WMZAlive
Results
2
comments of
WMZAlive
The high performance on MOT17 training set may be attributed to overfitting, as MOT17 is a small dataset with only 5k frames. Therefore, many works use additional data such as...
> what a good job ! thanks for releasing the codes of CQL ! BUT multiple experiments were mentioned in the paper such as CQL+QPIC CQL+SCG CQL+GEN , but only...