SARL-STG: A Spatially Aware Reinforcement Learning Framework for Refining MLLMs in Spatio-Temporal Video Grounding

Open paper
Benchmark Model Rank Results
moment-retrieval-on-charades-staSARL-STG–R@1 IoU=0.5: 73.6R@1 IoU=0.7: 49.1mIoU: 61.3

Rank counts only results with a code link.