Text-Visual Prompting for Efficient 2D Temporal Video Grounding

Benchmark Model Rank Results
moment-retrieval-on-charades-staTVP (extra data)#65R@1 IoU=0.5: 44.39R@1 IoU=0.7: 21.51R@1 IoU=0.3: 65.92
moment-retrieval-on-charades-staTVP#66R@1 IoU=0.5: 44.39