From Semantics, Scene to Instance-awareness: Distilling Foundation Model for Grounded Open-vocabulary Situation Recognition
Open paper
Benchmark
Model
Rank
Results
grounded-situation-recognition-on-swig
MIPD
–
Top-1 Verb: 58.86
Top-1 Verb & Grounded-Value: 41.78
…
Rank counts only results with a code link.