Spectrum-guided Multi-granularity Referring Video Object Segmentation

Benchmark Model Rank Results
referring-expression-segmentation-on-a2d-sentencesSgMg (Video-Swin-B)#1AP: 0.585IoU overall: 0.799IoU mean: 0.720Precision@0.5: 0.843…
referring-expression-segmentation-on-j-hmdbSgMg (Video-Swin-B)#1AP: 0.450IoU overall: 0.737IoU mean: 0.725Precision@0.5: 0.972…
referring-expression-segmentation-on-davis-2017-valSgMg#5J&F 1st frame: 63.3
referring-video-object-segmentation-on-refer-youtube-vosSgMg#8J&F: 65.7J: 63.9F: 67.4
referring-expression-segmentation-on-refer-youtube-vos-2021-public-validationSgMg (Pre-training)#28J&F: 65.7J: 63.9F: 67.4
referring-video-object-segmentation-on-ref-davis17SgMg#32J&F: 63.3J: 60.6F: 66.0