Temporally Consistent Referring Video Object Segmentation with Hybrid Memory

Benchmark Model Rank Results
referring-expression-segmentation-on-davisHTR#4J&F 1st frame: 65.6
referring-expression-segmentation-on-refer-1HTR (Pre-training)#7J&F: 67.1J: 65.3F: 68.9
referring-video-object-segmentation-on-mevisHTR#8J&F: 42.7J: 39.9F: 45.5
referring-video-object-segmentation-on-referHTR#5J&F: 67.1J: 65.3F: 68.9