Modeling Motion with Multi-Modal Features for Text-Based Video Segmentation
Open paper
Benchmark
Model
Rank
Results
referring-expression-segmentation-on-a2d-sentences
mmmmtbvs
#9
AP: 0.419
IoU overall: 0.673
IoU mean: 0.558
Precision@0.5: 0.645
…
Rank counts only results with a code link.