sukjunhwang / VITA

VITA: Video Instance Segmentation via Object Token Association (NeurIPS 2022)

sukjunhwang/VITA Issues

About "Maximum number of frames" in Table 4.
Closed 4 months ago
OVIS Dataset Error
Updated 8 months ago6
How to get the train.json, val.json of ytvis_2021?
Closed 2 years ago8
self.training when calling swin attention in object encoder
Closed a year ago4
about data preparation
Closed a year ago2
Demo
Updated 2 years ago2
Dear author, I did not find the fps data of VITA in your paper. Can you tell us the fps in different sizes?
Updated 2 years ago2
Error in detectron2
Closed 2 years ago4
Dateset prepare
Updated 2 years ago1
ytvis_2019 submit error
Closed 2 years ago2
COCO pretrained weight
Closed 2 years ago4
Some training details.
Closed 2 years ago9
How to use multiple GPUs for inference?
Closed 2 years ago6
How to get the AP for youtube_vis?
Closed 2 years ago2
how to visualize the segmentation result and generate the bitmask png for trained model?
Closed 2 years ago2
Looking forward to your excellent work open source.
Closed 2 years ago4