Training-Free Spatio-temporal Decoupled Reasoning Video Segmentation with Adaptive Object Memory

Open paper
Benchmark Model Rank Results
referring-video-object-segmentation-on-ref-davis17SDAM–J&F: 76.0J: 73.2F: 78.8
referring-video-object-segmentation-on-revosSDAM–J&F: 58.0J: 55.4F: 60.7

Rank counts only results with a code link.