SeViLA-Localizer

Reported on 3 benchmarks across 1 task

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision3 results

Moment RetrievalonQVHighlights
R@1 IoU=0.5
54.5
best: 76.59 (LLaVA-MR)
Moment RetrievalonQVHighlights
R@1 IoU=0.7
36.5
best: 61.48 (LLaVA-MR)
Moment RetrievalonQVHighlights
mAP
32.3
best: 58.8 (SG-DETR (w/ PT))