Checkpoints and datasets for paper "Beyond Appearance: Geometric Cues for Robust Video Instance Segmentation".
👋 Open to Work
Quanzhu Niu
QuanzhuNiu
AI & ML interests
Computer vision, Multi-modal,
Recent Activity
authored a paper about 8 hours ago
SaSaSaSa2VA: 2nd Place of the 5th PVUW MeViS-Text Track authored a paper about 10 hours ago
Report of the 5th PVUW Challenge: Towards More Diverse Modalities in Pixel-Level Understanding liked a model about 15 hours ago
godx7/PixelEyes-8BOrganizations
