Inconsistency between MOT challenge website and paper
Closed this issue · 1 comments
Hi, I am follow with interest your CroHD. It is very impressive. However, I have a question about the Table 4 in the paper "Tracking Pedestrian Heads in Dense Crowd". It shows the Headhunter--T method achieves a MOTA 63.6 and IDF1 57.1, while on MOT challenge https://motchallenge.net/results/Head_Tracking_21/ the Headhunter--T method only achieves a MOTA 57.8 and IDF1 53.9. Could you please tell me why there is an inconsistency between the two results and where is the gap. Thank you!
Refer to this note : https://github.com/Sentient07/HeadHunter--T#note-
This is due to using different packages for evaluation. At the time of this paper submission, PyMotMetric was the library used for evaluation. Then, they migrated to a TrackEval packages. If you want to use the same evaluation scheme as performed in the paper, use PyMotMetric package referred to in the note