Sleeping
ReferDINO
🚀
Segment objects in videos using text descriptions
Tianming Liang
liangtm
AI & ML interests
None yet
Recent Activity
authored
a paper
about 9 hours ago
ReferDINO: Referring Video Object Segmentation with Visual Grounding
Foundations
authored
a paper
about 9 hours ago
PVUW 2025 Challenge Report: Advances in Pixel-level Understanding of
Complex Videos in the Wild
authored
a paper
about 9 hours ago
Progressive Pretext Task Learning for Human Trajectory Prediction
Organizations
