sukjunhwang/VITA
VITA: Video Instance Segmentation via Object Token Association (NeurIPS 2022)
PythonApache-2.0
Issues
- 0
About "Maximum number of frames" in Table 4.
#16 opened by ruohaoguo - 6
OVIS Dataset Error
#11 opened by 1787594808 - 8
- 4
- 2
about data preparation
#14 opened by chen742 - 2
- 2
Dear author, I did not find the fps data of VITA in your paper. Can you tell us the fps in different sizes?
#8 opened by hekaijie123 - 4
Error in detectron2
#7 opened by fanghaook - 1
Dateset prepare
#13 opened by ChinChyi - 2
ytvis_2019 submit error
#12 opened by nanle771 - 4
COCO pretrained weight
#10 opened by fanghaook - 9
Some training details.
#6 opened by KainingYing - 6
How to use multiple GPUs for inference?
#5 opened by xjtuwh - 2
How to get the AP for youtube_vis?
#3 opened by xjtuwh - 2
how to visualize the segmentation result and generate the bitmask png for trained model?
#2 opened by f414158949 - 4