MeViS: A Multi-Modal Dataset for Referring Motion Expression Video Segmentation
Paper
•
2512.10945
•
Published
Henghui Ding
HenghuiDing
AI & ML interests
None yet
Recent Activity
submitted
a paper
9 days ago
MeViS: A Multi-Modal Dataset for Referring Motion Expression Video Segmentation
liked
a dataset
13 days ago
FudanCVL/Cut-VOS
liked
a dataset
13 days ago
FudanCVL/MOSE
Organizations
submitted
a
paper
to Daily Papers
9 days ago
authored
a
paper
5 months ago