Language-Bridged Spatial-Temporal Interaction for Referring Video Object Segmentation

Open paper
Benchmark Model Rank Results
referring-video-object-segmentation-on-mevisLBDT#16J&F: 29.3J: 27.8F: 30.8
referring-video-object-segmentation-on-ref-davis17LBDT#9J&F: 54.5

Rank counts only results with a code link.