$R^2$-Tuning: Efficient Image-to-Video Transfer Learning for Video Temporal Grounding

Benchmark Model Rank Results
highlight-detection-on-qvhighlightsR^2-Tuning#6mAP: 40.75Hit@1: 64.20
moment-retrieval-on-qvhighlightsR^2-Tuning#12mAP: 46.17R@1 IoU=0.5: 68.03R@1 IoU=0.7: 49.35mAP@0.5: 69.04