Inference on YouTube-VOS dataset

zlai0 / MAST

MAST: A Memory-Augmented Self-supervised Tracker (CVPR 2020)

https://zlai0.github.io/MAST/

273 stars 32 forks source link

Inference on YouTube-VOS dataset #21

Open bo-miao opened 3 years ago

bo-miao commented 3 years ago

Hi,

May I know how you test on YouTube-VOS since some new objects are added in middle frames in that dataset? In that case, I am confused about how to handle objects that added in middle frames, such as how to decide memory usage, how to merge segmentation results, e.t.c.

Thanks.

houhouhouhou11 commented 3 years ago

@bo-miao ,hello,I have the same problem. Have you solved it? thank you

ruoqi77 commented 3 years ago

@zlai0 Same question, too. Do you mind releasing the test code on Youtube-VOS ? If it's not convenient, then I'm so sorry to ask. Thank you very much!

houhouhouhou11 commented 3 years ago

@ruoqi77 can you run the train code with long memory successfully? thank you!