ReVisionLLM: Recursive Vision-Language Model for Temporal Grounding in Hour-Long Videos

Open paper
Benchmark Model Rank Results
natural-language-moment-retrieval-on-madReVisionLLM#1R@1,IoU=0.1: 17.3R@1,IoU=0.3: 12.7R@1,IoU=0.5: 6.7

Rank counts only results with a code link.