MeViS: A Multi-Modal Dataset for Referring Motion Expression Video Segmentation
Open paper
Benchmark
Model
Rank
Results
referring-video-object-segmentation-on-mevis
LMPM++
–
J&F: 47.6
J: 44.3
F: 50.9
referring-video-object-segmentation-on-ref-davis17
LMPM++
–
J&F: 65.0
J: 61.9
F: 68.1
Rank counts only results with a code link.