Asymmetric Cross-Guided Attention Network for Actor and Action Video Segmentation From Natural Language Query

Benchmark Model Rank Results
referring-expression-segmentation-on-a2d-sentencesACGA#12AP: 0.274IoU overall: 0.601IoU mean: 0.490Precision@0.5: 0.557…
referring-expression-segmentation-on-j-hmdbACGA#7AP: 0.289IoU overall: 0.576IoU mean: 0.584Precision@0.5: 0.756…