Universal Video Temporal Grounding with Generative Multi-modal Large Language Models

Open paper
Benchmark Model Rank Results
temporal-sentence-grounding-on-activitynet-captions-temporal-localization-val-2UniTime-SP (extra data)#12R1@0.5: 54.81R1@0.7: 36.62
moment-retrieval-on-charades-staUniTime-SP–R@1 IoU=0.5: 74.33R@1 IoU=0.7: 53.71

Rank counts only results with a code link.