Explore-And-Match: Bridging Proposal-Based and Proposal-Free With Transformer for Sentence Grounding in Videos

Benchmark Model Rank Results
temporal-sentence-grounding-on-activitynet-captions-temporal-localization-val-2LVTR-CLIP (extra data)#1mIoU: 53.0R1@0.5: 58.79R1@0.7: 33.38
moment-retrieval-on-charades-staLVTR-CLIP (extra data)#58R@1 IoU=0.5: 49.11R@1 IoU=0.7: 26.59R@5 IoU=0.5: 88.5…