Checkpoints and datasets for paper "Beyond Appearance: Geometric Cues for Robust Video Instance Segmentation".
Quanzhu Niu
QuanzhuNiu
AI & ML interests
Computer vision, Multi-modal,
Recent Activity
upvoted
a
paper
3 days ago
SAMTok: Representing Any Mask with Two Words
liked
a dataset
about 1 month ago
QuanzhuNiu/OVIS_RGBD
upvoted
a
paper
about 1 month ago
Depth Any Panoramas: A Foundation Model for Panoramic Depth Estimation