Referred by Multi-Modality: A Unified Temporal Transformer for Video Object Segmentation

Benchmark Model Rank Results
referring-video-object-segmentation-on-long-rvosMUTR#3J&F: 42.2tIoU: 70.4vIoU: 36.2
referring-expression-segmentation-on-refer-youtube-vos-2021-public-validationMUTR#17J&F: 68.4J: 66.4F: 70.4
referring-video-object-segmentation-on-ref-davis17MUTR#25J&F: 68.0J: 64.8F: 71.3