Next-generation Video instance recognition framework on top of Detectron2 which supports InstMove (CVPR 2023), SeqFormer(ECCV Oral), and IDOL(ECCV Oral))
I’m confused about how the threshold can be 0.5 for all situations, no matter what M and N is ? if M and N are big enough, f(i, ˆj) can easily be small than 0.5.
I’m confused about how the threshold can be 0.5 for all situations, no matter what M and N is ? if M and N are big enough, f(i, ˆj) can easily be small than 0.5.