LLaVA-MR: Large Language-and-Vision Assistant for Video Moment Retrieval

Benchmark Model Rank Results
moment-retrieval-on-charades-staLLaVA-MR#2R@1 IoU=0.5: 70.65R@1 IoU=0.7: 49.58
moment-retrieval-on-qvhighlightsLLaVA-MR#4mAP: 52.73R@1 IoU=0.5: 76.59R@1 IoU=0.7: 61.48mAP@0.5: 69.41…
natural-language-moment-retrieval-on-activitynet-captionsLLaVA-MR#2R@1,IoU=0.5: 55.16R@1,IoU=0.7: 35.68