haochenheheda / LVVIS

Large-Vocabulary Video Instance Segmentation dataset

haochenheheda/LVVIS Issues

OV2Seg+ Code
Updated 2 months ago
Open-vocabulary segmentation Demo
Updated 4 months ago
Burst pre-computed classifiers
Updated 4 months ago
Duplicate masks for some objects
Updated 6 months ago
APn and APb
Closed 9 months ago2
Where is image_val_instances.json?
Updated 10 months ago
Unable to reproduce Swin-B
Updated 10 months ago3
Results clarification
Closed 10 months ago1
Reproduce OV2Seg results on LVVIS val and test set
Updated 10 months ago1
No such file or directory: 'datasets/lvis/lvis_v1_train_norare.json'
Closed a year ago1
Clarification on Training Details
Closed a year ago1
Some issues
Closed a year ago9
🙏[Request] Could you please provide the generation script of dataset class clip features?
Closed a year ago1
model mismatch and inference demo
Closed a year ago1
LV-VIS training dataset
Closed a year ago1
❓[Question] Is there any results about OV2Seg trained on LV-VIS datasets?
Closed a year ago1
About the category classification
Closed a year ago2
problem solved
Closed a year ago
training datasets
Closed a year ago2