Closed knowlessthanenough closed 9 months ago
Hi, what detector and appearance feature extractor do you apply? And, could you please provide your experiment results (MOTA / IDF1 / HOTA / ... )?
i am using yolov7-tiny and osnet as feature extractor, here is the link to the output video.https://hkuhk-my.sharepoint.com/:f:/g/personal/tsunchak_hku_hk/En_gtsKn-pFNgGi3rtoJ2p4BcPrdqor8ffszWqGm2gbQhg?e=bwCPaC
It is common that some tricks lose efficacy in specific settings and cases. If you want to figure out the reason why "woC" doesn't work, you should compare the two visualization results carefully. Best wishes.
Thank you very much for respond .May I ask if I modify the correct part ? is this the only part that I have to modify?
I think you're right.
i base on deepSORT and add each of the changes, first NSA then EMA, MC, finally woC. before woC everything seem very well the performence increase. however when i add woC the profomence decrease a all, i can see the id switch even nothing block the object. i want to know if i make anything wrong ?
Here is the part of code i change for adding woC:
i copy the woC part of code and replace the orginal one, i run on https://motchallenge.net/vis/MOT17-08-SDP video.