Context Modulated Dynamic Networks for Actor and Action Video Segmentation with Language Queries

Benchmark Model Rank Results
referring-expression-segmentation-on-a2d-sentencesCMDy–AP: 0.333IoU overall: 0.623IoU mean: 0.531Precision@0.5: 0.607…
referring-expression-segmentation-on-j-hmdbCMDy–AP: 0.301IoU overall: 0.554IoU mean: 0.576Precision@0.5: 0.742…