[#Video ReID] Why image-based training beats video-based training(avg pooling) ?

[cwpeng-cn]

I noticed that many papers mentioned that the accuracy of image-based training is lower than that based on time series average pooling.

But I found that in your project, the image-based method is much higher than the accuracy reported by other papers.

Then I changed the image-based training in your code to time-series average pooling, but the accuracy decreased.