Deeply Interleaved Two-Stream Encoder for Referring Video Segmentation

Benchmark Model Rank Results
referring-expression-segmentation-on-a2d-sentencesVLIDE–AP: 0.469IoU overall: 0.714IoU mean: 0.598Precision@0.5: 0.702…
referring-expression-segmentation-on-j-hmdbVLIDE–AP: 0.441IoU overall: 0.68IoU mean: 0.666Precision@0.5: 0.874…
referring-expression-segmentation-on-refer-youtube-vos-2021-public-validationVLIDE–J&F: 49.56J: 48.44F: 50.67