0.33%.
The diff coverage is 100.00%.

@@            Coverage Diff             @@
##           master     #463      +/-   ##
==========================================
+ Coverage   73.04%   73.38%   +0.33%     
==========================================
  Files         126      126              
  Lines        7338     7378      +40     
  Branches     1390     1390              
==========================================
+ Hits         5360     5414      +54     
+ Misses       1550     1540      -10     
+ Partials      428      424       -4     

Flag	Coverage Δ
unittests	73.31% <100.00%> (+0.30%)	⬆️

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

Impacted Files	Coverage Δ
mmtrack/models/aggregators/selsa_aggregator.py	100.00% <100.00%> (ø)
mmtrack/models/reid/base_reid.py	78.26% <0.00%> (-8.11%)	⬇️
mmtrack/datasets/pipelines/processing.py	75.86% <0.00%> (-4.32%)	⬇️
mmtrack/models/trackers/base_tracker.py	84.73% <0.00%> (-0.99%)	⬇️
mmtrack/models/track_heads/siamese_rpn_head.py	93.15% <0.00%> (+0.10%)	⬆️
mmtrack/models/reid/linear_reid_head.py	89.85% <0.00%> (+0.14%)	⬆️
mmtrack/models/trackers/byte_tracker.py	89.68% <0.00%> (+0.16%)	⬆️
...track/models/trackers/quasi_dense_embed_tracker.py	75.88% <0.00%> (+0.17%)	⬆️
mmtrack/models/track_heads/roi_track_head.py	87.93% <0.00%> (+0.21%)	⬆️
mmtrack/models/track_heads/roi_embed_head.py	85.34% <0.00%> (+0.25%)	⬆️
... and 11 more

---

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update a14fcb3...759d9cf. Read the comment docs.

[OpenMMLab-Assistant003]

Hi @Chop1！First of all, we want to express our gratitude for your significant PR in the MMTracking project. Your contribution is highly appreciated, and we are grateful for your efforts in helping improve this open-source project during your personal time. We believe that many developers will benefit from your PR.

We would also like to invite you to join our Special Interest Group (SIG) private channel on Discord, where you can share your experiences, ideas, and build connections with like-minded peers. To join the SIG channel, simply message moderator— OpenMMLab on Discord or briefly share your open-source contributions in the #introductions channel and we will assist you. Look forward to seeing you there! Join us ：https://discord.gg/raweFPmdzG

If you are Chinese or have WeChat，welcome to join our community on WeChat. You can add our assistant ：openmmlabwx. Please add "mmsig + Github ID" as a remark when adding friends：）
Thank you again for your contribution❤ @Chop1