Temporally Consistent Referring Video Object Segmentation with Hybrid Memory

Benchmark Model Rank Results
referring-expression-segmentation-on-davis-2017-valHTR#4J&F 1st frame: 65.6
referring-video-object-segmentation-on-refer-youtube-vosHTR#6J&F: 67.1J: 65.3F: 68.9
referring-expression-segmentation-on-refer-youtube-vos-2021-public-validationHTR (Pre-training)#21J&F: 67.1J: 65.3F: 68.9
referring-video-object-segmentation-on-mevisHTR#30J&F: 42.7J: 39.9F: 45.5