PhysMLLMs: Spatial Priors for Unified Referring Segmentation and Grounded Reasoning of Images and Videos
Open paper
Benchmark
Model
Rank
Results
referring-video-object-segmentation-on-mevis
PhysMLLMs
–
J&F: 55.1
referring-video-object-segmentation-on-ref-davis17
PhysMLLMs
–
J&F: 76.0
referring-video-object-segmentation-on-revos
PhysMLLMs
–
J&F: 57.4
Rank counts only results with a code link.