UnLoc: A Unified Framework for Video Localization Tasks

Benchmark Model Rank Results
action-segmentation-on-coinUnLoc-L#1Frame accuracy: 72.8
natural-language-moment-retrieval-on-activitynet-captionsUnLoc-L#4R@1,IoU=0.5: 48.3R@1,IoU=0.7: 30.2R@5,IoU=0.5: 79.2…
natural-language-moment-retrieval-on-activitynet-captionsUnLoc-B#5R@1,IoU=0.5: 48.0R@1,IoU=0.7: 29.7R@5,IoU=0.5: 81.5…
moment-retrieval-on-charades-staUnLoc-L#29R@1 IoU=0.5: 60.8R@1 IoU=0.7: 38.4R@5 IoU=0.5: 88.2…
moment-retrieval-on-charades-staUnLoc-B#43R@1 IoU=0.5: 58.1R@1 IoU=0.7: 35.4R@5 IoU=0.5: 87.4…
temporal-action-localization-on-activitynet-1-3UnLoc-L#30mAP IOU@0.5: 59.3
moment-retrieval-on-qvhighlightsUnLoc-L#38R@1 IoU=0.5: 66.1R@1 IoU=0.7: 46.7
moment-retrieval-on-qvhighlightsUnLoc-B#39R@1 IoU=0.5: 64.5R@1 IoU=0.7: 48.8