Question about comparison between Cycle-CenterNet and LORE on WTW dataset

[Xelawk]

I've read both Cycle-CenterNet and LORE papers and noticed that LORE uses WTW dataset for training. However, in the experimental results section, why isn't there a direct comparison with Cycle-CenterNet's performance?

Is this because:

The results were not competitive enough to include?
There were different evaluation protocols?
Or other technical considerations?
It would be helpful to understand the rationale behind this omission, as a direct comparison could better demonstrate the relative strengths of these approaches. Any clarification would be appreciated!