CamoSAM2: Motion-Appearance Induced Auto-Refining Prompts for Video Camouflaged Object Detection
Open paper
Benchmark
Model
Rank
Results
camouflaged-object-segmentation-on-moca-mask
CamoSAM2
–
S-measure: 0.765
weighted F-measure: 0.607
MAE: 0.007
mDice: 0.62
…
Rank counts only results with a code link.