Cross-Modal Self-Attention Network for Referring Image Segmentation

Benchmark Model Rank Results
referring-video-object-segmentation-on-refer-youtube-vosCMSA#13J&F: 36.4J: 34.8F: 38.1
referring-expression-segmentation-on-refcoco-plus-test-bCMSA#23Overall IoU: 37.89
referring-expression-segmentation-on-refcoco-plus-testaCMSA#28Overall IoU: 47.60
referring-expression-segmentation-on-refcoco-plus-valCMSA#33Overall IoU: 43.76
referring-expression-segmentation-on-refcoco-valCMSA#36Overall IoU: 58.32