Actor and Action Modular Network for Text-based Video Segmentation

Benchmark Model Rank Results
referring-expression-segmentation-on-a2d-sentencesAAMN–AP: 0.396IoU overall: 0.617IoU mean: 0.552Precision@0.5: 0.681…
referring-expression-segmentation-on-j-hmdbAAMN–AP: 0.321IoU overall: 0.583IoU mean: 0.576Precision@0.5: 0.773…