QD-DETR (only Video w/ PT ASR Captions)
Reported on 5 benchmarks across 1 task · 1 paper
Note: results are matched by exact model name. Different papers may use the same name for different model variants.
Computer Vision5 results
- R@1 IoU=0.5· 2023-03-2463.2best: 76.59 (LLaVA-MR)
- R@1 IoU=0.7· 2023-03-2445.2best: 61.48 (LLaVA-MR)
- mAP· 2023-03-2440best: 58.8 (SG-DETR (w/ PT))
- mAP@0.5· 2023-03-2463.4best: 76.2 (SG-DETR (w/ PT))
- mAP@0.75· 2023-03-2440.4best: 60.8 (SG-DETR (w/ PT))